continuous-learning

Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。

Quality

48%

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/ja-JP/skills/continuous-learning/SKILL.md

Quality

Content

50%Weight 40%Scale 1-5

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

The body is reasonably organized with concrete config and hook examples, but it inlines research notes that belong in a separate file, omits the actual extraction script, and lacks validation checkpoints for an auto-save batch operation.

Suggestions

Include the contents of 'evaluate-session.sh' (or a scripts/ entry) so the extraction logic is executable rather than merely referenced.

Add validation/verification steps to the workflow (e.g., confirm a detected pattern meets the threshold before writing a skill, and re-check after save).

Move the '比較ノート' competitive-research section into the referenced 'docs/continuous-learning-v2-spec.md' to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	Most sections are efficient (config JSON, pattern table), but the inlined '比較ノート' competitive-research section and rationale blocks add explanation that does not directly aid execution, fitting 'mostly efficient but could be tightened'.	3 / 5
Actionability	Concrete config and hook-setup JSON are provided, but the core execution logic is delegated to a referenced 'evaluate-session.sh' that is never shown, leaving key details incomplete.	3 / 5
Workflow Clarity	A three-step sequence (evaluate → detect → extract) is listed, but no validation checkpoints exist; because this is a batch/auto-save operation, the missing feedback loop caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Sections provide some structure, but the research/comparison notes are inlined rather than kept in the referenced 'docs/continuous-learning-v2-spec.md', and no bundle files exist to support the referenced paths.	3 / 5
	Total	12 / 20 Passed

Description

46%Weight 40%Scale 1-5

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 states what the skill does but omits any explicit 'when to use it' trigger guidance, which caps completeness and weakens trigger-term quality. It is reasonably specific and distinct within its niche.

Suggestions

Add an explicit 'Use when ...' clause stating when Claude should invoke this skill (e.g., at session end, when a reusable pattern is suspected).

Include natural trigger terms and synonyms users would actually say, such as 'session learning', 'learn from session', or 'save reusable patterns'.

Optionally mention the target condition (e.g., long sessions with repeated fixes) to sharpen the 'when'.

Dimension	Reasoning	Score
Specificity	Names the domain ('Claude Codeセッション', '再利用可能なパターン') and two concrete actions ('抽出し', '保存します'), matching the anchor for 1-2 concrete actions but not comprehensive coverage.	3 / 5
Completeness	The 'what' is clear (extract patterns, save as learned skills) but there is no explicit 'when' trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Only domain-specific terms ('再利用可能なパターン', '学習済みスキル') appear; no natural 'Use when...' trigger phrases or synonyms a user would naturally say, placing it below the midpoint.	2 / 5
Distinctiveness Conflict Risk	The session-pattern-extraction niche is fairly distinct from most skills with only minor overlap risk, fitting 'mostly distinct' better than the midpoint anchor.	4 / 5
	Total	12 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: affaan-m/ECC
Path: docs/ja-JP/skills/continuous-learning/SKILL.md
Commit: e04ea0b

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.