continuous-learning

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Quality

27%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./docs/zh-TW/skills/continuous-learning/SKILL.md

Quality

Content

22%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads more like a design document or README than an actionable skill for Claude. It spends significant tokens on comparisons with other tools, future enhancement ideas, and justifications rather than concrete implementation guidance. The core mechanism (the evaluate-session.sh script and pattern extraction logic) is never shown, making it difficult for Claude to actually execute or troubleshoot the workflow.

Suggestions

Remove the 'Comparison Notes' and 'Potential v2 Enhancements' sections entirely, or move them to a separate docs/ file—they are research notes, not actionable skill content.

Provide the actual evaluate-session.sh script content or at minimum show a concrete example of what a learned skill file looks like after extraction.

Add explicit validation steps: how to verify the hook is installed correctly, how to check if a session was evaluated, and how to review/approve/reject extracted patterns.

Remove the 'Why Stop Hook?' section—Claude doesn't need justification for architectural decisions, just the instructions.

Dimension	Reasoning	Score
Conciseness	The skill contains significant bloat: a comparison table with Homunculus that is research/notes rather than actionable guidance, explanations of why a Stop hook is used (Claude doesn't need this justification), a 'Potential v2 Enhancements' roadmap section, and pattern type descriptions that are largely self-evident. Much of the content is informational rather than instructional.	1 / 3
Actionability	The hook configuration JSON and config.json are concrete and copy-paste ready, which is good. However, the core mechanism (evaluate-session.sh) is referenced but never shown or explained—there's no actual implementation of the pattern extraction logic, no example of what a learned skill file looks like, and no concrete commands for testing or verifying the setup works.	2 / 3
Workflow Clarity	The three-step workflow (evaluate → detect → extract) is described at a very high level with no validation checkpoints. There's no guidance on what to do if extraction fails, how to verify learned skills are correct, or how to review/approve extracted patterns when auto_approve is false. For a system that automatically writes files, missing validation is a significant gap.	1 / 3
Progressive Disclosure	There are references to external files (docs/continuous-learning-v2-spec.md, config.json) and a link to an external guide, but no bundle files are provided to support them. The comparison notes and v2 enhancements section should be in a separate document rather than inline. The main content structure is reasonable but polluted with research notes.	2 / 3
	Total	6 / 12 Passed

Description

32%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description conveys a reasonable high-level concept but lacks the specificity and explicit trigger guidance needed for reliable skill selection. It doesn't include a 'Use when...' clause, which is a significant gap for completeness. The actions described are too general—listing concrete steps like 'analyzes conversation history, identifies repeatable workflows, generates SKILL.md files' would strengthen it considerably.

Suggestions

Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks to save a pattern, create a skill from this session, or remember how to do something.'

List specific concrete actions such as 'analyzes conversation history, identifies repeatable commands or workflows, and generates reusable SKILL.md files.'

Include natural trigger terms users might say, such as 'save this as a skill', 'learn from this session', 'remember this workflow', 'extract skill'.

Dimension	Reasoning	Score
Specificity	Names the domain (extracting patterns from Claude Code sessions) and a general action (save as learned skills), but doesn't list multiple concrete actions like what kinds of patterns, how extraction works, or what formats are saved.	2 / 3
Completeness	Describes what it does (extract reusable patterns and save as skills) but has no explicit 'Use when...' clause or trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also somewhat vague, bringing it to 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'patterns', 'Claude Code sessions', 'learned skills', but misses natural user phrases like 'save skill', 'remember this', 'create a skill', 'skill extraction', or 'session patterns'.	2 / 3
Distinctiveness Conflict Risk	The concept of extracting patterns from Claude Code sessions is somewhat specific, but 'reusable patterns' and 'learned skills' could overlap with other meta-learning or skill-management tools without clearer scoping.	2 / 3
	Total	7 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: affaan-m/ECC
Path: docs/zh-TW/skills/continuous-learning/SKILL.md
Commit: 06c5e11

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.