agentleFS
Sign inStart free
fullerzzfullerzz/agent-skills/skills/reflect/SKILL.md

reflect

Skill2 starsChanged 29 days agoMITView on GitHub

Review the active session for durable lessons and propose or apply approved skill edits.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 146 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run independent native read-only judgment, tooling, and divergent lenses using the native contract.

    line 11
  2. Distinctive:

    Use the synthesis prompt. Verify moments, read target skills, prefer existing homes, and distinguish missing guidance from missed …

    line 12

“Common” is measured: kept by at least 6 in 10 of the 146 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

Propose durable lessons from the active conversation. Follow scoped session evidence; label a digest fallback.

  1. Run independent native read-only judgment, tooling, and divergent lenses using the native contract. Queue when needed.
  2. Use the synthesis prompt. Verify moments, read target skills, prefer existing homes, and distinguish missing guidance from missed invocation.
  3. Route enforceable rules to local Backlog mechanisms.
  4. Present Accepted / Rejected / Backlog. Apply accepted edits only after approval or an existing explicit request covering them. Filing backlog is a separate requested action.
  5. For approved edits use native authoring guidance, validate metadata/links, and run realistic scenarios when behavior changes.

Report proposals or applied edits and remaining gaps. Do not silently write memory, tickets, commits, or PRs.

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.

Reviews can't be read right now.

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