implement · rsmdt — Claude Code skill that runs a spec through a code→eval loop
An implementation orchestrator that reads slice and scenario tasks from the spec tracker, then launches a workflow which builds each slice and retries code→eval until holdout scenarios pass.
MIT ★ 587 updated 2026-10-26
/plugin marketplace add rsmdt/the-startup
/plugin install start@the-startupWhat implement does
The implement skill handles execution of a finished specification. It does not write product code itself. Instead it resolves the spec, reads the task graph, discovers service configuration, and launches one dynamic workflow. That workflow owns the loop: build a slice, evaluate it, retry if holdout scenarios fail the threshold.
Every plan phase is a root task with slice children, and each slice carries scenario children as acceptance evidence. The skill reads structure only — ids, dependencies, scenario counts. Slice and scenario bodies stay unread, so nothing leaks across the barrier: the code agent sees only its slice, the eval agent only that slice's scenarios.
Threshold and iteration count come from the plan doc's frontmatter. Defaults are 0.90 and 3. The service starts once before launch, configured, and every eval runs read-only against it. Holdout scripts and screenshots go to an eval directory outside the project, out of the code agents' reach.
The skill refuses to launch if a slice has no scenario child or service configuration is unresolved. It asks for configuration before launching, never mid-run. No spec or no plan means it stops and points to /start:specify.
What it helps with
- build every slice of each phase from a finished spec
- run a code→eval loop with automatic retries
- keep an information barrier between code and eval agents
- start a service once and evaluate scenarios read-only
- record per-slice results in the tracker
Example prompts for the agent
- Implement spec 002
- Run the build for spec 002 with threshold 0.90 and up to 3 iterations per slice
- Start the dynamic workflow for spec 002 and show the slice results when it returns
How to install implement
1Plugin marketplace
/plugin marketplace add rsmdt/the-startup/plugin install start@the-startupThis installs the whole start plugin with all its skills
2Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill implement -a claude-code3Manually: put the files in place
~/.claude/skills/implement/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/implement/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill implement -a codex2Manually: put the files in place
.agents/skills/implement/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill implement -a cursor2Manually: put the files in place
.cursor/skills/implement/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rsmdt/the-startup plugins/start/skills/implement2Manually: put the files in place
.github/skills/implement/SKILL.md1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill implement -a gemini-cli2Platform CLI
gemini skills install https://github.com/rsmdt/the-startup --path plugins/start/skills/implementManually: put the files in place
.devin/skills/implement/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 implement
How do I install the implement skill in Claude Code?
Through the marketplace: /plugin marketplace add rsmdt/the-startup, then /plugin install start@the-startup. Or run npx skills add rsmdt/the-startup --skill implement -a claude-code, which puts the skill at ~/.claude/skills/implement/SKILL.md.
What does the implement skill do?
It launches implementation of a completed spec: reads slices and scenarios from the tracker, resolves service configuration, and starts a workflow that builds each slice and runs a code→eval retry loop until holdout scenarios meet the threshold.
What do I need before running it?
A spec with a plan doc whose frontmatter has threshold and max_iterations. Service details should live in project instructions or package.json: startCommand, servicePort, healthPath, requiredEnv. If there are database migrations, migrateCommand must be a binary resolvable by which, not an npx or version-manager shim.
Source text
SKILL.md · MIT
---
name: implement
description: Implementation entry point. Use to execute a completed specification. Reads the spec's slice and scenario tasks from the tracker, then runs a dynamic workflow that builds each phase's slices and evaluates the phase through a barriered code→eval retry loop until every slice's holdout scenarios pass the threshold.
user-invocable: true
argument-hint: "spec ID to implement (e.g., 002)"
---
## Persona
Act as the implementation orchestrator. You resolve the spec, gather everything the build loop needs,
then author and run **one dynamic workflow** (the Workflow tool with an inline script you write) that
builds every slice. You do **not** write product code and you do **not** hand-run the loop — the
workflow holds the loop, the branching, and the retries as code.
Everything is a task (`task.js`). Each plan phase is a root **phase** task with **slice** child tasks
(each body is a code brief) and, under each slice, **scenario** child tasks (the holdout acceptance
evidence). specify-plan authors them; you read their structure.
**Implementation Target**: $ARGUMENTS
## Constraints
**Always:**
- Resolve the spec via the specify-meta skill; read the task graph with `task.js graph`.
- Read task **structure only** — ids, `dependsOn`, scenario counts. Never open a slice or scenario body yourself: you write every agent's prompt, so whatever you read can leak across the barrier.
- Preserve the information barrier inside the workflow: the code agent reads only its **slice** task; the eval agent reads only that slice's **scenario** child tasks.
- Take `threshold` and `max_iterations` from the frontmatter of the spec's `plan_doc` (`spec.md`; `plan.md` in a legacy spec); the workflow, not you, decides pass/fail and retries.
- Ask the user only for service configuration you cannot discover — before launching, never mid-run. Never ask to confirm what you read from a file.
- Present the per-slice results when the workflow returns; the tracker already reflects final status.
**Never:**
- Implement code directly, or run the code→eval loop outside the workflow.
- Author or modify specification artifacts beyond the run's status reconciliation.
- Launch with a slice that has no scenario child task, or with an unresolved service configuration.
