continuous-learning

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

Quality

40%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./docs/zh-TW/skills/continuous-learning/SKILL.md

Quality

Discovery

57%

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 communicates a clear and distinctive purpose—extracting reusable patterns from sessions and saving them as skills—but lacks explicit trigger guidance ('Use when...') and could benefit from more specific concrete actions and natural user-facing keywords. It is reasonably distinguishable from other skills but falls short on completeness and trigger term coverage.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to save a pattern, create a skill, remember a workflow, or extract learnings from a session.'

Include more natural trigger terms users might say, such as 'save skill', 'SKILL.md', 'remember this', 'create a reusable pattern', or 'skill file'.

List more specific concrete actions, e.g., 'Analyzes session transcripts, identifies repeatable workflows, generates SKILL.md files with frontmatter and instructions.'

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 specific 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 lacks an explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some relevant terms like 'patterns', 'Claude Code sessions', 'learned skills', but misses natural user phrases like 'save skill', 'create skill file', 'SKILL.md', 'skill extraction', or 'remember this for later'.	2 / 3
Distinctiveness Conflict Risk	The concept of extracting patterns from Claude Code sessions and saving them as learned skills is a fairly unique niche that is unlikely to conflict with other skills like general code generation or document processing.	3 / 3
	Total	9 / 12 Passed

Implementation

22%

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. The core execution logic (how to actually evaluate sessions and extract patterns) is missing, replaced by configuration examples and architectural comparisons. The comparison notes and v2 enhancement sections consume significant tokens without providing actionable guidance.

Suggestions

Remove the 'Comparison Notes' and 'Potential v2 Enhancements' sections entirely, or move them to a separate design doc—they provide no actionable guidance for Claude.

Add the actual implementation or concrete steps for evaluate-session.sh, including what pattern detection looks like in practice and an example of a generated skill file.

Add explicit validation steps: how to verify an extracted skill is valid, what to do if extraction produces low-quality output, and how to handle sessions with insufficient learnable content.

Remove the 'Why Stop Hook?' section—Claude doesn't need architectural justification, just instructions on what to do.

Dimension	Reasoning	Score
Conciseness	The skill contains significant unnecessary content: the comparison notes section with Homunculus is research/design discussion that doesn't help Claude execute the skill. The pattern types table explains concepts at a level Claude doesn't need. The 'Why Stop Hook?' section explains obvious architectural decisions. The 'Potential v2 enhancements' section is aspirational/roadmap content with no actionable value.	1 / 3
Actionability	The skill provides concrete JSON configuration examples and a hook setup command, which are copy-paste ready. However, the core mechanism—the actual session evaluation and pattern extraction logic—is entirely absent. There's no code for evaluate-session.sh, no examples of what extracted skills look like, and no guidance on how patterns are actually detected or stored.	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 happens when extraction fails, how to verify extracted skills are correct, or how to handle edge cases. For a skill that automatically writes files to disk, missing validation/verification steps is a significant gap.	1 / 3
Progressive Disclosure	There are references to external files (config.json, docs/continuous-learning-v2-spec.md, evaluate-session.sh) and a link to a longform guide, showing some progressive disclosure. However, the main file itself contains too much inline content that should be separated (comparison notes, v2 enhancements), and the reference to the v2 spec doc is buried at the bottom.	2 / 3
	Total	6 / 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: ysyecust/everything-claude-code
Commit: 79cc4e3

Reviewed: 8 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.