Skip to main content
skill CX Codex

creating-skills · osmontero — Claude Code skill: what it does, how to install

The creating-skills Claude Code skill helps create and revise other skills, then test how they perform. It activates for requests to draft a skill, evaluate its results, or adjust its trigger description.

Apache-2.0 101 installs ★ 18 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add osmontero/opencode-skills --skill creating-skills -a claude-code
Open on GitHub

What creating-skills does

The skill guides work from an initial idea to a tested draft, or helps improve an existing skill. It clarifies the intended task and trigger conditions, prepares a draft and test prompts, then supports reviewing the results and making revisions.

Testing follows a cycle: run the agent without the skill, run it with the skill, then address the gaps. The eval-viewer/generate_review.py script presents results for review. A separate description improver can refine the wording that controls triggering; the description limit is 500 characters.

What it helps with

  • draft a skill for a defined task
  • test a skill with sample prompts
  • compare agent runs with and without a skill
  • revise a trigger description

Example prompts for the agent

  • Create a skill for checking database migrations and draft test prompts.
  • Evaluate my skill with these examples and suggest changes based on the results.
  • Rewrite this skill description so it triggers on the right requests.

How to install creating-skills

1Skills CLI (Vercel)

npx skills add osmontero/opencode-skills --skill creating-skills -a claude-code

2Manually: put the files in place

~/.claude/skills/creating-skills/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/creating-skills/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about creating-skills

How do I install creating-skills in Claude Code?

Run npx skills add osmontero/opencode-skills --skill creating-skills -a claude-code. The skill file is at ~/.claude/skills/creating-skills/SKILL.md.

What does creating-skills do?

It helps draft and edit skills, test them with prompts, and refine the description that determines when a skill triggers.

How does creating-skills evaluate a skill?

It tests the agent without the skill, then with it. Results can be presented using eval-viewer/generate_review.py and used to guide revisions.

Source text

SKILL.md · Apache-2.0
---
name: creating-skills
description: Use when creating new opencode skills, modifying existing skills, or measuring skill performance. Triggers include requests to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
---

# Skill Creator

A skill for creating new skills and iteratively improving them.

**Core principle: Creating skills IS Test-Driven Development applied to process documentation.** Follow RED-GREEN-REFACTOR: run baseline tests without the skill (RED - watch agent fail), write the skill addressing those failures (GREEN - watch agent comply), then close loopholes (REFACTOR - stay compliant). If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.

At a high level, the process of creating a skill goes like this:

- Decide what you want the skill to do and roughly how it should do it
- Write a draft of the skill
- Create a few test prompts and run the agent with access to the skill on them
- Help the user evaluate the results both qualitatively and quantitatively
  - While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
  - Use the `eval-viewer/generate_review.py` script to show the user the results for them to look at, and also let them look at the quantitative metrics
- Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
- Repeat until you're satisfied
- Expand the test set and try again at larger scale

Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages. So for instance, maybe they're like "I want to make a skill for X". You can help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run all the prompts, and repeat.

On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop.

Of course, you should always be flexible and if the user is like "I don't need to run a bunch of evaluations, just vibe with me", you can do that instead.

Then after the skill is done (but again, the order is flexible), you can also run the skill description improver, which we have a whole separate script for, to optimize the triggering of the skill.

Cool? Cool.

## What Is a Skill

A **skill** is a reference guide for proven techniques, patterns, or tools. Skills help future agent instances find and apply effective approaches.

**Skills are:** Reusable techniques, patterns, tools, reference guides
**Skills are NOT:** Narratives about how you solved a problem once

### Skill Types

- **Technique**: Concrete method with steps to follow (e.g., condition-based-waiting, root-cause-tracing)
- **Pattern**: Way of thinking about problems (e.g., flatten-with-flags, test-invariants)
- **Reference**: API docs, syntax guides, tool documentation (e.g., office docs)

### When to Create a Skill

**Create when:**
- Technique wasn't intuitively obvious to you
- You'd reference this again across projects
- Pattern applies broadly (not project-specific)
- Others would benefit

**Don't create for:**
- One-off solutions
- Standard practices well-documented elsewhere
- Project-specific conventions (put in AGENTS.md)
- Mechanical constraints enforceable with regex/validation

## Communicating with the user

The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. If you haven't heard (and how could you, it's only very recently that it started), there's a trend now where the power of the agent is inspiring plumbers to open up their terminals, parents and grandparents to google "how to install npm". On the other hand, the bulk of users are probably fairly computer-literate.

