agentleFS
Sign inStart free
qwwiwiqwwiwi/agentos-skills-public/skills/learnings/SKILL.md

learnings

Skill4 starsChanged 4 months agoMITView on GitHub

Learnings System v2 — self-improvement через scoring ошибок. 3 слоя: Episodes (сырой лог) → Learnings (scored) → Rules (promoted). Используй когда: (1) пользователь поправил действие, (2) обнаружена ошибка, (3) нужен отчёт по learnings, (4) lint/audit накопленных уроков.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use product-analytics.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SkeneTechnologiesSkill

    product-analytics

    When the user wants to set up product analytics -- including event taxonomy, tracking plans, funnel analysis, or tool selection (Mixpanel, Amplitude, PostHog). Also use when the user says "event tracking," "analytics setup," "tracking plan," "analytics implementation," or "user identification." For PLG metrics, see plg-metrics. For experimentation, see growth-experimentation.

    Also in 3 projects that use this

The file

Create a free account to mount
Files
SKILL.md

Архитектура

Layer 1: Episodes    — core/learnings/episodes.jsonl (append-only)
Layer 2: Learnings   — core/LEARNINGS.md (scored, max 30)
Layer 3: Rules       — rules.md / CLAUDE.md (promoted, owner only)

CLI

Engine: ~/.claude/scripts/learnings-engine.mjs

ENGINE="node ~/.claude/scripts/learnings-engine.mjs"

# Record new episode
echo '{"context":"...","error":"...","rule":"...","impact":"high","tags":["workflow"]}' | $ENGINE capture

# View scored learnings
$ENGINE score

# Lint: find HOT (freq 3+), STALE (score < 0.15), PROMOTE (score > 0.8)
$ENGINE lint

# Promote learning to rules
$ENGINE promote EP-20260411-007

# Archive stale learning
$ENGINE archive EP-20260411-009

# Bump frequency (repeat violation)
$ENGINE bump EP-20260411-001

# Generate markdown report
$ENGINE report

Scoring

Composite score: Recency (40%) + Frequency (30%) + Impact (30%)

  • Recency: max(0, 1 - ageDays / 30) — decay to 0 over 30 days
  • Frequency: min(1, freq / 3) — 3+ violations = max score
  • Impact: critical=1.0, high=0.7, medium=0.4, low=0.1

Thresholds

ConditionAction
Score > 0.8Propose promotion to rules (via owner)
Score < 0.15Propose archival
Freq 3+ in 30 daysALERT: rule not working, change system

When to record

Record ONLY when:

  • Owner explicitly corrected ("no, do it this way", "wrong")
  • Expensive error (access, security, infrastructure, data)
  • Repeated pattern (same mistake twice)
  • Owner sets new standard/rule

Do NOT record:

  • Normal clarifications
  • Choice between options
  • Minor style tweaks without pattern

Episode format

{
  "id": "EP-YYYYMMDD-NNN",
  "ts": "ISO8601",
  "type": "correction|insight|knowledge_gap",
  "agent": "{{AGENT_ID}}",
  "source": "owner|experience|review",
  "context": "situation",
  "error": "what went wrong",
  "rule": "rule for the future",
  "impact": "critical|high|medium|low",
  "tags": ["tag1"],
  "freq": 1,
  "status": "active|promoted|archived"
}

Access zones for auto-fix

ZoneFilesWho edits
GREENSKILL.md, TOOLS.md, LEARNINGS.mdAgent autonomously
YELLOWAGENTS.md, decisions.mdAgent with justification
REDrules.md, CLAUDE.mdOwner only

What to do at freq 3+

Error typeAction
Forgot a stepAdd hook (PreToolUse/PostToolUse)
Wrong response styleUpdate CLAUDE.md or rules.md (via owner)
Used wrong toolUpdate TOOLS.md
Asked unnecessary questionAdd rule to CLAUDE.md (via owner)
Code errorAdd test or lint rule

Hooks integration

  • SessionStart: inject scored top-5 from $ENGINE score
  • Stop: analyze session corrections, auto-capture episodes
  • Weekly cron: $ENGINE lint + report to owner

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