agentleFS
charliehzmcharliehzm/medharness/.claude/skills/openspec-apply-change/SKILL.md

openspec-apply-change

Skill85 starsChanged 6 months agoApache-2.0View on GitHub

Use this skill at Step 6 of the v2 SOP to implement one task from the change's tasks/ directory at a time. Each invocation should produce a code diff for exactly one task document, touching ≤ 2 files, with prompts pre-routed through mcp-model-router and any L3/L4 text pre-desensitized via phi-desensitize. Updates the task document checkbox upon completion. Chinese trigger examples: "执行任务", "OpenSpec apply", "Step 6", "实现 任务", "应用变更". Do NOT use to implement multiple tasks at once, do NOT use without an active MODEL_ALLOWLIST, do NOT use bypassing phi-desensitize for L3/L4 text. Success = one task's diff produced, ≤ 2 files touched, task checkbox flipped, all model calls routed through mcp-model-router.

148 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use source-command-opsx-apply, source-command-opsx-archive and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • antech2-asyncSkill

    source-command-opsx-apply

    Implement tasks from an OpenSpec change (Experimental)

    Also in 5 projects that use this

  • antech2-asyncSkill

    source-command-opsx-archive

    Archive a completed change in the experimental workflow

    Also in 5 projects that use this

  • Microsoft AzureSkill

    openspec-update-change

    Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.

    Also in 94 projects that use this

  • MicrosoftSkill

    openspec-ff-change

    Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.

    Also in 62 projects that use this

  • MicrosoftSkill

    openspec-onboard

    Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.

    Also in 59 projects that use this

  • goernSkill

    draft-openspec-docs

    Collaborative page-drafting mode for the OpenSpec docs. Builds a scratch plan inside the target page (purpose, structure, numbered draft steps), iterates on it with the user, then drafts one section per approved step and cleans up after itself. Use when a page needs a from-scratch rewrite or a new page is being shaped with the user in the loop.

    Also in 3 projects that use this

  • +2 more from antech2-async
  • +1 more from microsoft

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 144 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the task document; do exactly what it says.

    line 32
  2. Distinctive:

    Do not bundle unrelated cleanup.

    line 33
  3. Distinctive:

    Do not refactor adjacent code.

    line 34
  4. Distinctive:

    Do not add comments unless WHY is non-obvious.

    line 35
  5. Very specific:

    If the task is wrong/incomplete, stop and route to prd-implementation-precheck instead.

    line 36
  6. Distinctive:

    Read the linked spec(s) for acceptance criteria.

    line 41
  7. Very specific:

    If any data-handling code involves L3/L4 → call phi-desensitize first.

    line 42
  8. Distinctive:

    Run quick local sanity (type-check, single test).

    line 45
  9. Distinctive:

    Do NOT mark the OpenSpec change as done — that's Step 7 Verify.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 144 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

OpenSpec Apply Change

The implementation step. One task per invocation. Stay in scope.

Discipline

  • Read the task document; do exactly what it says.
  • Do not bundle unrelated cleanup.
  • Do not refactor adjacent code.
  • Do not add comments unless WHY is non-obvious.
  • If the task is wrong/incomplete, stop and route to prd-implementation-precheck instead.

Workflow

  1. Open the task document.
  2. Read the linked spec(s) for acceptance criteria.
  3. If any data-handling code involves L3/L4 → call phi-desensitize first; never paste raw values.
  4. Plan diff mentally; if > 2 files needed, re-decompose (call task-decomposition).
  5. Apply changes.
  6. Run quick local sanity (type-check, single test).
  7. Flip the task document checkbox to [x].
  8. Do NOT mark the OpenSpec change as done — that's Step 7 Verify.

Common failure modes

  1. Scope creep — "while I'm here, let me also fix..." . Mitigation: discipline; flag adjacent issues to spawn_task-style follow-up, not inline.
  2. Bigger diff than spec — finish the task with 4 files. Mitigation: pause at file 2; re-decompose.
  3. PHI in prompt — pasted real schema row including patient_id. Mitigation: hook + skill enforcement.
  4. Comments that re-describe code — adds noise. Mitigation: comments only where WHY is non-obvious.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.