llm-friendly-context — Claude Code skill: what it does, how to install
llm-friendly-context rewrites prompts, handoffs and generated docs so the next agent can see the inputs, the steps and what counts as done. Useful whenever text goes to another model.
MIT ★ 720 updated 2026-10-29
npx skills add shinpr/claude-code-workflows --skill llm-friendly-context -a claude-codeWhat llm-friendly-context does
The skill edits text that another model will act on: prompts, handoffs, plans, reviews, reports, generated instructions. One goal sits behind it — the next executor knows what to read, what to do, what counts as success and which decisions are still open.
SKILL.md holds seven rules, a rewrite table and two checklists, one for a handoff and one for a finished artifact. The table targets specific wording such as appropriate, as needed, per convention, related files, placeholder, TBD. Each of those gets replaced with a condition, a path or a measurable criterion.
A prohibition survives only where it guards an irreversible boundary or a shipped contract, and then it must name the protected condition next to the allowed action. The skill works on wording, not on code. When a task is vague in substance, swapping appropriate for a measurable criterion will not fix it, and the open question goes back to whoever owns the decision.
What it helps with
- rewrite a prompt so the next model stops guessing
- swap
as neededin a handoff for a trigger condition and an action - run a pre-send checklist before another agent picks up the artifact
- log open questions with a decision owner and their effect on the result
- trim context down to what the step actually consumes
Example prompts for the agent
- Rewrite
handoff.mdwith the llm-friendly-context rules: name the inputs, the steps and the success criteria. - Run the handoff checklist from llm-friendly-context over this prompt and show me what is still vague.
- Turn this report into something the next agent can act on without asking questions.
How to install llm-friendly-context
1Skills CLI (Vercel)
npx skills add shinpr/claude-code-workflows --skill llm-friendly-context -a claude-code2Manually: put the files in place
~/.claude/skills/llm-friendly-context/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llm-friendly-context/
1Skills CLI (Vercel)
npx skills add shinpr/claude-code-workflows --skill llm-friendly-context -a codex2Manually: put the files in place
.agents/skills/llm-friendly-context/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add shinpr/claude-code-workflows --skill llm-friendly-context -a cursor2Manually: put the files in place
.cursor/skills/llm-friendly-context/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install shinpr/claude-code-workflows dev-skills/skills/llm-friendly-context2Manually: put the files in place
.github/skills/llm-friendly-context/SKILL.md1Skills CLI (Vercel)
npx skills add shinpr/claude-code-workflows --skill llm-friendly-context -a gemini-cli2Platform CLI
gemini skills install https://github.com/shinpr/claude-code-workflows --path dev-skills/skills/llm-friendly-contextManually: put the files in place
.devin/skills/llm-friendly-context/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about llm-friendly-context
How do I install llm-friendly-context in Claude Code?
Run npx skills add shinpr/claude-code-workflows --skill llm-friendly-context -a claude-code. The skill file then sits at ~/.claude/skills/llm-friendly-context/SKILL.md.
What does llm-friendly-context do?
It shapes prompts, handoffs and generated documents so the next executor can act without guessing: inputs, steps, acceptance criteria and open questions with their owner are spelled out.
Does the skill keep negative instructions?
Only when a prohibition guards an irreversible boundary or a shipped contract, and then it has to name the protected condition plus the allowed alternative. Everything else becomes a positive instruction.
