continuous-learning

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

Quality

50%

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

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 structured and supplies useful config and hook examples, but it embeds extraneous research notes, references missing script/spec files, and lacks validation steps for its automated batch workflow.

Suggestions

Remove or relocate the '比較筆記 / Homunculus comparison' and '為什麼用 Stop Hook' sections into a separate reference file to trim the context load.

Add the actual evaluate-session.sh script (or its contents) and the referenced docs/continuous-learning-v2-spec.md so references resolve to real bundle files.

Insert validation checkpoints into the workflow (e.g. verify a session meets min length, confirm a detected pattern before saving) to support the batch extraction operation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient (config example, pattern table, hook setup) but the entire Homunculus comparison-notes section and 'why Stop Hook' rationale are padding Claude does not need to execute the skill.	3 / 5
Actionability	Provides concrete config.json and hook JSON, but the referenced evaluate-session.sh is not shown and the actual extraction logic is missing, leaving key execution details absent.	3 / 5
Workflow Clarity	Three steps are sequenced but there are no validation checkpoints or feedback loops, and for batch/automated operations the rubric caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	Sections are organized, but the comparison notes and v2 spec belong in separate files and references point to non-existent bundle files (evaluate-session.sh, docs/continuous-learning-v2-spec.md).	3 / 5
	Total	12 / 20 Passed

Description

50%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' guidance, capping completeness. Trigger keywords are present but lack natural synonyms users would say.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when a Claude Code session ends and you want to capture reusable patterns or learned skills.'

Broaden trigger terms with natural user phrasings and synonyms such as 'learn from sessions', 'save patterns', 'session insights'.

Add one or two more concrete actions (e.g. 'detect error resolutions and workarounds') to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('extract reusable patterns', 'save them as learned skills') but coverage is not comprehensive enough for a 4.	3 / 5
Completeness	Has a clear 'what' but no 'Use when...' trigger clause; per the rubric a missing explicit 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ('Claude Code sessions', 'reusable patterns', 'learned skills') but lacks common user phrasings and synonyms like 'learn from sessions' or 'save patterns'.	3 / 5
Distinctiveness Conflict Risk	Targets a specific niche (session pattern extraction into learned skills) with minimal overlap risk, though 'patterns'/'sessions' could touch other learning skills, keeping it just below 5.	4 / 5
	Total	13 / 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/zh-TW/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.