## Reference Materials
- [Loop Contract](reference/loop.md) — the workflow's stages, agent return schemas, decision rules, and result shape
- [Code Agent](reference/code-agent.md) — prompt for the build stage
- [Eval Agent](reference/eval-agent.md) — prompt for the evaluation stage
- [Coverage Agent](reference/coverage-agent.md) — prompt for the spec-coverage audit
- [Preflight Agent](reference/preflight-agent.md) — prompt for the harness assertion
- [Service Agent](reference/service-agent.md) — prompt for restarting the service before each evaluation
## Workflow
### 1. Resolve Spec
Use the specify-meta skill with `$ARGUMENTS` to resolve the spec directory and `specId`. If no spec
exists, say so and suggest `/start:specify`; stop.
Read the `plan_doc` frontmatter for `threshold` (default 0.90) and `max_iterations` (default 3). If the
spec has no `plan_doc`, tell the user the spec has no plan and offer to run `/start:specify`; stop.
### 2. Read the Task Graph
`node ${CLAUDE_PLUGIN_ROOT}/scripts/task.js graph --spec {specId}`. Pass that absolute `task.js` path to the
workflow — its agents call it.
Identify the **phase** roots (id, `dependsOn`), each phase's **slice** children (id, `dependsOn`,
status), and each slice's count of **scenario** children. Leave out slices whose status is `passed`
(already built) or `building` (another run is building them), and phases left with no slice — the plan
may still be growing while earlier phases are built. Stop and point the user at `/start:specify` if
there is no phase root, no slice to build, a slice with zero scenarios, or a dependency cycle.
### 3. Order into Phases and Groups
Order the phases by their `dependsOn`. Within each phase, topologically sort its slices by `dependsOn`:
slices whose dependencies are all satisfied by earlier groups share one parallel group; a dependency on
a slice of an earlier phase, or on a non-slice id, does not block.
### 4. Discover Service Configuration
From the project instructions file and package.json (or equivalent) determine `startCommand`,
`servicePort`, `healthPath` (default `/health`), `requiredEnv` (env vars the scenarios depend on), and
`migrateCommand` when the project has database migrations. `migrateCommand` must be a directly
executable binary resolved with `which` — never an `npx` / `pnpm dlx` / version-manager shim. Run it once
yourself; fix or omit it if it errors. Ask the user for anything you could not read from a file.
Start the service once, configured, before launching. Every eval agent evaluates against it read-only.
Create `evalDir` — `${TMPDIR:-/tmp}/start-eval-{specId}`, as an absolute path outside the project. The
eval agents keep their holdout scripts and screenshots there, out of the code agents' reach.
### 5. Run the Dynamic Workflow
These instructions are the opt-in: call the Workflow tool directly with an inline script. Do not load the workflow-authoring reference or assemble the script through shell commands first — runs that detour through either stall before launching. Read reference/loop.md and the five agent references. Author one workflow script that implements the
loop contract exactly, with each agent's prompt taken from its reference and its placeholders filled
from steps 1–4. Launch it with the Workflow tool, passing the resolved values as `args`.
Choose `model` and `effort` per stage from what the stage does. Mechanical stages — running a command,
checking a URL, mapping text into a fixed schema — can run on a smaller, faster model at lower effort.
Code agents and the stages that judge another agent's work omit `model`, so they run on the session
model. When unsure, omit `model`.
Record the launch: `node ${CLAUDE_PLUGIN_ROOT}/scripts/spec.js {specId} --event '{"kind":"run","state":"started","threshold":<threshold>,"maxIterations":<max_iterations>}'`.
Present a one-line dispatch summary before launching:
```
Implementing spec {specId}: {sliceCount} slices in {phaseCount} phases (threshold {pct}%, max {n} iterations/slice) → dynamic workflow
```
The run executes in the background. Do not re-run the loop yourself or fabricate progress.
### 6. Report and Finalize
When the workflow returns (shape in reference/loop.md), record one `result` event per slice result
(`{"kind":"result","id":"<sliceId>","result":"<status>","business":<n>,"technical":<n>,"iterations":<n>}`,
leaving out a score the slice never got), then `{"kind":"run","state":"ended"}`, with
`node ${CLAUDE_PLUGIN_ROOT}/scripts/spec.js {specId} --event`.
1. A run-level `status` means nothing was built — report why and stop; never present it as zero slices
completed.
2. Present per slice: status, **business %** and **technical %**, iterations used. For `failed`, show the
symptoms and its `type: bug` child tasks. For `incomplete-coverage`, show `coverageGaps` and
`notExercisable` — both are spec gaps, not build failures.
An `incomplete-coverage` slice cleared both thresholds: it is built. Record its gaps as known gaps in
the Ledger part of `spec.md` and do not relaunch it. Recommend adding scenarios and relaunching only for
`business` gaps — a missing proof of a requirement; `technical` gaps are recorded, not re-run.
3. Three statuses mean the code was never judged:
- `blocked-environment` — report the faults and stop; do not relaunch until the user confirms the
environment is fixed.
- `stalled` — the loop stopped converging with retries left. Report the attempt history and ask for
guidance rather than relaunching unchanged.
- `harness-abort` — agents stopped being served. Offer to relaunch the same slices once available.
4. Only when a slice is not built (`failed`, `stalled`, `blocked-environment`, `harness-abort`), ask how to
proceed: retry with guidance, add the missing scenarios, skip, or stop. Recorded gaps and `bug` tasks of
a built slice are not open work: list them without offering a re-run.
5. Use the validate skill in constitution mode if a CONSTITUTION.md exists at the project root.
6. If every slice is `completed`, say so and name the next commands — commit per project convention and
`/start:archive {specId}` — without asking; git and archiving stay the user's call.
© Rudolf S. · MIT · rsmdt/the-startup
Similar skills
All skills for Agent setup: memory, context, orchestration →implement by other authors comes first.