Source text
SKILL.md · MIT
--- name: llm-friendly-context description: Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions. --- # LLM-Friendly Context The goal is stable downstream execution: the next consumer should know what to read, what to do, what counts as success, and which unresolved decisions can change the result. ## Core Rules 1. **Use positive, executable instructions** - State what the next consumer should do. - Convert quality policies into positive criteria. - Keep a prohibition only when it protects an irreversible boundary or shipped contract. Name the protected condition and the allowed action. - Example: "Preserve existing public API behavior across the documented compatibility cases." 2. **Make vague instructions concrete** - Clarify wording when plausible interpretations would change the outcome, scope, authority or proof. Supply purpose, evidence and selection criteria for reversible choices; reserve exact selections for actual consumer contracts and user-owned decisions. - Terms that often need clarification when they leave a decision to the next consumer: `appropriate`, `proper`, `related`, `existing behavior`, `optional`, `as needed`, `if needed`, `per convention`, unresolved alternatives, `TBD`, `placeholder`. 3. **Specify output shape** - Use the sections, fields, table columns, JSON keys, or checklist items the consumer uses. - For handoffs, include only produced artifact paths and status fields that control the next transition. 4. **Provide the smallest sufficient context** - Sufficient means sufficient for the assigned action, not complete background: every item you include is consumed by that action or by the result it must produce. - Include the purpose, source artifacts, hard constraints, accepted decisions, and unresolved conditions that action consumes. - Prefer concrete file paths and section hints over broad module names. - Follow references while they can change an in-scope decision, action, or verification result. 5. **Decompose complex work into verifiable steps** - Expose real dependencies and their completion evidence. Let independent reversible work follow the route suited to the task. - Each step needs a checkpoint: what evidence proves it is complete. 6. **Permit uncertainty explicitly** - Resolve missing operational detail from referenced artifacts and repository evidence before treating it as unresolved. - Record remaining uncertainty with its effect, required input, and decision owner. Make reversible repository-local choices when governing evidence resolves them. 7. **Keep constraints proportionate** - Add only constraints that reduce ambiguity or preserve a real requirement. - Keep simple downstream tasks lightweight when the target action, context, and success criteria are already clear. - Interpret minimal as the least downstream complexity that fully solves the problem. An explicit user diff limit is a constraint; otherwise necessary corrections are not bounded by a line count. ## Rewrite Patterns Use these rewrites before treating a prompt, handoff, or artifact as complete. | Ambiguous form | Rewrite as | |---|---| | `optional` used as an unresolved choice | Required, omitted, or required only under a named condition | | Alternatives whose choice changes a protected outcome | The governing constraint or unresolved owner decision; for reversible choices, purpose, evidence and selection criteria | | `as needed` / `if needed` | The triggering condition and required action | | `per convention` | The file, function, test, or documented convention to follow | | `related files` | Specific paths, globs, or search hints | | `existing behavior` | The observable behavior, source file, test, API response, or UI state to preserve | | `placeholder` | Exact temporary value/behavior, allowed dependencies, and verification expectation | | `TBD` used as a placeholder for required information | A blocking unresolved item with owner, required input, and decision effect | | `appropriate` / `proper` | A measurable criterion or checklist | ## Handoff Checklist Before sending a prompt or artifact to another consumer, verify: - [ ] The target action is explicit. - [ ] Required input paths, source artifacts, and decision-relevant facts are named. - [ ] Every included context item is consumed by the target action or its required result. - [ ] Accepted decisions and constraints use one canonical wording. - [ ] Output format or expected status fields are specified. - [ ] Success criteria are observable. - [ ] Outcome-relevant ambiguities are resolved or assigned to their decision owner; harmless execution flexibility remains. - [ ] Each instruction states the allowed action; each retained prohibition names the protected condition and allowed alternative. - [ ] The next consumer can complete its scope from the supplied purpose, sources, criteria, and evidence, or return the exact unresolved decision and owner. ## Generated Artifact Checklist Before writing or finalizing a generated document: - [ ] Each requirement, claim, task, test skeleton, or review finding has enough source context to trace why it exists. - [ ] Every executable instruction names the target, action, and expected result. - [ ] Verification steps say what to run or observe and what result proves success. - [ ] Each instruction states the allowed action; each retained prohibition names the protected condition and allowed alternative. - [ ] If an artifact is derived from another artifact, copied decisions stay consistent in wording and meaning. - [ ] If downstream work is blocked by missing information, the artifact records the missing input, decision owner, and effect.
© shinpr · MIT · shinpr/claude-code-workflows