continuous-learning

自动从 Claude Code 会话（Session）中提取可重用的模式（Pattern），并将其作为已学习的技能（Skill）保存以备将来使用。

Quality

42%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./docs/ja-JP/skills/continuous-learning/SKILL.md

Quality

Content

50%

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

The body is well-structured with concrete config and hook examples, but it is weakened by an inline research/comparison section, a dated survey note, a private absolute path, and a referenced extraction script that is not bundled. Validation steps for the batch extraction workflow are also missing.

Suggestions

Move the '比较笔记' / Homunculus comparison and v2 enhancement notes into a separate reference file and keep SKILL.md focused on execution.

Provide the evaluate-session.sh script (or its logic) in ./scripts/ so the core workflow is actually executable, and remove the user-specific /Users/affoon/... path.

Add a validation/verification checkpoint to the workflow (e.g., confirm a detected pattern is novel and well-formed before saving it as a learned skill).

Dimension	Reasoning	Score
Conciseness	The core sections are reasonably lean, but the inline comparison/research notes (dated '2025年1月'), the Homunculus table, and a user-specific absolute path (/Users/affoon/...) add tokens that do not help Claude execute the skill.	2 / 3
Actionability	Concrete config.json and Stop-hook JSON examples are provided and largely copy-pasteable, but the referenced evaluate-session.sh script is not present in any bundle, leaving the core extraction logic undefined.	2 / 3
Workflow Clarity	The three steps (session evaluation, pattern detection, skill extraction) are sequenced, but a batch automated operation on session data has no validation or verification checkpoints, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are clearly organized, but inline research/comparison content that should live in a separate reference file, plus dangling references to a missing script and a private local path, prevent a top score.	2 / 3
	Total	8 / 12 Passed

Description

35%

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 clearly conveys what the skill does but omits any explicit 'when to use it' trigger and leans on internal jargon rather than natural user keywords. It is a solid but incomplete description that would benefit from trigger guidance and more concrete action language.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should activate this skill (e.g., 'Use when a Claude Code session ends and you want to capture reusable patterns').

Replace internal jargon like 'learned skills' and 'reusable patterns' with natural trigger terms a user would actually say.

Expand the action list to more concrete, specific operations (e.g., 'detect error-resolution and debugging patterns, save them under ~/.claude/skills/learned/').

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('extract reusable patterns', 'save them as learned skills'), but the actions are somewhat abstract and not a comprehensive list of specific concrete actions.	2 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	The terms ('Claude Code sessions', 'reusable patterns', 'learned skills') are skill-internal jargon rather than natural phrases a user would say when they need this skill.	1 / 3
Distinctiveness Conflict Risk	The session-pattern-extraction niche is fairly specific, but without explicit triggers it could still overlap with related learning/memory skills.	2 / 3
	Total	7 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: xu-xiang/everything-claude-code-zh
Path: docs/ja-JP/skills/continuous-learning/SKILL.md
Commit: dfbf946

Reviewed: 2 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.