AI Agent Skills

Owns data understanding BEFORE any model is designed. Places and executes `data/eda.py` (a jupytext `# %%` script) via the shared in-process runner, reads the streamed d…

Owns the `audit/` folder: one `# %%` (jupytext percent) Python file per experiment, aligned 1:1 with `experiments/NN_<short_name>.py` and `journal/NN_<short_name>.md`, t…

Use when the user asks to capture, clarify, document, audit, generate, compare, prioritize, validate, or realize product ideas. Guides one-question-at-a-time discovery,…

Audit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 15 other rule categories…

Assess Azure governance maturity for Digital Natives and startups. Detects the most common anti-patterns from the "Digital Natives on Azure" series: incomplete Service H…

Ghost Security — combined security report. Aggregates findings from all scan skills (scan-deps, scan-secrets, scan-code) into a single prioritized report focused on the…

Use when implementing the Frappe/ERPNext permission system. Covers roles, user permissions, perm levels, data masking, and permission hooks for v14/v15/v16. Prevents com…

Guard task boundaries and preserve confirmed critical project state across Codex compaction. Use when a user wants topic-switch guidance, write-through critical memory,…

S3 resiliency, security, and data protection review. Assesses one or many S3 buckets across nine dimensions — versioning, replication, object lock, encryption, block pub…

Generate a full security-focused PRD (Product Requirements Document) from a plain-language feature description. Use this skill whenever someone wants to create a PRD, pr…

Use when a researcher, maintainer, or contributor found or suspects a malicious skill on ClawHub and needs a private reporting workflow: opening a GitHub privat

Reports a reproducible fault to a team or an upstream project — for ai-engineering itself or for any service the client is building — as a governed payload: clo

Audit and harden a Convex app's authorization: identity-from-arg impersonation, missing per-document ownership checks, public queries leaking data by a client-supplied i…

Run every Convex audit (authz, reviewer, advisor, insights) into one scored, deduped readiness report with an ordered fix plan — Lighthouse for your backend.

Codebase analysis with A-F grades explained in plain language for non-technical stakeholders. Self-contained iOS/Swift audit. Triggers: "plain talk", "plain talk report…

Technical codebase analysis with A-F grades across 9 categories. Self-contained iOS/Swift audit with automated grep scanning, verification, and Issue Rating Tables. Trig…