agentleFS
Sign inStart free
kriegcloudkriegcloud/beep-effect/.claude/skills/reflect/SKILL.md

reflect

Skill78 starsChanged 6 days agoApache-2.0View on GitHub

Write a structured agent reflection for a goal packet. Trigger on: a goal's P3 Close phase, the user invoking `/reflect <goal-slug>`, or when you notice a TODO worth codifying. Produces a schema-valid `goals/<slug>/history/reflections/<YYYY-MM-DD>-<agent>.md` enforced by `bun run beep lint reflection-artifacts`.

172 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.
  • ianclearySkill

    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 14 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 24 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 19 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply 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 26 projects that use this

  • jaydubya818Skill

    automate-me

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

    Also in 39 projects that use this

  • jaydubya818Skill

    poteto-mode

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

    Also in 27 projects that use this

  • +6 more from jaydubya818

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 163 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to capture a durable, information-rich reflection on a goal packet's execution.

    line 16
  2. Very specific:

    TODO codification: when you spot something that should become a standard, skill, lint rule, or issue, capture it as a codification-todo …

    line 32
  3. Very specific:

    Update packet README.md (latest evidence) and ops/manifest.json status.

    line 58

“Common” is measured: kept by at least 6 in 10 of the 163 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Reflect

Use this skill to capture a durable, information-rich reflection on a goal packet's execution. Reflections compound into reusable knowledge; the research (goals/agent-reflection-loop/research/reflection-frontier-report.md) shows that specific, structured reflections grounded in real tooling/CI signals far outperform terse free-text advice.

When to run

  • Automatic (P3 Close): the agent closing a goal packet writes one before preparing a typed proposedCloseout or adopting a committed closeout as completed-retained. That is the canonical completed status; legacy complete is migration input, not a live lifecycle value. Packets with reflectionRequired: true are gated, and a declared proposed or committed closeout also keeps the packet in the reflection gate. A missing or invalid required reflection blocks closeout.
  • On demand: /reflect <goal-slug> — reflect on any packet now.
  • TODO codification: when you spot something that should become a standard, skill, lint rule, or issue, capture it as a codification-todo finding.

How to write one

  1. Resolve the goal slug. Read the packet's SPEC.md, PLAN.md, README.md, history/, and the real execution evidence (PRs, CI runs, review threads, commits). Ground claims in that evidence — not unaided self-critique.
  2. Copy goals/_template/history/reflections/_TEMPLATE.md to goals/<slug>/history/reflections/<YYYY-MM-DD>-<agent>.md (today's date; <agent> lowercase, e.g. claude, codex).
  3. Fill the YAML frontmatter — it is the machine-validated block (ReflectionFrontmatter):
    • goal, agent, date (YYYY-MM-DD)
    • trigger: closeout | on-demand | todo-codify
    • confidence (overall): high | medium | low
    • findings[]: each { category, confidence, instruction, explanation } where category ∈ tooling-friction | implementation-improvement | goal-critique | prompt-critique | codification-todo. Make instruction concrete (what to change) and explanation evidence-backed (why).
    • todos[]: items worth codifying.
  4. Fill the body rubric: Summary, Tooling experience (worked / didn't / frustrating / wished existed), Implementation improvement opportunities, Goal & prompt critique (would you revise the GOAL/prompt to be clearer, easier, more efficient?), TODOs worth codifying, and Lessons (confidence-tiered: HIGH critical / MEDIUM best-practice / LOW consideration).
  5. Update packet README.md (latest evidence) and ops/manifest.json status.

Verify

bun run beep lint reflection-artifacts   # blocking_findings=0
git diff --check -- goals/<slug>

Related skills

  • yeet — commit/push/PR after the reflection is written.
  • quality-review-fix-loop — late-initiative closure + reviewer/fixer loop.

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.

Check your setup, free