learner

Extract a learned skill from the current conversation

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is a well-structured meta-skill with concrete, copy-paste-ready templates, exact save locations, and a clearly sequenced workflow with explicit validation checkpoints. Its main weaknesses are repeated 'avoid generic extractions' messaging that bloats the token budget and a lack of file-based progressive disclosure for a longer single-file skill.

Suggestions

Consolidate the recurring 'do not extract generic/easily-Googleable patterns' guidance into a single Anti-Patterns section to remove repetition across Core Principle, USEFUL Skill, and Quality Validation.

Consider splitting the full Skill Body Template and the BAD/GOOD example catalog into a referenced file (e.g. references/templates.md) so the main SKILL.md stays a lean overview.

Make the validation feedback loop explicit in Step 2, e.g. 'If a candidate fails any criterion, revise the problem statement/triggers and re-validate before saving.'

Dimension	Reasoning	Score
Conciseness	The body is mostly high-signal heuristics, but the 'avoid generic/non-codebase-specific extractions' message repeats across Core Principle, What Makes a USEFUL Skill, Anti-Patterns, and Quality Validation, so it could be tightened; it does not pad with concepts Claude already knows, ruling out a 1.	2 / 3
Actionability	The workflow gives exact save paths ('${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/<skill-name>.md', '.omc/skills/<skill-name>.md'), file-naming rules, and copy-paste-ready frontmatter and body templates, providing fully executable, specific guidance.	3 / 3
Workflow Clarity	A clear 4-step sequence (Gather -> Validate -> Classify -> Save) is paired with an explicit validation gate in Step 2 and checklists (the 'ALL three must be true' Quality Gate and the four rejection criteria), matching the clear-sequence-with-explicit-validation anchor.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers and separators, but the skill is a single ~160-line file with no bundle references, and the extensive BAD/GOOD examples and full templates are inline; the under-50-lines exemption does not apply, so it falls short of file-based progressive disclosure at 3.	2 / 3
	Total	10 / 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 is clear and grammatically third-person but thin: it states a single action with no 'Use when...' trigger guidance and no natural keyword variations. It reads as a capability label rather than a discoverable, trigger-rich description.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to capture a hard-won, codebase-specific lesson from the current conversation as a reusable skill.'

Include natural trigger variations a user might actually say, such as 'save what we learned', 'turn this into a skill', or 'remember this gotcha'.

Sharpen distinctiveness from /skillify and /note by stating what makes this skill's trigger unique (e.g. capturing debugging insights vs. quick notes).

Dimension	Reasoning	Score
Specificity	The phrase 'Extract a learned skill' names a concrete action and domain, but only one action rather than the multiple specific actions required for a 3; it is well above the vague 'Helps with documents' anchor at 1.	2 / 3
Completeness	It clearly states what the skill does ('Extract a learned skill from the current conversation') but gives no explicit 'when to use it' guidance; per the guidelines a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	'learned skill' and 'current conversation' are somewhat natural, but there are no common trigger variations and no user-facing 'Use when...' phrasing, leaving it short of the broad natural-term coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	Skill extraction is a recognizable niche, but the file is a deprecated alias for /skillify and lists /note as related, so it could overlap with similar skills rather than having fully distinct triggers.	2 / 3
	Total	8 / 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: Yeachan-Heo/oh-my-claudecode
Commit: 6c59219

Reviewed: about 4 hours 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.