agentleFS
egregore-labsegregore-labs/egregore/.claude/skills/archive/SKILL.md

archive

Skill293 starsChanged 11 days agoMITView on GitHub

Capture an effective prompting or steering technique as a reusable canonical pattern. Use when a prompt chain worked especially well; use /reflect for insight about the work and /note for a private thought.

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use distill, plan and 1 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.
  • HK-hubSkill

    distill

    Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean. Use when the user asks to simplify, declutter, reduce noise, remove elements, or make a UI cleaner and more focused.

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 3 projects that use this

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 18 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:

    No arguments: inspect this session for a meaningful steering chain.

    line 17
  2. Very specific:

    Add --relationship "RELATION:TARGET" only for explicit links.

    line 56
  3. Very specific:

    Do not separately run /save, Git, QMD, graph, telemetry, publishing, sharing, or notifications.

    line 65

“Common” is measured: kept by at least 6 in 10 of the 18 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

Archive

Capture a reusable human-to-agent steering technique as a typed pattern with subtype prompt-chain.

When to invoke

Capture an effective prompting or steering technique as a reusable canonical pattern. Use when a prompt chain worked especially well; use /reflect for insight about the work and /note for a private thought.

Modes

  • No arguments: inspect this session for a meaningful steering chain. If the session is too short or no chain exists, ask the user to describe one.
  • Arguments: treat them as the technique; a single principle is a one-move chain.

Each move records its type, trigger, intervention, effect, and distilled principle. Useful initial move types include inversion, calibration, scoping, elevation, reframing, grounding, sequencing, contradiction, analogy, and provocation; extend the vocabulary when needed.

Context and dedupe

Reuse attached EGREGORE_ORG_CONTEXT_V1 evidence. Do not repeat retrieval when it already contains sufficient related patterns. If a named gap remains, make one bash bin/search.sh query "<technique concept>" -n 6 call and open only a likely duplicate through bash bin/search.sh open. Never query implementation infrastructure or storage directly.

Flow

  1. Extract a chain name, when-to-use guidance, ordered moves, outcome, topics, workstream, and explicit relations.
  2. For a three-or-more move chain, show the complete breakdown. For shorter chains, show the compact proposal. Wait for y, edits, or skip.
  3. Render the accepted pattern body to a temporary file under tmp/ and invoke exactly one canonical command; {artifact-file} is that file, and {chain-name}, {topic}, and {workstream} come from the accepted chain proposal:
bash bin/knowledge.sh create \
  --type pattern \
  --subtype prompt-chain \
  --title '{chain-name}' \
  --input '{artifact-file}' \
  --topic prompt-chain \
  --topic '{topic}' \
  --workstream '{workstream}'

Add --relationship "RELATION:TARGET" only for explicit links. The Runtime resolves ActorContext, authorizes, assigns stable identity/provenance, persists canonical Markdown, records Git provenance, refreshes retrieval, starts background embedding, and emits content-free telemetry.

Boundaries

  • Archive captures an AI-steering technique, not a work decision or private scratch thought.
  • Do not separately run /save, Git, QMD, graph, telemetry, publishing, sharing, or notifications.
  • Graph projection is optional and advisory. Canonical Markdown wins.
  • Publishing, external sharing, or notification requires a separate permitted, explicitly consented action.

Report the canonical path and writeback status. Preserve the compact ◇ ARCHIVE confirmation style for rich output.

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.