learn-rule
Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says "remember this", "don't forget", "note this", or "learn from this".
71
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly communicates its purpose, lists concrete actions, and provides explicit trigger guidance with natural user phrases. It uses proper third-person voice throughout and covers both the 'what' and 'when' comprehensively. The description is concise yet thorough, making it easy for Claude to select this skill appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Capture a correction or lesson as a persistent learning rule', 'with category, mistake, and correction', 'Stores, categorises, and retrieves rules for future sessions'. These are concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (capture corrections/lessons as persistent learning rules, store/categorize/retrieve them) and 'when' (after mistakes, or when user says 'remember this', 'don't forget', 'note this', 'learn from this') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes highly natural trigger phrases users would actually say: 'remember this', 'don't forget', 'note this', 'learn from this', plus contextual triggers like 'after mistakes'. These are realistic user utterances with good coverage. | 3 / 3 |
Distinctiveness Conflict Risk | Has a clear niche around persistent learning rules and corrections with distinct trigger terms. The combination of 'correction', 'lesson', 'persistent learning rule', and the specific quoted trigger phrases makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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, concise skill that clearly defines when and how to capture learning rules. Its main weakness is the vagueness around the actual persistence mechanism — it tells Claude to 'persist to LEARNED section or project memory' without specifying the concrete file path, tool, or command to use. The wiki-scoped rules section references a 'capture hook' that is never defined, adding ambiguity.
Suggestions
Specify the exact persistence mechanism: which file to write to (e.g., `LEARNED.md` or `.claude/learned_rules.md`), and whether to use a specific tool or command to append the rule.
Clarify or remove the 'capture hook auto-detects' reference — either explain what this hook is and how it works, or remove the sentence to avoid confusion.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It avoids explaining concepts Claude already knows, uses tables and structured formats to convey information densely, and every section serves a clear purpose. The guardrails section efficiently distinguishes good from bad rules with concrete examples. | 3 / 3 |
Actionability | The skill provides a clear format template and a concrete example, but the persistence mechanism is vague — 'persist to LEARNED section or project memory' doesn't specify how (which file, what tool to use, what command). The workflow steps are descriptive rather than executable, and the 'capture hook auto-detects' reference is unexplained. | 2 / 3 |
Workflow Clarity | The four-step workflow is clearly sequenced and includes a user approval checkpoint before persisting, which is good. However, the actual persistence step lacks specifics (where exactly to write, how to append), and there's no validation or error recovery step after persisting (e.g., confirming the rule was written correctly). | 2 / 3 |
Progressive Disclosure | For a skill of this size and scope (~60 lines, single-purpose), the content is well-organized with clear sections (Trigger, Workflow, Format, Categories, Example, Guardrails, Output). No bundle files are needed, and the structure supports easy scanning without unnecessary nesting. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%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.
- Repository
- rohitg00/pro-workflow
- Commit
9fc35f5
- 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.