Maintain Project AI Records
SkillProductivityInitialize and maintain lightweight AI work records in a writable project. Use on the first substantive writable task and after meaningful milestones. Do not create records for read-only inspection or trivial answers.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Maintain Project AI Records skill
What this skill tells your AI
The instructions your AI receives, as published by wildpigking/codex-project-skill-manager in .agents/skills/maintain-project-ai-records/SKILL.md and read by ahel’s review.
Run scripts/ensure_project_ai_records.py with the exact project root. The script creates missing files and never replaces existing content.
Do not run the script or append a milestone during a read-only request. Wait for a separately authorized writable task.
Read the resulting project AGENTS.md before continuing.
Store confirmed project-specific habits in AGENTS.md. Append milestone summaries to docs/ai/dev_log.md and unpromoted reusable lessons to docs/ai/experience_candidates.md.
Use at most six concise milestone bullets covering the goal, decisions, changes, verification, open issues, and reusable candidate when relevant. Do not log every command, credentials, private identifiers, or hidden reasoning.
Keep cross-project workflows out of project AGENTS.md. Promote experience to a user skill only after explicit satisfaction and authorization, using a separate workflow reflection.
Signals
- GitHub stars
- 22
- Forks
- 1
- Last commit
- Aug 2026
ahel review
K6low
bundled executables the agent is told to run
Automated review, not a security audit. Ruleset v1+k2.
Advanced
- Catalog kind
- skill
- Gateway key
maintain-project-ai-records- Source
- github.com/wildpigking/codex-project-skill-manager