So please pay attention to context cues to understand how to phrase your communication! In the default case, just to give you some idea:

- "evaluation" and "benchmark" are borderline, but OK
- for "JSON" and "assertion" you want to see serious cues from the user that they know what those things are before using them without explaining them

It's OK to briefly explain terms if you're in doubt, and feel free to clarify terms with a short definition if you're unsure if the user will get it.

---

## Creating a skill

### Capture Intent

Start by understanding the user's intent. The current conversation might already contain a workflow the user wants to capture (e.g., they say "turn this into a skill"). If so, extract answers from the conversation history first — the tools used, the sequence of steps, corrections the user made, input/output formats observed. The user may need to fill the gaps, and should confirm before proceeding to the next step.

1. What should this skill enable the agent to do?
2. When should this skill trigger? (what user phrases/contexts)
3. What's the expected output format?
4. Should we set up test cases to verify the skill works? Skills with objectively verifiable outputs (file transforms, data extraction, code generation, fixed workflow steps) benefit from test cases. Skills with subjective outputs (writing style, art) often don't need them. Suggest the appropriate default based on the skill type, but let the user decide.

### Interview and Research

Proactively ask questions about edge cases, input/output formats, example files, success criteria, and dependencies. Wait to write test prompts until you've got this part ironed out.

Check available MCPs - if useful for research (searching docs, finding similar skills, looking up best practices), research in parallel via subagents if available, otherwise inline. Come prepared with context to reduce burden on the user.

### Write the SKILL.md

Based on the user interview, fill in these components:

- **name**: Skill identifier. Use only letters, numbers, and hyphens. Prefer gerund form (verb + -ing) for processes: `creating-skills`, `testing-skills`. Name by what you DO or core insight, not generic terms.
- **description**: When to trigger. This is the primary triggering mechanism. **CRITICAL: Description = When to Use, NOT What the Skill Does.** Start with "Use when..." and include specific symptoms, situations, and contexts. Write in third person. **NEVER summarize the skill's process or workflow** — when a description summarizes workflow, the agent may follow the description instead of reading the full skill content. Keep under 500 characters. All "when to use" info goes here, not in the body. Note: currently the agent tends to "undertrigger" skills -- to not use them when they'd be useful. To combat this, please make the skill descriptions a little bit "pushy".
  - Include concrete triggers: error messages, symptoms, tool names, file types
  - Use synonyms: "timeout/hang/freeze", "cleanup/teardown/afterEach"
  - Describe the *problem* not *language-specific symptoms*
  - Make sure to use this skill whenever the user mentions relevant keywords, even if they don't explicitly ask for the skill by name
- **compatibility**: Required tools, dependencies (optional, rarely needed)
- **the rest of the skill :)**

### Skill Writing Guide

#### Anatomy of a Skill

```
skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter (name, description required)
│   └── Markdown instructions
└── Bundled Resources (optional)
    ├── scripts/    - Executable code for deterministic/repetitive tasks
    ├── references/ - Docs loaded into context as needed
    └── assets/     - Files used in output (templates, icons, fonts)
```

#### Progressive Disclosure

Skills use a three-level loading system:
1. **Metadata** (name + description) - Always in context (~100 words)
2. **SKILL.md body** - In context whenever skill triggers (<500 lines ideal)
3. **Bundled resources** - As needed (unlimited, scripts can execute without loading)

These word counts are approximate and you can feel free to go longer if needed.

**Key patterns:**
- Keep SKILL.md under 500 lines; if you're approaching this limit, add an additional layer of hierarchy along with clear pointers about where the agent using the skill should go next to follow up.
- Reference files clearly from SKILL.md with guidance on when to read them
- For large reference files (>300 lines), include a table of contents

**Domain organization**: When a skill supports multiple domains/frameworks, organize by variant:
```
cloud-deploy/
├── SKILL.md (workflow + selection)
└── references/
    ├── aws.md
    ├── gcp.md
    └── azure.md
```
the agent reads only the relevant reference file.

