agentleFS
GusevV1987GusevV1987/ai-workspace-kit/skills/claudeception/SKILL.md

claudeception

Skill2 starsChanged 8 months agoMITView on GitHub

Extract reusable workflows from a session and turn them into new skills. Use when: "save this as a skill", "extract a workflow from this", or after a session produced a non-obvious repeatable lesson.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 6

    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:

    Do not create a skill for a one-off event.

    line 26
  2. Distinctive:

    when this should be used again

    line 36
  3. Distinctive:

    If an existing skill covers it, update that skill instead of creating a duplicate.

    line 42
  4. Distinctive:

    when it should be used

    line 80
  5. Distinctive:

    If the lesson will probably matter again, capture it.

    line 86
  6. Distinctive:

    If not, leave it in the session log instead.

    line 88

“Common” is measured: kept by at least 6 in 10 of the 9 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

Claudeception

Purpose

Turn repeated learning into reusable instructions.

When To Extract A Skill

Extract a skill when the session produced:

  1. a non-obvious fix
  2. a repeatable workflow
  3. a reliable checklist
  4. a project pattern worth preserving

Do not create a skill for a one-off event.

Process

Step 1: Identify The Lesson

Write down:

  • what happened
  • what was non-obvious
  • when this should be used again

Step 2: Check If It Already Exists

Look through skills/.

If an existing skill covers it, update that skill instead of creating a duplicate.

Step 3: Create Or Update The Skill

Project-level skills should live here:

  • skills/<skill-name>/SKILL.md

Optional tool-specific mirrors can be added later, but the canonical version should stay in this repo.

Step 4: Use This Structure

---
name: skill-name
description: Short description with trigger conditions
version: 1.0.0
date: YYYY-MM-DD
---

# Skill Name

## When to use
...

## Steps
...

## Verification
...

Step 5: Summarize

Tell the user:

  • what skill was created or updated
  • what problem it now solves
  • when it should be used

Rule

If the lesson will probably matter again, capture it.

If not, leave it in the session log instead.

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.