legreffier-explore

Systematic diary exploration: discover tags, entry distribution, coverage gaps, agent mistakes, and compile recipes. Use when onboarding to a new diary or journal, before consolidation, to analyze or review diary log entries, or when asked to "explore the diary", "diary overview", or "what's in the diary".

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%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.

A thorough, actionable skill body with concrete MCP/CLI examples, a well-sequenced multi-phase workflow, and properly signaled one-level references. Its main weakness is length and some redundancy that could be tightened or externalized.

Suggestions

Consolidate the pack-creation guidance so it lives in one place rather than being split across Phase 5/6 and the separate 'Pack creation and export' section.

Tighten or externalize Phase 6 (Pack-to-docs transformation) into its own reference file, keeping only the goal and the per-section attribution format inline.

Add a concrete validation step to Phase 4 (e.g., a checklist for comparing codebase subsystems against discovered scope: tags) so coverage-gap detection is as actionable as the other phases.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but at ~450 lines it has minor trim opportunities such as repeated 'See references/discovery-to-pack-method.md' pointers and pack creation covered in both Phase 5/6 and a separate 'Pack creation and export' section.	4 / 5
Actionability	Provides copy-paste-ready, fully executable guidance: parameterized MCP calls (diary_tags({ diary_id, prefix: 'scope:' })), a CLI equivalents table, a concrete packs_create payload, and a YAML recipe template covering common cases.	5 / 5
Workflow Clarity	Six phases are clearly sequenced with explicit fallback queries, transport fallback, and a recovery-after-compression section, but Phase 4 (coverage gaps) is comparatively vague and pack garbage-collection is a warning rather than a validate-fix-retry loop.	4 / 5
Progressive Disclosure	SKILL.md points to real one-level-deep references (discovery-to-pack-method.md for Phases A-D, exploration-pack-plan.yaml as the canonical template) that exist in the bundle, though some inline bulk such as the 8-step Phase 6 could be externalized.	4 / 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.

A strong description that concretely states what the skill does, when to use it, and the natural trigger phrases a user would say. It is concise, third-person, and clearly distinguishable from sibling skills.

Dimension	Reasoning	Score
Specificity	Names the domain and lists five concrete actions ('discover tags, entry distribution, coverage gaps, agent mistakes, and compile recipes'), giving comprehensive coverage rather than the 1-2 actions of the score-3 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (systematic diary exploration with named actions) and 'when' ('Use when onboarding... before consolidation... or when asked to...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would actually say ('explore the diary', 'diary overview', 'what's in the diary', 'onboarding to a new diary or journal') with synonyms, matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (moltnet diary exploration) with domain-specific triggers, and the 'before consolidation' framing distinguishes it from the sibling consolidate skill, yielding minimal conflict risk.	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
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

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

Reviewed: ~13 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.