#### Principle of Lack of Surprise

This goes without saying, but skills must not contain malware, exploit code, or any content that could compromise system security. A skill's contents should not surprise the user in their intent if described. Don't go along with requests to create misleading skills or skills designed to facilitate unauthorized access, data exfiltration, or other malicious activities. Things like a "roleplay as an XYZ" are OK though.

#### Writing Patterns

Prefer using the imperative form in instructions.

**Incremental file writing (CRITICAL):** The model cannot output large files in a single call — each edit is limited to ~1000 tokens of output. Exceeding this causes API error 500. Always instruct agents to write large files incrementally:

1. Write the skeleton first (imports, signatures, section comments)
2. Fill in one section per edit call (~1000 tokens per chunk)
3. Final review and commit

Include this pattern in any skill that generates large outputs (documents, code files, configs). Example instruction to include:

```markdown
## Writing Large Files

This document may be large. Write it incrementally to avoid API errors:

1. **First pass:** Write the header, structure, and section outlines
2. **Subsequent passes:** Edit to fill in each section one at a time (~1000 tokens per edit)
3. **Final pass:** Review the complete document, fix issues, save
```

**Defining output formats** - You can do it like this:
```markdown
## Report structure
ALWAYS use this exact template:
# [Title]
## Executive summary
## Key findings
## Recommendations
```

**Examples pattern** - It's useful to include examples. You can format them like this (but if "Input" and "Output" are in the examples you might want to deviate a little):
```markdown
## Commit message format
**Example 1:**
Input: Added user authentication with JWT tokens
Output: feat(auth): implement JWT-based authentication
```

### Writing Style

Try to explain to the model why things are important in lieu of heavy-handed musty MUSTs. Use theory of mind and try to make the skill general and not super-narrow to specific examples. Start by writing a draft and then look at it with fresh eyes and improve it.

### Token Efficiency (Critical)

The context window is a shared resource. Every token in SKILL.md competes with conversation history and other context.

**Target word counts:**
- Frequently-loaded skills: <200 words total
- Other skills: <500 words (still be concise)

**Techniques:**
- **Default assumption: the agent is already very smart.** Only add context the agent doesn't already have. Challenge each piece: "Does the agent really need this explanation?"
- **Move details to tool help:** Instead of documenting all flags, reference `--help`
- **Use cross-references:** Reference other skills by name rather than repeating their workflows. Use `**REQUIRED SUB-SKILL:** Use skill-name` or `**REQUIRED BACKGROUND:** You MUST understand skill-name`. Never use `@` syntax — it force-loads files immediately, consuming context.
- **Compress examples:** One excellent example beats many mediocre ones. Don't implement in 5+ languages. Don't create fill-in-blank templates.
- **Eliminate redundancy:** Don't repeat what's in cross-referenced skills. Don't explain what's obvious from commands. Don't include multiple examples of the same pattern.
- **Avoid time-sensitive information:** Don't include dates that will become outdated. Use "old patterns" sections for deprecated approaches.
- **Use consistent terminology:** Choose one term and use it throughout.

### Code Examples

**One excellent example beats many mediocre ones.** Choose the most relevant language for the task (testing techniques → TypeScript/JS, system debugging → Shell/Python, data processing → Python). A good example is complete, runnable, well-commented explaining WHY, from a real scenario, and ready to adapt.

### Flowchart Usage

Use flowcharts (graphviz DOT format) ONLY for non-obvious decision points, process loops where the agent might stop too early, or "When to use A vs B" decisions. Never use flowcharts for reference material, code examples, linear instructions, or labels without semantic meaning.

See `references/graphviz-conventions.dot` for graphviz style rules. Use `render-graphs.js` to render flowcharts to SVG for your human partner:
```bash
./render-graphs.js ../some-skill           # Each diagram separately
./render-graphs.js ../some-skill --combine # All diagrams in one SVG
```

### Anti-Patterns

- **Narrative examples** ("In session 2025-10-03, we found...") — Too specific, not reusable
- **Multi-language dilution** (example-js.js, example-py.py, example-go.go) — Mediocre quality, maintenance burden
- **Code in flowcharts** — Can't copy-paste, hard to read
- **Generic labels** (helper1, step3, pattern4) — Labels should have semantic meaning
- **Too many options** — Don't present multiple approaches unless necessary. Provide a default with an escape hatch.
- **Deeply nested references** — Keep file references one level deep from SKILL.md. The agent may partially read files referenced from other referenced files.
- **Windows-style paths** — Always use forward slashes

### The Iron Law

```
NO SKILL WITHOUT A FAILING TEST FIRST
```

This applies to NEW skills AND EDITS to existing skills. Run a baseline scenario WITHOUT the skill before writing it. Watch the agent fail. Document exact rationalizations. Then write the skill addressing those specific failures.

