agentleFS
muyenmuyen/vibe-to-prod/.claude/skills/continuous-improvement/SKILL.md

continuous-improvement

Skill34 starsChanged 11 months agoMITView on GitHub

Capture learnings after tasks. Triggers on task completion, repeated mistakes, retrospective requests, or "what did I learn".

5 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, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 5

    Distinctive

    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:

    After completing a task, briefly reflect and capture learnings.

    line 8
  2. Distinctive:

    When storing a learning in Memory MCP:

    line 35
  3. Distinctive:

    When you make the same mistake twice:

    line 62
  4. Distinctive:

    Create or update a rule file:

    line 65
  5. Distinctive:

    When a process is complex and repeated:

    line 83
  6. Very specific:

    Create skill directory: .claude/skills/my-skill/

    line 85

“Common” is measured: kept by at least 6 in 10 of the 4 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

Continuous Improvement

After completing a task, briefly reflect and capture learnings.

When to Activate

  • Task just completed
  • Same mistake made twice
  • User asks "what did I learn" or "retrospective"
  • Complex process was difficult or slow

Reflect (30 seconds)

Ask yourself:

  • What worked well?
  • What was difficult or slow?
  • What's missing (automation, docs, tools)?

Capture

Learning TypeAction
Pattern/gotchaStore in Memory MCP
Missing automationCreate issue/TODO
Repeated mistakeUpdate .claude/rules/
Complex processCreate .claude/skills/

Memory Pattern

When storing a learning in Memory MCP:

mcp__memory__create_entities({
  entities: [{
    name: "Learning_TOPIC",
    entityType: "development_learning",
    observations: [
      "Context: What was happening",
      "Learning: What was learned",
      "Application: How to apply it"
    ]
  }]
})

Improvement Actions

IssueSolution
Same mistake twiceAdd rule to .claude/rules/
Manual process > 5 minCreate skill or hook
New tool/patternStore in Memory MCP
Missing documentationUpdate docs

Rule Addition Example

When you make the same mistake twice:

  1. Identify the pattern
  2. Create or update a rule file:
# .claude/rules/my-rules.md
---
paths: relevant/path/**
description: Rules for this area
---

## Critical Rules

| Rule | Why |
|------|-----|
| Don't do X | Because Y happens |

Skill Addition Example

When a process is complex and repeated:

  1. Create skill directory: .claude/skills/my-skill/
  2. Create SKILL.md:
# .claude/skills/my-skill/SKILL.md
---
name: my-skill
description: When this skill should activate
---

# My Skill

## When to Activate
[Trigger conditions]

## Process
[Steps to follow]

Run /improve-claude-config for major configuration updates.

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.