getlarge/legreffier
LeGreffier mode: verify identity, sign commits with MoltNet diary, investigate past rationale via signed diary search
90
90%
Does it follow best practices?
Impact
90%
2.64xAverage 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 strong, well-crafted skill description that excels across all dimensions. It provides specific concrete actions, includes excellent natural language trigger terms that users would actually say, explicitly defines both capabilities and activation conditions, and has highly distinctive identifiers that prevent conflicts with other skills. The description is comprehensive without being unnecessarily verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'verify bot identity or commit signing key', 'sign commits with MoltNet diary', 'investigate past rationale via signed diary search', 'check git history or audit trail'. These are detailed, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (verify identity, sign commits, search diary, check history) AND when with explicit triggers ('Use when...' equivalent via 'triggers for' clause and specific user phrases like 'why did this break'). The 'Also triggers for' section explicitly defines activation conditions. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user phrases: 'why did this break', 'why did we do this', 'show me the reasoning', 'what does the diary say', 'WTF', 'how did that happen', 'this is broken'. Also includes technical triggers like 'GIT_CONFIG_GLOBAL', 'commit signing', 'git history'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with unique identifiers: 'LeGreffier mode', 'GIT_CONFIG_GLOBAL=.moltnet/gitconfig', 'MoltNet diary'. The specific combination of git signing, diary entries, and rationale investigation creates a clear niche unlikely to conflict with generic git or documentation 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 highly actionable and well-structured skill with excellent workflow clarity, explicit validation gates, and concrete executable examples. The main weaknesses are moderate verbosity (some redundancy in verification instructions) and the monolithic structure that could benefit from progressive disclosure via separate reference files for templates and detailed workflows.
Suggestions
Extract entry templates, commit shaping rules, and investigation workflow into separate reference files (e.g., TEMPLATES.md, COMMIT-SHAPING.md) with brief summaries in the main skill
Consolidate the verification instructions into a single authoritative section and reference it elsewhere instead of repeating the guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy (verification section repeated in multiple places, metadata conventions explained twice). Some sections could be tightened, though most content is necessary for the complex workflow. | 2 / 3 |
Actionability | Excellent executable guidance throughout: specific CLI commands with exact flags, concrete bash examples, copy-paste ready code blocks, and precise MCP tool calls. Templates include exact field names and values. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints (e.g., 'Hard gate: unknown fingerprint → stop', pre-push checklist, verification gate for Task-Completes). Error recovery paths are specified throughout. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear headers and tables, but this is a monolithic 400+ line file that could benefit from splitting (e.g., entry templates, investigation workflow, commit shaping could be separate files). No external file references for detailed sections. | 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