self-improvement

Appends new entries to LESSONS-LEARNED.md via opencastle lesson CLI; searches past lessons for matching errors; 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.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly concise, actionable, and has a well-sequenced workflow with validation feedback loops. The main weakness is progressive disclosure: it points to LESSON-CATEGORIES.md for required valid values, but that file is not present in the bundle.

Suggestions

Add the missing LESSON-CATEGORIES.md file to the bundle (under ./references/ or alongside SKILL.md) so the link target for valid --category and --severity values actually resolves.

Alternatively, inline the valid --category and --severity enumerations directly in SKILL.md so the skill is self-contained without the dangling reference.

Confirm the LESSON-CATEGORIES.md reference path is correct relative to SKILL.md's location; if it lives elsewhere, fix the link so it resolves from where the skill is loaded.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — it assumes Claude's competence, gives only the actionable rule, the exact CLI command with required/optional flags, and a short workflow, with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Provides a fully executable, copy-paste-ready `opencastle lesson` command with concrete flags, a concrete verification command (`tail -1 .opencastle/LESSONS-LEARNED.md`), and a concrete search example (`rg "missing CRON_SECRET" ...`) covering the common cases.	5 / 5
Workflow Clarity	The 6-step workflow is clearly sequenced with an explicit validation/verification checkpoint (step 5: confirm entry has title/category/severity; if malformed → re-run) and a feedback loop for error recovery, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Content is well-sectioned for a short skill, but the body references [LESSON-CATEGORIES.md](LESSON-CATEGORIES.md) for valid category/severity values, and that referenced file is absent from the bundle — the navigation target does not exist.	3 / 5
	Total	18 / 20 Passed

Description

96%Weight 40%Scale 1-5

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 strong: specific, concrete actions paired with a comprehensive 'Use when...' trigger clause in third person. It clearly communicates both capability and invocation conditions with minimal fluff.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions — 'Appends new entries to LESSONS-LEARNED.md via opencastle lesson CLI', 'searches past lessons for matching errors', 'proposes skill updates when retry patterns exceed thresholds' — giving comprehensive, specific coverage.	5 / 5
Completeness	Explicitly answers both 'what' (appends entries via CLI, 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') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would actually say — 'task failures', 'retrospective insights', 'a retry succeeds', 'consulting or updating LESSONS-LEARNED.md' — with comprehensive coverage of trigger variations.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche around the LESSONS-LEARNED.md / opencastle lesson CLI workflow with distinct triggers, but the general 'after task failures' trigger could overlap with other retrospective or debugging skills.	4 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: monkilabs/opencastle
Path: src/orchestrator/skills/self-improvement/SKILL.md
Commit: fa0c341

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.