self-improvement
Appends new entries to LESSONS-LEARNED.md via the opencastle lesson CLI, searches past lessons for matching errors, and proposes skill updates when retry patterns exceed thresholds. Use when consulting or updating LESSONS-LEARNED.md, after task failures, when capturing retrospective insights, or when a retry succeeds.
77
96%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
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 articulates specific capabilities, provides explicit trigger conditions, and occupies a distinct niche. It uses third person voice consistently and covers both the 'what' and 'when' comprehensively with natural trigger terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: appending entries to LESSONS-LEARNED.md via CLI, searching past lessons for matching errors, and proposing skill updates when retry patterns exceed thresholds. | 3 / 3 |
Completeness | Clearly answers both what (appends entries, searches past lessons, proposes skill updates) and when ('Use when consulting or updating LESSONS-LEARNED.md, after task failures, when capturing retrospective insights, or when a retry succeeds'). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users/Claude would encounter: 'LESSONS-LEARNED.md', 'task failures', 'retrospective insights', 'retry succeeds', 'lesson', 'errors'. These cover the natural scenarios where this skill would be needed. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific references to LESSONS-LEARNED.md, the opencastle lesson CLI, and retry pattern thresholds. Unlikely to conflict with other skills due to its narrow, well-defined niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-crafted skill that is concise, actionable, and has a clear workflow with validation checkpoints. The hard gate on CLI usage is an effective safety constraint, and the verification step with a fallback re-run is a good feedback loop. The only minor weakness is that the referenced LESSON-CATEGORIES.md file is not provided in the bundle, making the progressive disclosure slightly harder to fully validate.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what LESSONS-LEARNED.md is or how CLIs work. The anti-patterns section is terse bullet points. The content assumes Claude's competence throughout. | 3 / 3 |
Actionability | Provides a complete, copy-paste-ready CLI command with all flags, a concrete search example using `rg`, and a verification command (`tail -1`). The required vs optional flags are clearly delineated. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with explicit validation at step 5 (verify entry, re-run if malformed) and a feedback loop for failures at step 3. The hard gate on CLI usage and the post-write skill-update check add appropriate guardrails. | 3 / 3 |
Progressive Disclosure | Categories and severity are appropriately moved to LESSON-CATEGORIES.md, and agent-memory is referenced for cross-session knowledge. However, LESSON-CATEGORIES.md is not provided in the bundle, making it impossible to verify the reference resolves. The skill is otherwise well-structured but has only one external reference to evaluate. | 2 / 3 |
Total | 11 / 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
- monkilabs/opencastle
- Commit
cc13aaf
- 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.