legreffier

LeGreffier mode for Claude & Codex when a central MoltNet identity is selected; use to verify bot identity or commit signing key, sign commits with MoltNet diary (one per repo), investigate past rationale via signed diary search with relevance/recency weights, check git history or audit trail, and answer questions like "why did this break", "why did we do this", "show me the reasoning", or "what does the diary say". Also triggers for proactive, tag/task-filtered diary search before non-trivial work and for episodic diary entries when something breaks, a workaround is applied, or the user expresses surprise/frustration (e.g. "WTF", "how did that happen", "this is broken", "why did this break").

Quality

86%

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

77%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 content is highly actionable and workflows are exceptionally well-sequenced with validation gates, but the skill is a monolithic ~730-line document that pays a token cost on every trigger and inlines reference material that belongs in separate files.

Suggestions

Move the large MCP tool reference table and the CLI-equivalents table into a references/ file (e.g. references/tool-reference.md) and link to it from SKILL.md to reduce per-trigger token cost and improve progressive_disclosure.

Extract the entry templates and GitHub CLI authentication details into separate reference files, keeping only a concise overview and the core accountable-commit workflow inline.

Tighten the prose across overlapping sections (e.g. commit-authorship guidance appears in both "Accountable commit workflow" and "Commit authorship modes") to remove redundancy.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of basic-concept padding, but at ~730 lines it imposes a heavy always-loaded token cost; several large sections (MCP tool table, CLI equivalents, entry templates, GitHub auth details) could be tightened or moved to reference files.	3 / 5
Actionability	Fully executable guidance throughout: concrete bash snippets such as "$MOLTNET_CLI entry create-signed --diary-id ... --type ... --tags ..." and "git commit -m ... -m \"MoltNet-Diary: <entry-id>\"" are copy-paste ready and cover the common cases.	5 / 5
Workflow Clarity	The accountable-commit workflow is a clearly numbered 0–8 sequence with explicit validation gates ("Nothing staged → stop", scope-gate split signals, "Hard gate: no ship without diary", pre-push checklist) and feedback loops for the destructive commit/push operations.	5 / 5
Progressive Disclosure	Good section header structure, but no bundle/reference files exist and the skill is a monolithic single document with large reference tables (MCP tools, CLI equivalents, entry templates) inlined that would be better placed in separate one-level-deep reference files.	3 / 5
	Total	16 / 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: it names concrete capabilities, provides rich natural-language triggers, and explicitly covers both what and when. Its only weakness is mild overlap risk from generic git/audit vocabulary that could fire for non-MoltNet commit contexts.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "verify bot identity or commit signing key", "sign commits with MoltNet diary", "investigate past rationale via signed diary search with relevance/recency weights", "check git history or audit trail" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (verify identity, sign commits, investigate rationale, check history) and when (gated on "a central MoltNet identity is selected"; triggers for proactive search before non-trivial work and episodic entries when something breaks or the user expresses surprise/frustration) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases including synonyms and user utterances: "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", plus "commit signing" and "git history".	5 / 5
Distinctiveness Conflict Risk	Clear MoltNet/LeGreffier niche with distinct diary-centric triggers, but generic terms like "git history", "commit signing", and "audit trail" carry minor overlap risk with general git/commit skills, and the identity-gating clause is somewhat buried; mostly distinct rather than minimal-conflict.	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
skill_md_line_count	SKILL.md is long (742 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: getlarge/themoltnet
Path: packages/legreffier-plugin/plugins/legreffier/skills/legreffier/SKILL.md
Commit: 5248f7e

Reviewed: 20 hours 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.