legreffier-consolidate

Consolidate diary entries by proposing and reviewing entry relations using server-side clustering. Optionally creates tiles when entries are too granular for direct compilation.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/legreffier-consolidate/SKILL.md

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.

The body is highly actionable with executable tool calls and a well-sequenced four-phase workflow including verification, supported by a clean one-level-deep reference. It is slightly verbose in places and one external navigation link is broken.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and focused on domain specifics Claude would not know (thresholds, tool params, relation patterns) with no generic-concept padding, though a few sections (repeated cluster-noise warnings, the recovery block) could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready tool calls with concrete parameters (diaries_consolidate, entries_relations_update, relations_create, diaries_compile), an exact CLI-command table, and a complete tile-format template covering the common cases.	5 / 5
Workflow Clarity	Four numbered phases are clearly sequenced with a Phase-3 decision gate and a Phase-4 verify-with-compile checkpoint; validation is present for the batch accept/reject work so the cap-3 does not apply, but the recovery action when verification still shows noise is not spelled out as a loop.	4 / 5
Progressive Disclosure	A dedicated 'Internal references' section plus inline pointers lead to a real one-level-deep references/consolidation-approach.md with content appropriately split, but SKILL.md is denser than a pure overview and the external ../../../docs/knowledge-factory.md link does not resolve.	4 / 5
	Total	17 / 20 Passed

Description

58%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 states concrete capabilities clearly but lacks an explicit use-when trigger and leans on domain jargon, capping completeness and trigger-term quality. It is otherwise distinct and specific to its niche.

Suggestions

Add a 'Use when…' clause naming the concrete trigger (e.g. 'Use when consolidating scan entries or commit/decision/incident entries after a scan session or feature merge').

Soften jargon with a natural synonym or two (e.g. pair 'entry relations' with 'links between diary entries') so users phrase the need in their own words.

Mention the accept/reject review and compile-verification actions to round out capability coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'proposing and reviewing entry relations', 'server-side clustering', 'creates tiles' — naming the domain clearly, but omits the accept/reject review and compile-verification step so coverage has minor gaps.	4 / 5
Completeness	The 'what' is clear, but there is no 'Use when…' clause; 'when entries are too granular' only conditions the optional tile sub-step, not when to invoke the skill, so the cap at 3 applies.	3 / 5
Trigger Term Quality	'Consolidate diary entries' is a natural phrase, but 'server-side clustering' and 'entry relations' are domain jargon with no synonyms or file-type terms, leaving common variations missing.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (the consolidate stage of a diary flywheel) with distinct triggers, but sibling skills like scan/compile create minor overlap risk.	4 / 5
	Total	14 / 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: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: getlarge/themoltnet
Path: .agents/skills/legreffier-consolidate/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.