**No exceptions:**
- Not for "simple additions"
- Not for "just adding a section"
- Not for "documentation updates"

### Test Cases

After writing the skill draft, come up with 2-3 realistic test prompts — the kind of thing a real user would actually say. Share them with the user: [you don't have to use this exact language] "Here are a few test cases I'd like to try. Do these look right, or do you want to add more?" Then run them.

Save test cases to `evals/evals.json`. Don't write assertions yet — just the prompts. You'll draft assertions in the next step while the runs are in progress.

```json
{
  "skill_name": "example-skill",
  "evals": [
    {
      "id": 1,
      "prompt": "User's task prompt",
      "expected_output": "Description of expected result",
      "files": []
    }
  ]
}
```

See `references/schemas.md` for the full schema (including the `assertions` field, which you'll add later).

### Testing All Skill Types

For discipline-enforcing skills specifically, the `testing-skills` skill covers the full RED-GREEN-REFACTOR campaign: writing pressure scenarios, capturing rationalizations verbatim, the four places to plug each loophole, and meta-testing when a skill is read and violated anyway.

Different skill types need different test approaches:

**Discipline-enforcing skills** (rules/requirements like TDD, verification-before-completion):
- Test with pressure scenarios combining 3+ pressures: time, sunk cost, authority, exhaustion
- Force explicit A/B/C choices, not open-ended questions
- Identify rationalizations and add explicit counters
- Success: Agent follows rule under maximum pressure

**Technique skills** (how-to guides):
- Test with application scenarios and edge cases
- Test for missing information and gaps in instructions
- Success: Agent successfully applies technique to new scenario

**Pattern skills** (mental models):
- Test recognition: Does agent know when pattern applies?
- Test counter-examples: Does agent know when NOT to apply?
- Success: Agent correctly identifies when/how to apply pattern

**Reference skills** (documentation/APIs):
- Test retrieval: Can agent find the right information?
- Test application: Can agent use what they found correctly?
- Gap testing: Are common use cases covered?
- Success: Agent finds and correctly applies reference information

### Bulletproofing Against Rationalization

For skills that enforce discipline, agents will find loopholes under pressure. Close every loophole explicitly:

1. **Explicit negation:** Don't just state the rule — forbid specific workarounds
2. **Rationalization table:** Capture every excuse agents make during testing
3. **Red flags list:** Make it easy for agents to self-check when rationalizing
4. **Foundational principle:** Add "Violating the letter of the rules is violating the spirit of the rules" to cut off "spirit vs letter" arguments

See `references/persuasion-principles.md` for research on how authority, commitment, and scarcity principles increase compliance.

## Running and evaluating test cases

**Before running any Python scripts, activate the opencode virtual environment:**

```bash
source ~/.local/opencode-venv/bin/activate
```

This section is one continuous sequence — don't stop partway through.

Put results in `<skill-name>-workspace/` as a sibling to the skill directory. Within the workspace, organize results by iteration (`iteration-1/`, `iteration-2/`, etc.) and within that, each test case gets a directory (`eval-0/`, `eval-1/`, etc.). **Each configuration (with_skill / without_skill / old_skill) must contain a `run-N/` subdirectory** — `aggregate_benchmark.py` only discovers runs that way, and it reads `run-N/grading.json` and `run-N/timing.json`. So a run lives at `iteration-<N>/eval-<ID>/<config>/run-<R>/`, with the subagent's outputs under `<config>/run-<R>/outputs/`. Don't create all of this upfront — just create directories as you go.

### Step 1: Spawn all runs (with-skill AND baseline) in the same turn

For each test case, spawn two subagents in the same turn — one with the skill, one without. This is important: don't spawn the with-skill runs first and then come back for baselines later. Launch everything at once so it all finishes around the same time.

