Automated summary
Performs a read-only, post-run inspection of completed artifacts to surface drift, inconsistencies, omissions, and unsupported claims.
Strengths
- Scope is selectable via --scope (auto, facts, style, structure, cross-ref, coverage, all) alongside flags such as --read-only, --report-only, and --no-fact-check.
- Read-only/report-only posture: findings are surfaced without modifying the artifact.
- Explicit pre-approval boundary: no references are loaded and no work starts before the route is confirmed.
- Reinforces artifact, worktree, role, and verification guards, and forbids claiming unverified token, cost, or masking savings.
Limitations
- Fixes nothing; findings must be handed off to another stage for remediation.
- Does not replace verification performed during the execution stage.
- Tightly coupled to its surrounding harness (harness-manifest.json, core/WORKFLOW.md, capabilities/audit.md) and is not standalone.
Use when a piece of completed work or an artifact needs an independent read-through for drift, gaps, or unsupported claims before sign-off.
Do not use when the artifact must be created or fixed, or when the run's execution-stage verification steps are still outstanding.
Security analysis
SafeThe skill is a read-oriented router with no declared tools and no execution procedure. It explicitly forbids loading references before approval and contains no commands, network calls, destructive actions, or data exfiltration. The guard pointer only requires reporting unsupported mechanics, which is a documentation concern, not a security risk.
No concerns found
How this analysis is madeExamples
audit docs/architecture.md --scope all --report-only and list every place where the document has drifted from the current implementation, plus any omissions.audit docs/release-notes.md --scope cross-ref and report broken links, missing cross-references, and sections that were never filled in — do not edit the file.audit reports/q3-analysis.md --scope facts --read-only and flag every claim that is not backed by a citation or supporting evidence.GENERATED METADATA — edit harness-manifest.json, then run tools/generate.py.
name: audit description: "Use when completed work or artifacts need a read-oriented inspection for drift, inconsistency, omissions, or unsupported claims. Not for implementing fixes, producing the primary artifact, or replacing execution-stage verification." argument-hint: "<artifact_path> [--scope auto|facts|style|structure|cross-ref|coverage|all] [--read-only] [--report-only] [--no-fact-check]" metadata: group: ops fam: ops invocation_class: entry-router modes: [] blurb: "Read-oriented post-run inspection for artifact drift, inconsistency, and omissions." use_when: "Use when completed work or artifacts need a read-oriented inspection for drift, inconsistency, omissions, or unsupported claims." not_for: "Not for implementing fixes, producing the primary artifact, or replacing execution-stage verification."
audit
This is a compact pre-approval entry router. Its manifest-owned frontmatter is the authoritative discovery metadata; it intentionally contains no execution procedure.
Pre-approval boundary
Use only this router, harness-manifest.json, and core/WORKFLOW.md §0.2 to
propose a route. Present the one-time confirmation in core/WORKFLOW.md §0.4
unless the same route and scope are already approved. Do not load references
before approval.
Post-approval owner contract
After approval, direct/quick sessions and the standard+ dispatch-depth-1 owner load
capabilities/audit.md, then use the Reference Index below. Assigned
stage workers load only their assigned stage contracts.
Reference Index
| File | Load when | Obligation |
|---|---|---|
| references/owner-execution.md | After approval, by the selected direct/quick session or dispatch-depth-1 owner | Read the complete execution procedure before material work. This is the router's only post-approval reference edge. |
Guard pointer
Follow the portable artifact, worktree, role, and verification guards in the selected owner contract. Runtime projections must report unsupported mechanics and must not claim physical instruction masking, token, billing, or cost savings without verified evidence.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/artifact-audit-ms71b484/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/artifact-audit-ms71b484' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/artifact-audit-ms71b484/download' --output '.skill-downloads/artifact-audit-ms71b484/SKILL.md.part' && mv '.skill-downloads/artifact-audit-ms71b484/SKILL.md.part' '.skill-downloads/artifact-audit-ms71b484/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/artifact-audit-ms71b484/SKILL.md' && test -s '.skill-downloads/artifact-audit-ms71b484/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/audit' && cp -R '.skill-downloads/artifact-audit-ms71b484' '.claude/skills/audit'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/artifact-audit-ms71b484'openskills read 'artifact-audit-ms71b484'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/artifact-audit-ms71b484/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
ClickHouse Performance Comparison
Testing
Evaluate ClickHouse performance test results, check PR performance changes, compare with history, and assess whether a result is actionable.
Analyze CI Performance Reports
Testing
Analyze CI performance comparison reports for a ClickHouse PR. Cross-references master history to distinguish real regressions from flaky tests.
Santa Method
Testing
Multi-agent adversarial verification with two independent reviewers. Output is checked twice and iteratively fixed until both pass before shipping.