legreffier

LeGreffier mode for Claude & Codex when GIT_CONFIG_GLOBAL=.moltnet/gitconfig; 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

92%

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

85%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 actionable and workflow-clear with strong validation gates, but it is a large monolithic document that would benefit from splitting the reference tables and detailed procedures into separate bundle files for better progressive disclosure and token efficiency.

Suggestions

Split the MCP tool reference table, CLI equivalents table, and commit authorship modes into separate reference files (e.g. references/tools.md, references/cli.md, references/authorship.md) and link to them one level deep.

Deduplicate the signature/verification guidance that appears in both 'Two signature layers' and the 'Verification' section, consolidating into a single canonical section.

Move the GitHub CLI authentication and 401-recovery details into a dedicated reference file, keeping only the core guard/wrapper guidance inline.

Dimension	Reasoning	Score
Conciseness	Mostly lean operational prose with no basic-concept padding and concrete commands throughout, but at 724 lines with some redundancy between the signature/verification sections and the Reminders block it could be trimmed slightly; a 5 would require every token to earn its place.	4 / 5
Actionability	Provides fully executable, copy-paste-ready CLI commands, git invocations, and MCP tool calls with parameters covering the common cases across signing, commits, investigation, and verification.	5 / 5
Workflow Clarity	Multi-step processes (session activation, accountable commit workflow, investigation workflow) are clearly sequenced with explicit validation checkpoints, hard gates, feedback loops (401 recovery, signature re-verify), and a pre-push checklist.	5 / 5
Progressive Disclosure	Good section structure and navigation, but the skill is monolithic with no reference/scripts/assets bundle files and large inlined reference tables (MCP tools, CLI equivalents, memory types, authorship modes) that clearly belong in separate one-level-deep files.	3 / 5
	Total	17 / 20 Passed

Description

100%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 specific, trigger-rich, complete, and highly distinct. It concretely states both capabilities and triggering contexts with natural phrasing a user would say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (verify bot identity, sign commits with MoltNet diary, investigate past rationale via signed diary search, check git history/audit trail) with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (identity verification, commit signing, diary search, history/audit checks) and when (proactive search before non-trivial work, episodic entries on breakage/surprise) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases with synonyms and variations such as "why did this break", "why did we do this", "show me the reasoning", "WTF", and "this is broken" that users would actually say.	5 / 5
Distinctiveness Conflict Risk	A narrow MoltNet/LeGreffier accountability niche gated by GIT_CONFIG_GLOBAL=.moltnet/gitconfig with distinct triggers, giving minimal conflict risk with unrelated skills.	5 / 5
	Total	20 / 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 (725 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: getlarge/themoltnet
Path: .agents/skills/legreffier/SKILL.md
Commit: 5daa9ca

Reviewed: ~14 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.