The description communicates the core purpose reasonably well—extracting patterns from Claude Code sessions to create reusable skills—but lacks the specificity and explicit trigger guidance needed for reliable skill selection. It would benefit from listing concrete actions and adding a 'Use when...' clause with natural trigger terms.

Suggestions

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

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

Include natural trigger terms users might say, such as 'save this as a skill', 'remember how to do this', 'create a skill file', 'SKILL.md'.

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 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', 'remember this pattern', or 'extract workflow'.	2 / 3
Distinctiveness Conflict Risk	The concept of extracting patterns from sessions is somewhat specific, but 'reusable patterns' and 'learned skills' are broad enough to potentially overlap with other meta-learning or documentation skills.	2 / 3
	Total	8 / 12 Passed

Implementation

37%

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

The skill provides good configuration examples and hook setup instructions, but falls short on the core task: it never shows how pattern extraction actually works (the evaluate-session.sh script is referenced but not provided). The comparison notes section consumes significant tokens without helping Claude execute the skill. The workflow lacks validation steps for a process that automatically writes files to disk.

Suggestions

Provide the actual evaluate-session.sh script or its core logic so Claude can implement/maintain the pattern extraction rather than just referencing an opaque script.

Add validation steps after pattern extraction: e.g., review extracted skill content, verify file format, check for duplicates before saving to ~/.claude/skills/learned/.

Move the Homunculus comparison and v2 enhancement notes to a separate docs/comparison.md file and link to it, keeping the main skill focused on actionable instructions.

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

Dimension	Reasoning	Score
Conciseness	The skill includes useful configuration and setup details, but the comparison notes section at the bottom is verbose and largely informational rather than actionable. The 'Why Stop Hook?' section explains things Claude already understands. The Homunculus comparison and v2 enhancement ideas add significant length without helping Claude execute the skill.	2 / 3
Actionability	The hook setup JSON and config.json are concrete and copy-paste ready, which is good. However, the actual core task—extracting patterns from sessions—is described abstractly ('Checks if session has enough messages', 'Identifies extractable patterns') without showing the evaluate-session.sh script contents or concrete extraction logic. Claude wouldn't know how to actually implement the pattern extraction.	2 / 3
Workflow Clarity	The 3-step 'How It Works' section is extremely high-level with no validation checkpoints. There's no guidance on what to do if extraction fails, how to verify extracted skills are valid, or how to handle edge cases. For a system that automatically writes files to disk (~/.claude/skills/learned/), the absence of any validation or review step is a significant gap.	1 / 3
Progressive Disclosure	There are references to external files (docs/continuous-learning-v2-spec.md, the longform guide) and the learned skills directory, but the main file itself contains a large comparison section that could be in a separate reference doc. The structure has clear sections but the inline comparison table and v2 enhancement notes bloat the primary skill file.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Reviewed

2 days ago

Table of Contents

Discovery Implementation Validation