**With-skill run:**

```
Execute this task:
- Skill path: <path-to-skill>
- Task: <eval prompt>
- Input files: <eval files if any, or "none">
- Save outputs to: <workspace>/iteration-<N>/eval-<ID>/with_skill/run-<R>/outputs/
- Outputs to save: <what the user cares about — e.g., "the .docx file", "the final CSV">
```

**Baseline run** (same prompt, but the baseline depends on context):
- **Creating a new skill**: no skill at all. Same prompt, no skill path, save to `without_skill/outputs/`.
- **Improving an existing skill**: the old version. Before editing, snapshot the skill (`cp -r <skill-path> <workspace>/skill-snapshot/`), then point the baseline sub-agent at the snapshot. Save to `old_skill/run-<R>/outputs/`.

Write an `eval_metadata.json` for each test case (assertions can be empty for now). Give each eval a descriptive name based on what it's testing — not just "eval-0". Use this name for the directory too. If this iteration uses new or modified eval prompts, create these files for each new eval directory — don't assume they carry over from previous iterations.

```json
{
  "eval_id": 0,
  "eval_name": "descriptive-name-here",
  "prompt": "The user's task prompt",
  "expectations": []
}
```

### Step 2: While runs are in progress, draft assertions

Don't just wait for the runs to finish — you can use this time productively. Draft quantitative assertions for each test case and explain them to the user. If assertions already exist in `evals/evals.json`, review them and explain what they check.

Good assertions are objectively verifiable and have descriptive names — they should read clearly in the benchmark viewer so someone glancing at the results immediately understands what each one checks. Subjective skills (writing style, design quality) are better evaluated qualitatively — don't force assertions onto things that need human judgment.

Update the `eval_metadata.json` files and `evals/evals.json` with the assertions once drafted. Also explain to the user what they'll see in the viewer — both the qualitative outputs and the quantitative benchmark.

### Step 3: As runs complete, capture timing data

When each sub-agent task completes, you receive a notification containing `total_tokens` and `duration_ms`. Save this data immediately to `timing.json` in the run directory:

```json
{
  "total_tokens": 84852,
  "duration_ms": 23332,
  "total_duration_seconds": 23.3
}
```

This is the only opportunity to capture this data — it comes through the task notification and isn't persisted elsewhere. Process each notification as it arrives rather than trying to batch them.

### Step 4: Grade, aggregate, and launch the viewer

Once all runs are done:

   1. **Grade each run** — spawn the `grader` global agent using the `subagent` tool (or grade inline) that evaluates each expectation against the outputs. The grader is read-only — it *returns* the grading JSON in its final message; you (the parent) save that to `<config>/run-<R>/grading.json`. The grading.json expectations array must use the fields `text`, `passed`, and `evidence` (not `name`/`met`/`details` or other variants) — the viewer depends on these exact field names. For assertions that can be checked programmatically, write and run a script rather than eyeballing it — scripts are faster, more reliable, and can be reused across iterations.

2. **Aggregate into benchmark** — run the aggregation script from the skill-creator directory:
   ```bash
   python -m scripts.aggregate_benchmark <workspace>/iteration-N --skill-name <name>
   ```
   This produces `benchmark.json` and `benchmark.md` with pass_rate, time, and tokens for each configuration, with mean ± stddev and the delta. If generating benchmark.json manually, see `references/schemas.md` for the exact schema the viewer expects.
Put each with_skill version before its baseline counterpart.

   3. **Do an analyst pass** — use the `analyzer` global agent to read the benchmark data and surface patterns the aggregate stats might hide. Look for things like assertions that always pass regardless of skill (non-discriminating), high-variance evals (possibly flaky), and time/token tradeoffs.

4. **Launch the viewer** with both qualitative outputs and quantitative data. It starts a local web server and opens a browser tab, so run it as a **background** shell command (`background: true` on the `shell` tool) and let the URL print to stdout:
   ```bash
   python <skill-creator-path>/eval-viewer/generate_review.py \
     <workspace>/iteration-N \
     --skill-name "my-skill" \
     --benchmark <workspace>/iteration-N/benchmark.json
   ```
   (Run as a background shell command so the viewer survives across turns; the URL is printed to stdout.)
   For iteration 2+, also pass `--previous-workspace <workspace>/iteration-<N-1>`.

