This skill is more of a design document/research note than an actionable skill for Claude. It spends significant tokens on comparisons with external projects and future enhancement ideas while leaving the core mechanism (how patterns are actually extracted and validated) completely unspecified. The configuration examples are concrete but the actual workflow is too vague to be useful.

Suggestions

Remove the entire 'Comparison Notes' and 'Potential v2 Enhancements' sections (or move to a separate RESEARCH.md file) — they consume ~40% of tokens without helping Claude execute the skill.

Show the actual pattern extraction logic or at minimum the evaluate-session.sh script contents, so Claude knows what's being executed and can debug issues.

Add explicit validation steps: how to verify an extracted pattern is valid before saving, what to do if extraction fails, and how to review/prune learned skills.

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

Dimension	Reasoning	Score
Conciseness	The skill contains significant bloat: a comparison table with an external project (Homunculus), research notes dated Jan 2025, a 'Potential v2 Enhancements' section, and explanations of why a Stop hook was chosen. The comparison section alone is ~40% of the content and provides no actionable guidance for Claude. The 'Why Stop Hook?' section explains rationale Claude doesn't need.	1 / 3
Actionability	The hook setup JSON and config.json are concrete and copy-paste ready, which is good. However, the core mechanism—the actual evaluate-session.sh script and how pattern extraction works—is never shown or explained. Claude wouldn't know how to actually implement or debug the extraction logic from this skill alone.	2 / 3
Workflow Clarity	The 3-step 'How It Works' section is extremely vague ('Checks if session has enough messages', 'Identifies extractable patterns', 'Saves useful patterns') with no validation steps, no error handling, and no feedback loops. For a system that writes files to disk automatically, there's no verification that extracted patterns are valid or useful before saving.	1 / 3
Progressive Disclosure	The skill references related files (the longform guide, a v2 spec at a local path, learned skills directory) but the main content itself is bloated with comparison notes that should be in a separate file. The structure has clear sections but mixes operational guidance with research notes in a single document.	2 / 3
	Total	6 / 12 Passed

Description

50%

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 the core purpose reasonably well—extracting patterns from sessions and saving them as skills—but lacks explicit trigger guidance ('Use when...') and specific concrete actions. It would benefit from more natural trigger terms users might say and a clearer delineation of when this skill should activate versus other pattern/template skills.

Suggestions

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

Include natural trigger terms users would say, such as 'save skill', 'SKILL.md', 'remember this', 'create skill from session', 'extract workflow'.

List more specific concrete actions, e.g., 'Analyzes conversation history, identifies repeatable workflows, generates SKILL.md files with proper 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 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	Somewhat specific to the niche of skill extraction from Claude Code sessions, but 'reusable patterns' and 'learned skills' are broad enough to potentially overlap with general knowledge management or template-creation skills.	2 / 3
	Total	8 / 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.

Reviewed

3 months ago

Table of Contents

Discovery Implementation Validation