AGENT SKILL

create-audit

Create an evidence-based audit document and save it to docs/audits/. Triggers on: "audit", "review", "assessment".

License 许可
MIT
最近更新
2026-10-26
Stars
★ 0
Forks
0

01 前言 Front Matter

name
create-audit
description
Create an evidence-based audit document and save it to docs/audits/. Triggers on: "audit", "review", "assessment".
allowed-tools
Read Grep Glob Bash Write
argument-hint
[subject]

03 SKILL.md 正文

Create a structured audit document and save it to the project's docs/audits/ directory.

Trigger: when the user asks for an audit, review, or assessment of any system, feature, data quality, process, or component. Also triggered directly via /create-audit.

Arguments: $ARGUMENTS — a description of what to audit (e.g. "data quality for user profiles", "API endpoint security", "deployment pipeline reliability").

Steps

  1. Parse the audit subject from $ARGUMENTS. If empty or vague, infer the subject from recent conversation context. If still unclear, ask the user what they want audited.

  2. Investigate the subject thoroughly. Read relevant source files, configs, logs, test results, git history, and any external state (API responses, deployment status) needed to form an evidence-based assessment. Do not guess — verify.

  3. Generate the audit document with this structure:

    # <Audit Title> — <YYYY-MM-DD>
    
    <One-line summary of what was audited and why.>
    
    ## Scope
    
    What was included and excluded from this audit.
    
    ## Findings
    
    ### <Finding Category 1>
    
    | Item | Status | Details |
    | ---- | ------ | ------- |
    | ...  | ...    | ...     |
    
    <Narrative explanation of the findings with evidence (file paths, line numbers, metrics, command output).>
    
    ### <Finding Category 2>
    
    ...
    
    ## Issues
    
    | Severity | Issue | Location | Recommendation |
    | -------- | ----- | -------- | -------------- |
    | CRITICAL | ...   | ...      | ...            |
    | WARNING  | ...   | ...      | ...            |
    | INFO     | ...   | ...      | ...            |
    
    If no issues: "No issues found."
    
    ## Summary
    
    <2-3 sentence verdict. What's healthy, what needs attention, what's the recommended next action.>
    
  4. Generate a filename in the format: <topic-slug>-<YYYY-MM-DD>.md (e.g. data-quality-2026-04-05.md, api-security-2026-04-09.md). Use lowercase kebab-case.

  5. Write the file to docs/audits/<filename>. Create the docs/audits/ directory if it doesn't exist.

  6. Report to the user: show the file path and a brief summary of findings (critical/warning/info counts). Do not dump the full document into chat. To turn a specific CRITICAL/WARNING finding into an isolated reproduction with a failing test, hand it to /reproduce-bug <finding>.

Rules

  • Every claim in the audit must be backed by evidence (a file read, command output, metric, or test result). No assumptions.
  • Severity levels: CRITICAL = broken or actively harmful, WARNING = degraded or risky, INFO = improvement opportunity.
  • Do not fix issues found. Report them. The user decides what to act on.
  • Do not commit the audit file. Leave it as an untracked file for the user to review.
  • Keep the document concise. Tables over prose where possible. No filler.

04 同仓库更多 Skills

kaiohenricunha
kaiohenricunha/dotbabel

yolo

Start temporary autonomy for the current task or an explicit scope with a required --for expiry. Codex permits scoped pushes, merges, deploys, and releases after strict testing and validation; Full access is a separate runtime setting. Claude Code uses a session permission hook with a protected-action denylist.

开发工程师
★ 0
kaiohenricunha
kaiohenricunha/dotbabel

veracity-audit

Audit a data pipeline for Veracity and Value. Dispatches data-scientist, compliance-auditor, and data-engineer agents with project context injected at dispatch time. All source paths are supplied via flags — no defaults, no project assumptions. Subcommands: audit (full pipeline walk), score-check (scoring math only), gate-check (gate coverage only), source-trace <label> (single source end-to-end). Invoke when: "audit pipeline", "veracity check", "scoring math correct?", "check gates", "trace source", "verify quality gates", "formula correct?".

律师与法务Skill与智能体开发
★ 0
kaiohenricunha
kaiohenricunha/dotbabel

validate-spec

Audit an already-implemented spec against the codebase. Walks each constraint (ARCH-N, PERF-N, KD-N, etc.) and acceptance criterion, grounds findings in file:line evidence, runs the spec.json acceptance_commands, and writes a single audit doc to docs/audits/. Use whenever the user asks to "validate a spec", "audit a spec", "check if spec is implemented", "verify the spec is done", "is this spec really done", or otherwise wants closure on spec-driven work. Read-only against the spec — produces an audit, never modifies the spec itself.

★ 0
kaiohenricunha
kaiohenricunha/dotbabel

terragrunt-specialist

Deep-dive Terragrunt hierarchy review, DRY pattern audits, and run-all orchestration analysis. Use for structured investigations of multi-environment Terragrunt layouts, dependency graphs, remote state config, and hook correctness. Triggers on: "Terragrunt audit", "run-all review", "dependency block", "DRY pattern review", "env hierarchy audit", "mock_outputs", "terragrunt hooks".

运维与部署
★ 0
kaiohenricunha
kaiohenricunha/dotbabel

terraform-specialist

Deep-dive Terraform architecture review, module design, state management, and migration. Use for structured investigations of Terraform workspaces, provider configuration, module coupling, import workflows, and test coverage. Triggers on: "Terraform audit", "module review", "state management", "Terraform import", "workspace design", "provider config review", "Terraform testing".

测试与质量运维与部署
★ 0
kaiohenricunha
kaiohenricunha/dotbabel

spec

Create structured engineering specs through interactive pairing. Use when the user wants to create a spec, design doc, technical specification, architecture document, RFC, or engineering plan. Triggers on "let's spec this out", "create a spec", "design doc", "write a technical plan", "plan the architecture". Works for greenfield and brownfield projects. Outputs to docs/specs/.

设计师视觉设计
★ 0