learner

Extract a learned skill from the current conversation

Quality

46%

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 ./skills/learner/SKILL.md

Quality

Content

63%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 a well-structured, mostly actionable extraction skill with a clear sequenced workflow and explicit quality-gate validation. Its main weakness is conciseness, with the full BAD/GOOD examples and body template adding length that could be trimmed or offloaded to a reference file.

Suggestions

Tighten the Expertise BAD/GOOD contrast blocks or move the detailed examples to a reference file to reduce token load.

Add an explicit validate->fix->retry feedback loop to Step 2 so rejected skills are revised and re-validated rather than only listed as rejected.

Optionally extract the Skill Body Template into a separate bundled template file and reference it one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the Expertise section's BAD/GOOD contrast blocks and the full Skill Body Template add length that could be tightened; it sits at 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the leaner anchor 4.	3 / 5
Actionability	It provides concrete, executable guidance such as exact save paths ('.omc/skills/<skill-name>.md'), a required frontmatter block, and a copy-ready Skill Body Template with named sections, with only minor gaps (no example of a finished extracted file), matching 'mostly executable guidance; concrete code or commands with minor gaps' below the fully-copy-paste anchor 5.	4 / 5
Workflow Clarity	The extraction workflow is clearly sequenced (Gather -> Validate -> Classify -> Save) with an explicit quality-gate checkpoint (Step 2 REJECTS criteria) and a quality gate in Expertise, but the validation is a rejection list rather than a validate->fix->retry feedback loop, so it fits 'clear sequence with most checkpoints present; minor validation gaps' and not the explicit-feedback-loop anchor 5.	4 / 5
Progressive Disclosure	The content is well organized into clearly signaled Expertise/Workflow sections with a Related Commands pointer, and no bundle files exist so references are minimal and one level deep; it is essentially self-contained but slightly long where a separate template file could offload the Skill Body Template, fitting 'good structure; most content appropriately placed' below the optimally-split anchor 5.	4 / 5
	Total	15 / 20 Passed

Description

28%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 is a bare single sentence naming a single action with no 'Use when' trigger guidance and few natural keywords, so it underperforms on completeness and trigger quality. It is distinguishable enough as a niche skill but generic in phrasing.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when capturing a hard-won debugging insight or non-obvious gotcha from the current conversation.'

List the concrete actions performed (validate the insight against a quality gate, classify as expertise vs workflow, save to the appropriate location) to raise specificity.

Include natural user-facing keywords (e.g. 'learned skill', 'capture insight', 'save debugging lesson') so users would naturally say them.

Dimension	Reasoning	Score
Specificity	The phrase 'Extract a learned skill' names the domain and a single concrete action, but provides no further concrete actions (no validation, no classification, no save steps), matching 'Names the domain but actions are minimal or generic' rather than the multi-action anchor 3.	2 / 5
Completeness	It gives a clear-ish 'what' (extract a learned skill) but entirely lacks any 'when/Use when' clause, which the guidelines say caps completeness at 3; with no trigger guidance and only a minimal 'what' it fits anchor 2 better than 3.	2 / 5
Trigger Term Quality	It contains only the technical phrase 'learned skill' with no natural trigger terms a user would say (e.g. 'save what you learned', 'capture this debugging insight'), so it sits at 'one or two generic keywords; missing the natural phrases users say' and below anchor 3.	2 / 5
Distinctiveness Conflict Risk	'Extract a learned skill from the current conversation' is somewhat specific to the skill-extraction niche but could still overlap with related note/learning skills (e.g. the referenced /skillify), placing it at 'somewhat specific but could still overlap' rather than the clearly-niche anchor 4.	3 / 5
	Total	9 / 20 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
Path: skills/learner/SKILL.md
Commit: 5aa678c

Reviewed: 8 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.