learner
Extract a learned skill from the current conversation
36
33%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/learner/SKILL.mdQuality
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 conveys the general purpose, it would be difficult for Claude to reliably select this skill from a large pool because it doesn't specify when to use it or what concrete outputs it produces. Adding a 'Use when...' clause and more specific capability details would significantly improve it.
Suggestions
Add an explicit 'Use when...' clause with natural trigger phrases such as 'save this as a skill,' 'remember how to do this,' 'learn from this conversation,' or 'create a skill file.'
List specific concrete actions the skill performs, e.g., 'Analyzes the current conversation to identify reusable patterns, then generates a SKILL.md file with YAML frontmatter and step-by-step instructions.'
Include distinguishing terms that separate this from general summarization or note-taking skills, such as 'skill extraction,' 'skill file creation,' or 'SKILL.md.'
| Dimension | Reasoning | Score |
|---|---|---|
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 | Describes what it does at a high level but provides no 'Use when...' clause or explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' itself is also thin, bringing it to 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 'learn from this chat.' | 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
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers primarily from verbosity—the Expertise section contains extensive redundant guidance across Quality Gate, Recognition Signals, What Makes a USEFUL Skill, and Anti-Patterns that all communicate the same core idea. The workflow section is reasonably structured but lacks validation/feedback loops. The content would benefit significantly from consolidation of the overlapping quality criteria sections and addition of explicit verification steps.
Suggestions
Consolidate the Quality Gate, Recognition Signals, What Makes a USEFUL Skill, and Anti-Patterns sections into a single concise quality checklist—these four sections all express the same filtering criteria with different framing.
Add a verification step after Step 4 (e.g., 'Confirm the saved file is loadable by checking frontmatter parses correctly and triggers are specific enough to avoid false matches').
Remove the extensive BAD/GOOD example pairs and keep at most one illustrative example per criterion—Claude already understands the difference between generic and specific advice.
Move the detailed Skill Body Template to a separate reference file and keep only a brief summary in the main skill, or inline it more concisely since the template sections are self-explanatory.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~150+ lines. It explains concepts Claude already knows (what makes good vs bad skills, generic anti-patterns), includes extensive 'BAD/GOOD' examples that belabor obvious points, and has significant redundancy between the Quality Gate, Recognition Signals, What Makes a USEFUL Skill, and Anti-Patterns sections which all convey overlapping information. | 1 / 3 |
Actionability | The workflow steps provide a reasonable procedure and the file format template is concrete and copy-paste ready. However, much of the 'Expertise' section is abstract guidance about what constitutes a good skill rather than executable instructions, and the actual save paths use variable syntax that requires interpretation. The skill body template is actionable but the surrounding content is more philosophical than instructional. | 2 / 3 |
Workflow Clarity | The 4-step workflow (Gather → Validate → Classify → Save) is clearly sequenced, but there are no validation checkpoints or feedback loops. Step 2 mentions the system 'REJECTS' skills but doesn't specify what happens on rejection or how to iterate. There's no verification step to confirm the saved skill is correctly formatted or discoverable. | 2 / 3 |
Progressive Disclosure | The skill has some structure with clear section headers (Expertise vs Workflow) and references related commands at the end. However, the Expertise section is a monolithic block that could benefit from being split out, and the deprecation notice at the top pointing to another command creates a confusing navigation pattern. No bundle files are provided to offload the extensive examples. | 2 / 3 |
Total | 7 / 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.
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 | |
- Repository
- Yeachan-Heo/oh-my-claudecode
- Commit
3e94567
- 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.