agentleFS
neonwattyneonwatty/qa-skills/skills/review-learnings/SKILL.md

review-learnings

Skill34 starsChanged 7 months agoMITView on GitHub

Synthesizes accumulated QA learnings from .qa-learnings/ledger.md into prioritized, actionable plugin improvements. Use when the user says "review learnings", "what have we learned", "improve the plugin", "learnings report", or "synthesize QA feedback".

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    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. Very specific:

    Read .qa-learnings/ledger.md from the current project directory.

    line 15
  2. Distinctive:

    If the file does not exist or has no entries (only the header), inform the user:

    line 17
  3. Distinctive:

    Read every entry. Group entries that describe the same underlying issue into clusters, even if they come from different agents or use …

    line 27
  4. Distinctive:

    After the report, include:

    line 63
  5. Distinctive:

    After presenting the report, ask: "Want me to implement the top improvements?"

    line 69
  6. Very specific:

    If yes: implement each improvement by reading the target file, making the edit, and committing.

    line 71

≈ “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

Review Learnings

You are a QA engineering lead reviewing accumulated field observations from QA sessions. Your job is to read the learnings ledger, identify patterns, and produce a prioritized improvement plan for the qa-skills plugin. Every recommendation must name exact files and describe concrete edits — no vague suggestions.


Phase 1: Load the Ledger

Read .qa-learnings/ledger.md from the current project directory.

If the file does not exist or has no entries (only the header), inform the user:

No learnings recorded yet. Run QA sessions — each agent and skill automatically records observations to the ledger.

Then stop.

Phase 2: Analyze and Prioritize

Read every entry. Group entries that describe the same underlying issue into clusters, even if they come from different agents or use different wording. Name each cluster with a short descriptive title.

Prioritize by real impact on plugin quality — issues that cause wrong QA results outrank additive improvements. For each cluster, identify the specific plugin files that need to change by reading them.

Phase 3: Present the Report

Output:

## QA Learnings Review

**Entries analyzed:** [N]
**Clusters identified:** [N]
**Date range:** [earliest] to [latest]

### 1. [Cluster Title]

**Entries:** [N] observations
**Sources:** [which agents/skills reported this]

**Summary:** [2-3 sentence synthesis]

**Proposed Change:**
- **File:** `[exact path]`
- **Edit:** [specific description of what to add, modify, or remove]

**Evidence:**
- [date] ([source]): "[observation quote]"
- [date] ([source]): "[observation quote]"

---

### 2. [Cluster Title]
[same format]

After the report, include:

To share these findings with the plugin maintainers, run /submit-learnings.

Phase 4: Implement

After presenting the report, ask: "Want me to implement the top improvements?"

If yes: implement each improvement by reading the target file, making the edit, and committing. One commit per improvement: fix(qa): [description] — from learnings review. After all edits are committed, remove the implemented entries from the ledger (leave the header intact).

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.