   **Cowork / headless environments:** If `webbrowser.open()` is not available or the environment has no display, use `--static <output_path>` to write a standalone HTML file instead of starting a server. Feedback will be downloaded as a `feedback.json` file when the user clicks "Submit All Reviews". After download, copy `feedback.json` into the workspace directory for the next iteration to pick up.

Note: please use generate_review.py to create the viewer; there's no need to write custom HTML.

5. **Tell the user** something like: "I've opened the results in your browser. There are two tabs — 'Outputs' lets you click through each test case and leave feedback, 'Benchmark' shows the quantitative comparison. When you're done, come back here and let me know."

### What the user sees in the viewer

The "Outputs" tab shows one test case at a time:
- **Prompt**: the task that was given
- **Output**: the files the skill produced, rendered inline where possible
- **Previous Output** (iteration 2+): collapsed section showing last iteration's output
- **Formal Grades** (if grading was run): collapsed section showing assertion pass/fail
- **Feedback**: a textbox that auto-saves as they type
- **Previous Feedback** (iteration 2+): their comments from last time, shown below the textbox

The "Benchmark" tab shows the stats summary: pass rates, timing, and token usage for each configuration, with per-eval breakdowns and analyst observations.

Navigation is via prev/next buttons or arrow keys. When done, they click "Submit All Reviews" which saves all feedback to `feedback.json`.

### Step 5: Read the feedback

When the user tells you they're done, read `feedback.json`:

```json
{
  "reviews": [
    {"run_id": "eval-0-with_skill", "feedback": "the chart is missing axis labels", "timestamp": "..."},
    {"run_id": "eval-1-with_skill", "feedback": "", "timestamp": "..."},
    {"run_id": "eval-2-with_skill", "feedback": "perfect, love this", "timestamp": "..."}
  ],
  "status": "complete"
}
```

Empty feedback means the user thought it was fine. Focus your improvements on the test cases where the user had specific complaints.

Kill the viewer server when you're done with it — stop the background shell process that runs it (`Stop-Process` on the owning PID on Windows, `kill <pid>` on POSIX).

---

## STOP: Before Moving to Next Skill

**After writing ANY skill, you MUST STOP and complete the testing and deployment process.**

**Do NOT:**
- Create multiple skills in batch without testing each
- Move to next skill before current one is verified
- Skip testing because "batching is more efficient"

Deploying untested skills = deploying untested code.

## Improving the skill

This is the heart of the loop. You've run the test cases, the user has reviewed the results, and now you need to make the skill better based on their feedback.

### How to think about improvements

1. **Generalize from the feedback.** The big picture thing that's happening here is that we're trying to create skills that can be used a million times (maybe literally, maybe even more who knows) across many different prompts. Here you and the user are iterating on only a few examples over and over again because it helps move faster. The user knows these examples in and out and it's quick for them to assess new outputs. But if the skill you and the user are codeveloping works only for those examples, it's useless. Rather than put in fiddly overfitty changes, or oppressively constrictive MUSTs, if there's some stubborn issue, you might try branching out and using different metaphors, or recommending different patterns of working. It's relatively cheap to try and maybe you'll land on something great.

2. **Keep the prompt lean.** Remove things that aren't pulling their weight. Make sure to read the transcripts, not just the final outputs — if it looks like the skill is making the model waste a bunch of time doing things that are unproductive, you can try getting rid of the parts of the skill that are making it do that and seeing what happens.

3. **Explain the why.** Try hard to explain the **why** behind everything you're asking the model to do. Today's LLMs are *smart*. They have good theory of mind and when given a good harness can go beyond rote instructions and really make things happen. Even if the feedback from the user is terse or frustrated, try to actually understand the task and why the user is writing what they wrote, and what they actually wrote, and then transmit this understanding into the instructions. If you find yourself writing ALWAYS or NEVER in all caps, or using super rigid structures, that's a yellow flag — if possible, reframe and explain the reasoning so that the model understands why the thing you're asking for is important. That's a more humane, powerful, and effective approach.

