memory-merger
Reviews mature LESSONS-LEARNED.md entries, rewrites them as permanent rules in skill/instruction files, and archives graduated lessons. Use when graduating lessons into skills, promoting validated lessons, updating skills from past learnings, archiving mature lessons, codifying repeated patterns, or cleaning up a crowded LESSONS-LEARNED.md.
72
88%
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 an excellent skill description that clearly articulates what the skill does (reviews, rewrites, and archives lessons-learned entries into permanent skill files) and when to use it (with six specific trigger scenarios). The description is concise, uses third-person voice, includes natural trigger terms, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'reviews mature LESSONS-LEARNED.md entries', 'rewrites them as permanent rules in skill/instruction files', and 'archives graduated lessons'. These are clear, actionable operations. | 3 / 3 |
Completeness | Clearly answers both 'what' (reviews, rewrites, archives lessons-learned entries into skill files) and 'when' with an explicit 'Use when...' clause listing six specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'graduating lessons into skills', 'promoting validated lessons', 'updating skills from past learnings', 'archiving mature lessons', 'codifying repeated patterns', 'cleaning up a crowded LESSONS-LEARNED.md'. Good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on the LESSONS-LEARNED.md to skill file graduation workflow. The specific file references (LESSONS-LEARNED.md, skill/instruction files) and the concept of 'graduating lessons' make it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 skill with clear workflow sequencing, good validation checkpoints, and efficient use of tokens. Its main weakness is moderate actionability — while the templates and formats are helpful, the skill lacks executable commands for validation steps and defers its only concrete example to an external file that isn't provided. The anti-patterns section adds valuable guardrails.
Suggestions
Include a brief inline worked example (even abbreviated) rather than deferring entirely to REFERENCE.md, so the skill is self-contained for the most common case.
Make step 6 'run validation checks' more concrete — specify what validation commands or checks to run (e.g., markdown lint command, grep command for duplicate detection).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. Every section serves a purpose — run criteria, workflow, merge protocol, quality gates, and anti-patterns. There's no unnecessary explanation of concepts Claude already knows. The table format for criteria is efficient. | 3 / 3 |
Actionability | The workflow steps are clear and the merge protocol provides concrete templates (draft edit format, attribution comment syntax, archive format). However, there are no executable code/commands — the 'validation checks' in step 6 are vague, and the worked example is deferred to REFERENCE.md rather than shown inline. The guidance is specific but not fully copy-paste ready. | 2 / 3 |
Workflow Clarity | The workflow is clearly numbered with six sequential steps. Steps 3-6 are expanded with detailed sub-instructions. Quality gates provide explicit validation checkpoints including a checklist format. The anti-patterns section adds guardrails. The 'never delete' constraint and conflict resolution guidance provide error recovery direction. | 3 / 3 |
Progressive Disclosure | The skill references REFERENCE.md for a worked example, which is good progressive disclosure. However, no bundle files are provided, so we can't verify REFERENCE.md exists. The main content is well-organized with clear sections, but the skill is somewhat long and could potentially split the merge protocol details into a reference file while keeping the overview leaner. | 2 / 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
- 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.