agentleFS
tornikebolokadze1-cybertornikebolokadze1-cyber/agent-foundation-kit/.claude/skills/reflect/SKILL.md

reflect

Skill6 starsChanged 27 days agoMITView on GitHub

Self-improvement pass — read recent episodes, lessons and proposals, find repeated friction, repeated manual steps and checks done by eye, and propose concrete improvements (a skill, rule, gate or ADR) in memory/PROPOSALS.md. Creates nothing without the owner's yes. Use every few sessions, when the owner asks what to improve, or right after a repeated mistake.

183 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use poteto-help, setup-pstack and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • shiwenbin1617Skill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 16 projects that use this

  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 27 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 20 projects that use this

  • jaydubya818Skill

    automate-me

    Use when the user wants working preferences captured in a reusable mode skill.

    Also in 43 projects that use this

  • jaydubya818Skill

    poteto-mode

    Use when non-trivial work should follow the smallest rigorous Jstack workflow.

    Also in 30 projects that use this

  • shiwenbin1617Skill

    principle-explain-the-number

    Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 29 projects that use this

  • +6 more from jaydubya818

The file

Files
SKILL.md

/reflect — the project improves itself, with the owner's consent

  1. Read memory/episodes/INDEX.md and the last ~5 episodes (their "გაკვეთილები" and "წინადადებები" sections), memory/LESSONS.md, memory/PROPOSALS.md, and the latest gate/drill output if relevant.
  2. Find patterns — the same mistake twice (→ lesson + a gate that prevents it); the same multi-step instruction given by the owner twice (→ skill candidate); a check done by eye that a script could do (→ gate candidate); a decision made implicitly (→ ADR candidate); a stale fact in CLAUDE.md, AGENTS.md or docs (→ correction).
  3. Write each as a proposal in memory/PROPOSALS.md: - [ ] **P-NNN** <change> — why (episode links as evidence) — cost/risk — how we will know it worked (a machine check if possible).
  4. Present the top 3 to the owner in Georgian, one sentence each, with your recommendation.
  5. Only after an explicit yes: implement it; for a new skill use .claude/skills/<name>/SKILL.md with a name that does not collide with ~/.claude/skills (global skills win on a clash) and a description that says when to use it; add a drill for any script. Then mark the proposal [x] with the date and move it under "გადაწყვეტილი". A "no" is recorded there too, with the reason.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.