CtrlK
BlogDocsLog inGet started
Tessl Logo

learner

Extract a learned skill from the current conversation

46

Quality

48%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/learner/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

32%

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 too terse and lacks both concrete action details and explicit trigger guidance. While it hints at a specific niche (skill extraction), it doesn't enumerate the concrete steps involved or tell Claude when to select this skill, making it hard to reliably match against user requests.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases such as 'save this as a skill,' 'remember how to do this,' 'create a SKILL.md,' or 'extract a skill from this chat.'

List specific concrete actions the skill performs, e.g., 'Identifies reusable patterns from the conversation, generates a SKILL.md file with YAML frontmatter, description, and step-by-step instructions.'

Include file-type or artifact references (e.g., 'SKILL.md', 'markdown skill file') to improve distinctiveness and reduce conflict with generic summarization or note-taking skills.

DimensionReasoningScore

Specificity

Names a specific action ('extract a learned skill') and a context ('current conversation'), but doesn't elaborate on what that entails—e.g., creating a markdown file, identifying patterns, writing YAML frontmatter, etc.

2 / 3

Completeness

Provides a brief 'what' but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' itself is thin enough to warrant a 1.

1 / 3

Trigger Term Quality

Contains some relevant terms like 'skill' and 'conversation,' but misses natural user phrases such as 'save this as a skill,' 'remember how to do this,' 'create a skill file,' or 'SKILL.md.'

2 / 3

Distinctiveness Conflict Risk

The phrase 'learned skill from the current conversation' is somewhat distinctive but could overlap with skills related to summarization, note-taking, or knowledge extraction from conversations.

2 / 3

Total

7

/

12

Passed

Implementation

64%

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

This is a well-structured skill with strong actionability—concrete templates, specific file paths, and clear good/bad examples make it immediately usable. Its main weaknesses are moderate verbosity (the Expertise section repeats similar concepts across Quality Gate, Recognition Signals, What Makes a USEFUL Skill, and Anti-Patterns) and a workflow that lacks explicit validation/feedback loops for error recovery when a skill draft doesn't meet quality standards.

Suggestions

Add a validation feedback loop in the workflow: after Step 2 (Quality Validation), specify what to do if the skill fails the gate—e.g., 'If any gate fails, either discard or refine the insight until all three pass.'

Consolidate the overlapping sections (Quality Gate, Recognition Signals, What Makes a USEFUL Skill, Anti-Patterns) into a single concise checklist to reduce redundancy and save ~40 tokens.

DimensionReasoningScore

Conciseness

The skill is moderately verbose. The 'Core Principle' section with BAD/GOOD examples is useful but the anti-patterns section largely restates the quality gate and recognition signals. The deprecation notice and meta-commentary about 'Level 7 (self-improving)' adds tokens without actionable value. Some sections like 'What Makes a USEFUL Skill' repeat concepts already covered by the Quality Gate.

2 / 3

Actionability

The skill provides highly concrete guidance: specific file paths for save locations, a complete YAML frontmatter template, a full skill body template with section headers, exact quality gate questions to ask, and concrete good/bad examples for each criterion. The workflow steps are specific and executable.

3 / 3

Workflow Clarity

The 4-step workflow (Gather → Validate → Classify → Save) is clearly sequenced, but there's no explicit validation checkpoint or feedback loop. Step 2 says the system 'REJECTS' skills but doesn't specify what happens next—no retry/fix guidance. For a skill that involves writing files, there's no verification step to confirm the saved skill is correctly formatted or loadable.

2 / 3

Progressive Disclosure

The skill has good internal structure with clear section headers (Expertise vs Workflow) and the separation is well-signaled. However, it's a fairly long monolithic document (~150 lines of content) with no references to external files for detailed content. The related commands at the bottom hint at a broader system but the skill itself could benefit from splitting the extensive examples and anti-patterns into a reference file.

2 / 3

Total

9

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
Yeachan-Heo/oh-my-claudecode
Reviewed

Table of Contents

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.