4. **Look for repeated work across test cases.** Read the transcripts from the test runs and notice if the subagents all independently wrote similar helper scripts or took the same multi-step approach to something. If all 3 test cases resulted in the sub-agent writing a `create_docx.py` or a `build_chart.py`, that's a strong signal the skill should bundle that script. Write it once, put it in `scripts/`, and tell the skill to use it. This saves every future invocation from reinventing the wheel.

This task is pretty important (we are trying to create billions a year in economic value here!) and your thinking time is not the blocker; take your time and really mull things over. I'd suggest writing a draft revision and then looking at it anew and making improvements. Really do your best to get into the head of the user and understand what they want and need.

### The iteration loop

After improving the skill:

1. Apply your improvements to the skill
2. Rerun all test cases into a new `iteration-<N+1>/` directory, including baseline runs. If you're creating a new skill, the baseline is always `without_skill` (no skill) — that stays the same across iterations. If you're improving an existing skill, use your judgment on what makes sense as the baseline: the original version the user came in with, or the previous iteration.
3. Launch the reviewer with `--previous-workspace` pointing at the previous iteration
4. Wait for the user to review and tell you they're done
5. Read the new feedback, improve again, repeat

Keep going until:
- The user says they're happy
- The feedback is all empty (everything...

© osmontero · Apache-2.0 · osmontero/opencode-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

creating-skills by other authors comes first.

creating-skills fvadicamo creating-skills is a Claude Code skill that guides the creation and revision of skills, including their SKILL.md files. It activates for requests about skill structure, naming, or setup. CX Codex +1 208installs create-tooluniverse-skill mims-harvard create-tooluniverse-skill is a Claude Code skill that builds production-ready ToolUniverse skills in seven phases, from tool testing to documentation and validation. CX Codex +1 416installs creating-online-evaluations PostHog creating-online-evaluations — a Claude Code skill that turns production failure modes into continuously-running online evaluations in PostHog. It starts when new generations need automatic scoring against specific errors. CX Codex +1 195installs bmad-eval bmad-code-org bmad-eval — a skill for Claude Code, Codex, Cursor and Copilot that runs another skill's test suite and reports findings. Triggers when you need to check description accuracy, compare versions or grade output against a rubric. CX Codex +1 9,100installs eval-harness affaan-m eval-harness — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that brings eval-driven development into every agent session: success criteria go in before any code, results are scored with pass@k and pass^k. CX Codex +1 6,500installs adk-evals botpress adk-evals is a Claude Code skill that documents how to write and run conversation evals for Botpress ADK agents. It helps inspect tool parameters, bot state, and workflows without mocks. CX Codex +1 1,700installs inngest-agent-evals inngest inngest-agent-evals guides the setup of production AI agent evaluations, direct and deferred scoring, session grouping, and prompt experiments in Inngest workflows. CX Codex +1 635installs

From the same set11

The whole set →
reviewing-interface-quality reviewing-interface-quality audits an existing interface with screenshots, browser data, and CSS values. Use it before shipping or when a page feels unfinished. CX Codex +1 451installs testing-webapps testing-webapps lets an agent test your local web app in a real browser: it writes a Python Playwright script, starts the servers, and reports what the page actually does. CX Codex +1 192installs reviewing-security The reviewing-security skill reviews code before a merge or release by tracing attacker-controlled input to the operation and impact it can reach. CX Codex +1 185installs investigating-performance investigating-performance stops coding agents from guessing at performance bottlenecks by enforcing strict baselines, target metrics, and dimensioned profiling before touching code. CX Codex +1 146installs applying-themes applying-themes puts one palette of eight semantic tokens on a deck, report or HTML page, then verifies the contrast with a bundled script. CX Codex +1 139installs evolving-apis-and-schemas The evolving-apis-and-schemas Claude Code skill assesses changes to APIs and data schemas. It activates when other services, clients, or stored data depend on the shape being changed. CX Codex +1 115installs executing-plans The executing-plans Claude Code skill carries out a written implementation plan in stages, with checks between batches. It activates when subagents cannot be used or tasks are too coupled to split up. CX Codex +1 107installs using-git-worktrees The using-git-worktrees Claude Code skill sets up a separate Git worktree for a task. It kicks in before feature work or an implementation plan when the current checkout should stay untouched. CX Codex +1 103installs

Project sponsors

Companies that keep this analytics open