Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Use after mistakes or when the user says "remember this".
92
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
75%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 description effectively communicates both purpose and trigger conditions, making it functional for skill selection. The main weaknesses are moderate specificity in describing capabilities and limited coverage of natural trigger phrases users might employ. The description successfully carves out a distinct niche for correction/learning capture.
Suggestions
Expand trigger terms to include common variations like 'don't forget', 'note this for next time', 'learn from this', or 'save this correction'
Add more specific actions beyond 'capture' such as 'stores', 'categorizes', 'retrieves', or 'applies to future interactions'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (learning rules) and some actions (capture correction/lesson with category, mistake, correction), but doesn't comprehensively list all capabilities or concrete actions beyond the basic capture function. | 2 / 3 |
Completeness | Clearly answers both what ('Capture a correction or lesson as a persistent learning rule with category, mistake, and correction') and when ('Use after mistakes or when the user says "remember this"') with explicit triggers. | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'remember this' and 'mistakes', but missing common variations users might say like 'don't forget', 'note this', 'learn from this', 'save this rule', or 'I corrected you'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on capturing corrections and learning rules with distinct triggers ('remember this', 'after mistakes'); unlikely to conflict with general note-taking or documentation skills due to the specific correction/lesson framing. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
100%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-crafted skill that efficiently teaches Claude how to capture learning rules. It excels in providing concrete formats, clear workflows with approval checkpoints, and actionable examples. The category table adds useful structure without verbosity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, with no unnecessary explanations. Every section serves a purpose and assumes Claude understands basic concepts like memory persistence and rule formatting. | 3 / 3 |
Actionability | Provides concrete format templates, a clear workflow with numbered steps, specific trigger phrases, and a practical example showing exact input/output. The guardrails give specific actionable guidance (e.g., 'Always use snake_case for database columns' vs 'Write good code'). | 3 / 3 |
Workflow Clarity | Clear 4-step workflow with explicit approval checkpoint before persisting. The guardrail 'Always wait for user approval before persisting' ensures validation before destructive/permanent changes. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized with clear sections (Trigger, Workflow, Format, Categories, Example, Guardrails, Output). The category table provides quick reference without bloating the main content. | 3 / 3 |
Total | 12 / 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.
Table of Contents
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.