getlarge/legreffier-explore
Systematic diary exploration: discover tags, entry distribution, coverage gaps, agent mistakes, and compile recipes
86
90%
Does it follow best practices?
Impact
81%
1.06xAverage score across 5 eval scenarios
Advisory
Suggest reviewing before use
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 well-crafted skill description that excels across all dimensions. It provides specific capabilities (tags, distribution, gaps, mistakes, recipes), includes natural trigger phrases users would actually say, and has an explicit 'Use when...' clause covering multiple scenarios. The diary/journal focus creates a clear, distinct niche.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'discover tags, entry distribution, coverage gaps, agent mistakes, and compile recipes'. These are distinct, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (systematic diary exploration with specific capabilities) AND when (explicit 'Use when...' clause with multiple trigger scenarios and exact phrases). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'explore the diary', 'diary overview', 'what's in the diary', plus contextual triggers like 'onboarding', 'consolidation', 'analyze', 'review diary log entries'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on diary/journal exploration with distinct triggers like 'diary overview' and 'coverage gaps'. Unlikely to conflict with general document or logging 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, highly actionable skill for diary exploration with clear multi-phase workflows and concrete MCP tool examples. Its main weakness is length—the comprehensive coverage comes at the cost of token efficiency, and some phases (especially Phase 6) could be extracted to separate reference files. The operator preflight and explicit recovery instructions demonstrate mature workflow design.
Suggestions
Extract Phase 6 (Pack-to-docs transformation) into a separate PACK_TO_DOCS.md reference file to reduce main skill length
Tighten the 'When to trigger' and introductory sections—Claude doesn't need the rationale explained, just the trigger conditions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some verbose explanations that could be tightened. Phrases like 'This is the **discovery** step — run it before consolidation' and extensive phase descriptions add bulk. However, most content is necessary for the complex multi-phase workflow. | 2 / 3 |
Actionability | Provides concrete, executable MCP tool calls with specific parameters, clear YAML templates for compile recipes, and exact CLI commands for pack export. The code examples are copy-paste ready with realistic parameter structures. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow with clear sequencing (phases 1-6), explicit validation checkpoints, and recovery instructions. Each phase builds on previous findings with clear inputs/outputs. The 'Recovery after context compression' section provides explicit resumption guidance. | 3 / 3 |
Progressive Disclosure | References an external template file ('exploration-pack-plan.yaml') appropriately, but the skill itself is quite long (~400 lines) with detailed inline content that could be split into separate reference files. The Phase 6 pack-to-docs transformation is substantial enough to warrant its own file. | 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.
Reviewed
Table of Contents