ai-mapping-audit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ai-mapping-audit (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill provides the framework and knowledge for performing AI Mapping Audits — systematic evaluations of where AI creates value across a business's production functions.
Use this knowledge when the user:
Paper: "Mapping AI into Production: A Field Experiment on Firm Performance" Authors: Hyunjin Kim (INSEAD), Dahyeon Kim (INSEAD), Rembrand Koning (Harvard Business School) Date: March 30, 2026 Program: INSEAD AI Founder Sprint / AI Venture Lab
The Mapping Problem: The central friction in AI adoption is not AI capability — it's discovering WHERE and HOW AI creates value within a firm's production process.
The Experiment: 515 high-growth startups. Treatment group received information about how OTHER firms had reorganized production around AI, prompting them to search for use cases across a BROADER set of firm functions.
Results:
Read ${CLAUDE_PLUGIN_ROOT}/skills/ai-mapping-audit/references/ten-functions.md for the complete framework.
Read ${CLAUDE_PLUGIN_ROOT}/skills/ai-mapping-audit/references/examples-from-other-firms.md for examples of how real firms have reorganized around AI across all 10 functions.
Read ${CLAUDE_PLUGIN_ROOT}/skills/ai-mapping-audit/references/case-studies-from-paper.md for the 4 actual case studies shown to the treatment group — Gamma (process redesign), RyzLabs (parallel prototyping), FazeShift (eliminating glue work), and Ranger (sell first, build AI second). These caused firms to discover 44% more use cases.
Ask the user: "Which of these 10 functions does your business use AI for?" Then identify the gaps.
Run the /map command to scan their workspace automatically.
Run /map-venture [name] for a focused analysis.
Run /map-score after a map to prioritize opportunities.
If a user's AI usage is concentrated only in:
...they have the mapping problem. The highest-value applications are in:
Always guide users toward these higher-value functions.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.