agentleFS
Sign inStart free
scchearnscchearn/agent-skills/skills/revise-agent-md/SKILL.md

revise-agent-md

Skill0 starsChanged 6 months agoApache-2.0View on GitHub

Update agent guidance markdown files with learnings from the current session. Use when a session uncovered missing context, useful commands, testing patterns, environment quirks, or gotchas that should be captured for future agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Ask if the user wants to apply the changes.

    line 61

≈ “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

Revise Agent Markdown

Review the current session for learnings about working in this codebase. Update the relevant agent guidance markdown file with context that would help future agent sessions be more effective.

Step 1: Reflect

What context was missing that would have helped an agent work more effectively?

  • Bash commands that were used or discovered
  • Code style patterns followed
  • Testing approaches that worked
  • Environment/configuration quirks
  • Warnings or gotchas encountered

Step 2: Find Guidance Files

find . \( -name "AGENTS.md" -o -name "CLAUDE.md" -o -name ".claude.local.md" \) 2>/dev/null | head -20

Decide where each addition belongs:

  • AGENTS.md - Team-shared, harness-agnostic guidance
  • CLAUDE.md - Team-shared Claude-specific guidance when the repo uses it
  • .claude.local.md - Personal/local only (gitignored)

Step 3: Draft Additions

Keep it concise - one line per concept. Guidance files are part of the prompt, so brevity matters.

Format: <command or pattern> - <brief description>

Avoid:

  • Verbose explanations
  • Obvious information
  • One-off fixes unlikely to recur

Step 4: Show Proposed Changes

For each addition:

### Update: ./AGENTS.md

**Why:** [one-line reason]

```diff
+ [the addition - keep it brief]

## Step 5: Apply with Approval

Ask if the user wants to apply the changes. Only edit files they approve.

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