experience-library
Capture task outcomes, score performance, and derive rules as token priors for continual learning without model weight changes. Use for post-task feedback, experience capture, pattern extraction, and learning from mistakes. Achieves continual learning for $18 per 100 samples vs $10k fine-tune cost. Triggers on "learn from experience", "capture patterns", "post-task analysis", "continual learning", "experience extraction".
npx skills add majiayu000/claude-skill-registry --skill experience-library-dredd-us-seashells-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Experience Library Update ## Purpose Sample task answers, score outcomes, and derive rules as token priors - achieving continual learning for $18/100 samples vs $10k fine-tune cost, without changing model weights. ## When to Use - Post-task learning and improvement - Capturing successful patterns - Learning from failures - Tool call optimization - Building domain expertise over time - Pattern extraction from experience ## Core Instructions ### Pattern: Experience Capture Loop ```python def update_experience_library(task, answer, outcome): """ Capture and learn from task experience """ # 1. Score the outcome score = evaluate_outcome(answer, outcome) # 2. Extract patterns if successful if score > threshold: pattern = extract_pattern(task, answer) library.add_rule(pattern) # 3. Use as token prior (no weight changes) return library.get_relevant_rules(new_task) ``` ### Step 1: Score Task Outcome ```python def evaluate_outcome(answer, outcome): """ Score how well the task was completed Returns: float: Score from 0.0 (failed) to 1.0 (perfect) """ metrics = { 'correctness': check_correctness(answer, outcome), 'efficiency': measure_efficiency(answer), 'completeness': check_completeness(an
- Purpose
- When to Use
- Core Instructions
- Pattern: Experience Capture Loop
- Step 1: Score Task Outcome
- Step 2: Extract Patterns
- Step 3: Store as Token Prior
- Step 4: Apply to New Tasks
- Example Workflow
- Initial Task (No Experience)
- Similar Task Later (With Experience)
- Performance Characteristics
- Pattern Storage
- Best Practices
What does the experience-library skill do?
Capture task outcomes, score performance, and derive rules as token priors for continual learning without model weight changes. Use for post-task feedback, experience capture, pattern extraction, and learning from mistakes. Achieves continual learning for $18 per 100 samples vs $10k fine-tune cost. Triggers on "learn from experience", "capture patterns", "post-task analysis", "continual learning", "experience extraction".
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill experience-library-dredd-us-seashells-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.