ai-audit
Skill4 starsChanged 6 days agoMITView on GitHub
Audits AI/ML/LLM components: benchmarks, leakage, calibration, explainability, bias, red-team, confidentiality, monitoring.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- sunitghub/canon-skillstheir own version, first seen Oct 22, 2026
- Bartosh16/claude-skillstheir own version, first seen Sep 2, 2026
- AlonMiz/ai-audittheir own version, first seen Aug 25, 2026
- Ajeesh25353646/claude-skillstheir own version, first seen Jun 3, 2026
- kumaran-is/claude-code-onboardingtheir own version, first seen May 25, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- kumaran-is/claude-code-onboarding★ 35same name
- sunitghub/canon-skills★ 9same name
- AlonMiz/ai-audit★ 4same name
- Bartosh16/claude-skills★ 3same name
- Ajeesh25353646/claude-skills★ 0same name
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.
In this repository210 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/ai-ml-code.mdcCursor rule
- .cursor/rules/code-translation.mdcCursor rule
- .cursor/rules/data-pipelines.mdcCursor rule
- .cursor/rules/documentation.mdcCursor rule
- .cursor/rules/dsge-code.mdcCursor rule
- .cursor/rules/econometrics-code.mdcCursor rule
- .cursor/rules/eviews-code.mdcCursor rule
- .cursor/rules/forecasts.mdcCursor rule
- .cursor/rules/gempack-code.mdcCursor rule
- .cursor/rules/lego-manifests.mdcCursor rule
- .cursor/rules/llm-code.mdcCursor rule
- .cursor/rules/model-code.mdcCursor rule
- .cursor/rules/notebooks-and-scripts.mdcCursor rule
- .cursor/rules/r-code.mdcCursor rule
- .cursor/rules/restricted-data.mdcCursor rule
- .cursor/rules/rl-code.mdcCursor rule
- .cursor/rules/sectoral-trade-climate-code.mdcCursor rule
- .cursor/rules/semi-structural-code.mdcCursor rule
- .cursor/rules/stata-code.mdcCursor rule
- .cursor/rules/tests.mdcCursor rule
- .cursor/rules/validation.mdcCursor rule
- adoptSkill
- backtestSkill
- build-abmSkill
- build-causal-mlSkill
- build-cgeSkill
- build-climate-macroSkill
- build-deep-forecasterSkill
- build-drl-policySkill
- build-dsgeSkill
- build-financial-programmingSkill
- build-fpasSkill
- build-game-modelSkill
- build-hankSkill
- build-io-samSkill
- build-llm-agentsSkill
- build-llm-pipelineSkill
- build-multicountrySkill
- build-neural-solverSkill
- build-rag-kbSkill
- build-semi-structuralSkill
- build-sfcSkill
- build-trade-modelSkill
- calibrate-modelSkill
- calibration-planSkill
- carbon-pricing-analysisSkill
- chart-packSkill
- climate-scenarioSkill
- code-inventorySkill
- code-reviewSkill
- country-typologySkill
- create-exerciseSkill
- data-requirementsSkill
- debt-decompositionSkill
- debt-sustainabilitySkill
- design-trainingSkill
- distributional-analysisSkill
- equivalence-testSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
5
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
- Very specific: line 27
If a required input is ABSENT, that part is NOT ASSESSED — NO DATA: do not estimate or invent it.
- Very specific: line 29
Collaboration: Follow .claude/docs/collaboration-protocol.md: ask questions first, present options, get approval before writing files, and …
- Distinctive: line 49
Check data splits for leakage and benchmark fairness
- Distinctive: line 51
Check calibration, uncertainty and stability across seeds, windows and versions
- Distinctive: line 58
After scope: confirm depth and benchmarks
- Distinctive: line 59
Before the verdict: review conditions and owners
- Distinctive: line 74
Every finding cites evidence and has an owner
“Common” is measured: kept by at least 6 in 10 of the 5 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.
Files
<!-- Generated from .claude/skills/ai-audit/SKILL.md by tools/sync_agents.py. Edit the source, then run the script. -->/ai-audit — AI Audit
Category: Validation & QA · Primary agent: model-risk-governance-specialist
Audits AI/ML/LLM components: benchmarks, leakage, calibration, explainability, bias, red-team, confidentiality, monitoring.
Arguments: whatever the user wrote after the command name.
Purpose
Audit an AI, machine-learning or LLM component before it is used in analysis or advice: whether its evaluation is honest (no leakage, fair benchmarks), whether its uncertainty is calibrated and stable, whether what it learned makes economic sense, whether it performs fairly across country groups, whether it resists red-team attacks, and whether confidentiality and human oversight are in place. The output is a verdict that can block release.
Use it when any AI component (forecaster, classifier, solver, RL policy, LLM pipeline, RAG system) is about to be used in production or published work.
Do not use it when the component is a traditional econometric or structural model (/validate-model).
Before you start
- Check required inputs. For each input below record
FOUNDorABSENT(never 'assumed'):- Experiment log
- Model code
- Evaluation card
If a required input is
ABSENT, that part isNOT ASSESSED — NO DATA: do not estimate or invent it; name what is missing and which skill produces it. If all required inputs are absent, stop and say so.
- Check confidentiality. Identify the data classification level of the inputs (
.claude/docs/confidentiality-and-ai-use.md). Do not proceed with restricted or confidential data in a way the policy does not allow. - Collaboration. Follow
.claude/docs/collaboration-protocol.md: ask questions first, present options, get approval before writing files, and updateproduction/session-state/active.mdafter each approved section.
Agents
model-risk-governance-specialist— primary agent; coordinates the work and integrates resultsai-ethics-fairness-specialist— Reviews AI ethics and fairnessllm-red-team-specialist— Red-teams LLM systemsinterpretable-ml-specialist— Makes AI models explainablemodel-validation-specialist— Performs independent model validation
Each agent is defined in .claude/agents/<name>.md. If your tool runs subagents, run these agents as subagents, in parallel where the steps are independent; otherwise read each agent's file and apply its instructions in turn. Subagents only write to the paths named in your instructions.
Key design decisions (present options, let the user choose)
| Decision | Typical options | What it changes |
| Depth | light review, full audit | Effort and assurance |
| Benchmarks | simple econometric models, previous version | Bar for added value |
| Fairness groups | country groups, income levels, regions | Disaggregated results |
| LLM tests | factuality sets, injection, leakage, version regression | Security coverage |
Workflow
- Check data splits for leakage and benchmark fairness
- Time-aware splits; preprocessing fitted on training data only; benchmarks given equal tuning effort
- Check calibration, uncertainty and stability across seeds, windows and versions
- Review explainability and economic plausibility of learned relationships
- Flag counterintuitive relationships for economic review
- Review bias by country group and income level; for LLMs run the red-team harness
- Review confidentiality and human-oversight design; define monitoring
Checkpoints with the user
- After scope: confirm depth and benchmarks
- Before the verdict: review conditions and owners
Common pitfalls
- Accepting reported scores without rerunning
- Benchmarks tuned less carefully than the AI model
- Average performance hiding failures for some groups
- Oversight that exists only on paper
Output
validation/<model>/ai-audit.md
The audit report covers leakage, benchmarks, calibration, stability, plausibility, fairness, red-team results, confidentiality and oversight, with findings, conditions, owners and the verdict.
Gate / verdict
- Verdict: PASS / PASS WITH CONDITIONS / FAIL; failures block release
- Every finding cites evidence and has an owner
Suggested next steps
/validate-model/model-risk-review
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
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.

