agentleFS
Sign inStart free
wheslleyrimarwheslleyrimar/BuildCLI-Agents/.claude/skills/audit/SKILL.md

audit

Skill3 starsChanged 11 days agoMITView on GitHub

Check the implementation against the brief's acceptance criteria. Green/amber/red per criterion. Reads .buildcli/active automatically.

We split this skill into the rules it gives an agent

9 rules. 0 are common, 3 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 173 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read brief.md and extract the complete Acceptance Criteria list.

    line 25
  2. Very specific:

    Read the band tags in worklist.md to learn which bands this work touched.

    line 26
  3. Distinctive:

    Read only the changed files that fall inside the blueprint's bands.

    line 31
  4. Distinctive:

    Look for a test that exercises it.

    line 34
  5. Very specific:

    Run the suite and compare the quality gates from shape.md against the real result:

    line 36
  6. Very specific:

    Write the report to blueprints/<kind>/<slug>/audit.md.

    line 41
  7. Very specific:

    Never load context.md whole.

    line 81
  8. Distinctive:

    If the git history is ambiguous, ask which files to audit rather than guessing.

    line 85
  9. Very specific:

    Always save audit.md. An all-green record is still worth keeping.

    line 86

“Common” is measured: kept by at least 6 in 10 of the 173 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

Audit

Arguments

(optional) Path to a blueprint directory. Omitted → reads .buildcli/active.

Output

Audit report — green / amber / red per criterion, saved as audit.md.

Goal

Close the loop between what was asked for and what was written. Every acceptance criterion in brief.md gets a verdict backed by a file and a line — using the same narrow-context discipline as the rest of the pipeline.

Steps

  1. Resolve the blueprint directory: arguments if given, otherwise .buildcli/active.
    • .buildcli/active missing → stop, ask the user to run brief first.
  2. Read brief.md and extract the complete Acceptance Criteria list.
  3. Read the band tags in worklist.md to learn which bands this work touched.
  4. For each of those bands — and only those — load it with .buildcli/runtime/bcx band <name>.
  5. Collect the changed files:
    • git diff --name-only HEAD for uncommitted work.
    • Or, if brief.md carries a <!-- created: YYYY-MM-DD --> header, git log --since to find the relevant commits.
  6. Read only the changed files that fall inside the blueprint's bands.
  7. Rule on each criterion:
    • Find the behavior in the changed code.
    • Look for a test that exercises it.
    • Assign ✅ green (implemented and tested), ⚠️ amber (implemented, untested), ❌ red (not found).
  8. Run the suite and compare the quality gates from shape.md against the real result:
    .buildcli/runtime/bcx verify --json
    Report what it returns. A gate asserted without a run is not a gate.
  9. Write the report to blueprints/<kind>/<slug>/audit.md.
  10. Return the report inline plus the saved path.

Output format (audit.md)

# Audit: <Feature Name>
<!-- brief: <path> -->
<!-- audited: <YYYY-MM-DD> -->
<!-- verdict: green | amber | red -->

## Verdict: <overall>

## Acceptance Criteria

| # | Criterion | Status | Evidence |
|---|-----------|--------|----------|
| 1 | Given X When Y Then Z | ✅ green | src/api/checkout.ts:42, checkout.test.ts:18 |
| 2 | Given X When Y Then Z | ⚠️ amber | implemented in checkout.ts, no test found |
| 3 | Given X When Y Then Z | ❌ red   | not present in the changed files |

## Quality Gates

| Gate | Status | Detail |
|------|--------|--------|
| All tests pass | ✅ | 48/48 |
| Coverage ≥ 80% | ⚠️ | 74% — 6 points short |

## Gaps

- Criterion 3: what is missing, and where it belongs
- Coverage: which paths are untouched

## Next steps

- [ ] specific action that moves this to green

Rules

  • Never load context.md whole. Only the bands this blueprint actually touched.
  • Judge each criterion by reading the code and its tests; use .buildcli/runtime/bcx verify for the gate results, not to decide whether an individual criterion is satisfied.
  • Amber is not failure. It means the behavior works and the test is missing.
  • If the git history is ambiguous, ask which files to audit rather than guessing.
  • Always save audit.md. An all-green record is still worth keeping.

Download now (ZIP)

  • Other versions193 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 193

    1. openai/plugins★ 7.4ksame name
    2. ccch1mneyyy/dsh-TUI★ 6.5ksame name
    3. macro-inc/macro★ 6ksame name
    4. yournextstore/yournextstore★ 5.5ksame name
    5. gadievron/raptor★ 4ksame name
    6. alchemy-run/alchemy★ 1.8ksame name
    7. alchemy-run/alchemy-effect★ 1.8ksame name
    8. mattmireles/gemma-tuner-multimodal★ 1.5ksame name
    9. jsmastery-pro/skills★ 1.4ksame name
    10. nateherkai/AIS-OS★ 1.4ksame name

    183 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use delight, teach-impeccable and 10 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.
    • HK-hubSkill

      delight

      Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.

      Also in 32 projects that use this

    • HK-hubSkill

      teach-impeccable

      One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

      Also in 19 projects that use this

    • zwy123zwySkill

      normalize

      将用户随意输入的提示词规范化为结构清晰、便于大模型执行的标准化提示词。适用于需要整理、统一提示词格式时调用。

      Also in 19 projects that use this

    • ww-w-aiSkill

      pm-discovery

      PM Agent Team - Automated product discovery, strategy, and PRD generation. Runs PM analysis workflow to produce comprehensive PRD before PDCA Plan phase.

      Also in 3 projects that use this

    • ww-w-aiSkill

      qa-phase

      Run QA tests at various levels (L1-L5) for features under PDCA management. Integrates with MCP tools to execute structured test plans.

      Also in 3 projects that use this

    • +7 more from HK-hub
  • In this repository19 other files it gives its agents.

Does it work?

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

Reviews can't be read right now.

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.

Check your setup, free