Learning & Documentation Agent Skills

Detect and remove AI typos from French text, then rewrite it with a human voice. Use this when…

Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving…

Search for images on Unsplash and download them.

Compares tracked job postings against the candidate profile to identify skill gaps and generate a prioritized learning plan with study…

Create or update skills by generating, editing, or refining SKILL.md files in this repository.

Updates one exact durable Markdown document with a complete replacement or explicit text patch and named metadata changes.

Sync aiagentflow.dev with the latest CLI version — providers, agents, docs, version numbers.

Add, refresh, reclassify, or retire entries in the Awesome Codex Doctors catalog and leave a verified, merge-ready repository change.

Update project dependencies to their latest compatible versions with verification.

Update documentation in docs/public/ based on recent code changes.

Update all project documentation after code changes.

Update public API reference docs to match Python source code.

Use when commits have landed since the onboarding files were last synced (the drift-check hook nudges for this), or the user asks to…

Updates changelog documentation for contract developers and node operators by analyzing branch changes relative to 'next'.

Write Urdu that sounds human. Not formal, not robotic, not AI-generated.

Draft a production-readable US vertical microdrama screenplay from an approved beat sheet without silently redesigning its core beats.

Generate release notes for dist/RELEASE_NOTES.md.

Use when positioning a USENIX Security Symposium paper against prior work — covering the Big-Four security venues plus specialty…

Use when targeting USENIX Security Symposium (USENIX Security) or deciding whether a computer-science manuscript fits this venue.

Use when drafting or revising prose for a USENIX Security Symposium paper — threat-model-first structure, calibrated security claims…

Explain anything — turn ideas into podcasts, explainer videos, or voice narration.