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".
91
86%
Does it follow best practices?
Impact
100%
3.70xAverage score across 3 eval scenarios
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 strong skill description that clearly communicates what the skill does (captures corrections as persistent learning rules with structured fields), how it works (stores, categorises, retrieves), and when to use it (after mistakes or with specific user phrases). It uses third person voice consistently and provides natural trigger terms that users would realistically say.
| 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 actions. | 3 / 3 |
Completeness | Clearly answers both 'what' (capture corrections/lessons as persistent learning rules with category, mistake, and correction; store, categorise, and retrieve rules) and 'when' (after mistakes or when user says specific trigger phrases). Explicit 'Use after/when' clause is present. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'remember this', 'don't forget', 'note this', 'learn from this', and contextual triggers like 'after mistakes'. These are realistic, natural-language phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Has a clear niche focused on persistent learning rules and corrections, with distinct trigger terms like 'remember this', 'learn from this'. Unlikely to conflict with other skills due to the specific domain of capturing and storing correction rules. | 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 communicates the intent and format for capturing learned rules. Its main weakness is the lack of specificity around the 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 guardrails section is a strength, providing good/bad examples for rule quality.
Suggestions
Specify the exact persistence mechanism: which file to write to (e.g., `LEARNED.md` or `.claude/learned_rules.md`), and what tool/command to use (e.g., `write_to_file` or `append`).
Add a verification step after persistence — e.g., 'Read back the file to confirm the rule was appended correctly' — since this is a write operation that modifies persistent state.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. Every section serves a purpose — trigger conditions, workflow, format, categories, example, and guardrails. No unnecessary explanations of concepts Claude already knows. | 3 / 3 |
Actionability | The format template and example are concrete, but the persistence step ('persist to LEARNED section or project memory') is vague — it doesn't specify how or where to actually write the rule (e.g., which file, what tool to use, what command). The workflow describes intent rather than executable steps. | 2 / 3 |
Workflow Clarity | The 4-step workflow is clearly sequenced and includes a user approval checkpoint before persisting, which is good. However, the actual persistence mechanism is unspecified (no file path, no tool invocation), and there's no validation or error recovery step for confirming the rule was actually saved correctly. | 2 / 3 |
Progressive Disclosure | For a skill under 50 lines with a single purpose, the content is well-organized with clear sections (Trigger, Workflow, Format, Categories, Example, Guardrails, Output). No external references are needed and the structure supports easy scanning. | 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
9df6af8
- 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.