agentleFS
Sign inStart free
Asaf-DahanAsaf-Dahan/super-skill/template/SKILL.md

super-skill

Skill1 starsChanged 7 months agoMITView on GitHub

Domain expert layer. Loads full context, methodology, and operational knowledge for the defined domain. Gives any AI agent complete understanding before any action is taken.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. grooverLab/stash★ 0same name
    2. sdsrss/super-skill★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read these files in this order:

    line 17
  2. Distinctive:

    Never skip this sequence. Context before action, always.

    line 22
  3. Distinctive:

    Write all proposals and evaluations to PENDING.md.

    line 29
  4. Distinctive:

    Do not modify any layer file without explicit user approval.

    line 30
  5. Very specific:

    After reading the three required files above, load the remaining layer files as needed for the current task: DOMAIN_MAP.md - structure and …

    line 34
  6. Distinctive:

    Before proposing any change, load the files most likely to contain relevant evidence for your task type.

    line 51
  7. Distinctive:

    All prompts live in ONBOARDING.md.

    line 69

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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
<!-- TEMPLATE FILE -- Do not edit. This is the scaffold. Root files are your working copy. -->

Super Skill - Agent Entry Point

<!-- Replace this header with your own project/organization name -->

Before Any Action

Read these files in this order:

  1. CONTEXT.md - who owns this, what domain, what goals
  2. CURRENT_STATE.md - what the domain looks like right now
  3. PENDING.md - what is waiting for user approval

Never skip this sequence. Context before action, always.

Operating Principle

The model proposes. The user decides. The Super Skill records. The system executes.

Write all proposals and evaluations to PENDING.md. Do not modify any layer file without explicit user approval.

Domain Files

After reading the three required files above, load the remaining layer files as needed for the current task: DOMAIN_MAP.md - structure and sub-domain relationships EVALUATION.md - criteria for evaluating new entrants DECISIONS.md - decisions made and reasoning MONITORING.md - sources to watch for drift LEARNING.md - NotebookLM integration structure LOG.md - change log and audit trail experts/COUNCIL.md - active expert council and debates traces/ - execution traces for causal reasoning wiki/graph.json - domain structure map (optional; run /ss-graph to generate)

Individual expert profiles (experts/[name].md) load on demand only, not by default. Load them when a specific expert's perspective is needed.

Evidence Routing

Before proposing any change, load the files most likely to contain relevant evidence for your task type. This prevents blind proposals.

Task typeEvidence files (load in order)
Evaluate a new tool/methodEVALUATION.md, CURRENT_STATE.md, DECISIONS.md
Propose architecture changeDECISIONS.md, DOMAIN_MAP.md, CURRENT_STATE.md
Investigate drift or breakageMONITORING.md, CURRENT_STATE.md, traces/
Resolve a PENDING itemPENDING.md, DECISIONS.md, EVALUATION.md
Generate learning contentLEARNING.md, CONTEXT.md, CURRENT_STATE.md
Root-cause analysistraces/, DECISIONS.md, LOG.md
Cross-domain impact checkDOMAIN_MAP.md, CURRENT_STATE.md, DECISIONS.md
Expert disagreementexperts/COUNCIL.md, DECISIONS.md, experts/[name].md

Load the minimum set. Do not load files not listed for your task type.

How Prompts Work

All prompts live in ONBOARDING.md. Claude Code reads and runs them automatically. Users do not copy prompts after the initial Bootstrap setup.

Slash commands: see CLAUDE.md

Learning Generation

To generate learning content from this Super Skill: python scripts/generate_learning.py audio python scripts/generate_learning.py quiz python scripts/generate_learning.py mindmap

Capabilities

File operations (no shell required)

  • Reading and explaining any layer file
  • Writing proposals to PENDING.md
  • Generating learning content to notebooks/

Shell required

  • python scripts/update_summary.py (regenerate SUMMARY.md)
  • python scripts/feed_notebook.py (push files to NotebookLM)
  • python scripts/generate_learning.py audio | quiz | mindmap

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