coding-agents-hooks-authoring

To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.

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

100%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 a dense, well-organized reference that assumes Claude's competence, provides executable paths and commands, sequences the multi-step SemanticKind workflow with validation, and stays within a single appropriately structured file. No significant weaknesses relative to the rubric.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: no explanation of concepts Claude already knows; every line states a concrete rule, path, or failure mode, with line-numbered references that earn their place.	5 / 5
Actionability	Fully executable guidance — exact file paths, line references (e.g. 'run-hook.ts:98'), a copy-pasteable sync command, and concrete regex patterns covering the common cases.	5 / 5
Workflow Clarity	The 'Adding a SemanticKind' section is a clearly numbered 4-step sequence with ordering rationale, a silent-drop failure mode called out, and validation via the regression test guard and the pre_commit sync step that provides a feedback loop.	5 / 5
Progressive Disclosure	No bundle files are present; the body is a single self-contained ~80-line file with well-organized section headers and a 'Reference files' list, which meets the simple-skill exception for a top score.	5 / 5
	Total	20 / 20 Passed

Description

85%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, distinctive, and gives clear triggering situations, with concrete named actions rather than vague language. It would benefit from an explicit 'Use when...' clause and a few synonyms to push trigger quality to the top anchor.

Suggestions

Add an explicit 'Use when...' sentence (e.g. 'Use when authoring or registering Rosetta hooks, adding a SemanticKind, or debugging a hook that won't fire.') to reach the top completeness anchor.

Include a few natural synonyms or file extensions users might say (e.g. 'hooks.json', 'hooks.json.tmpl') to broaden trigger term coverage.

Keep the third-person voice consistent; it is correct here, so no change needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('author, register, and test Rosetta hooks', 'add a SemanticKind', 'debug a hook that won't fire') with comprehensive coverage of the skill's domain.	5 / 5
Completeness	The 'what' is explicit and concrete, and the 'when' is conveyed through the OR-list of triggering situations, but there is no standalone 'Use when...' clause, which the guideline treats as slightly less explicit.	4 / 5
Trigger Term Quality	Includes natural phrases users would say ('debug a hook that won't fire', 'add a SemanticKind') but lacks synonyms or extension-style variations for broader keyword coverage.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Rosetta hooks, SemanticKind) with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: griddynamics/rosetta
Path: instructions/r2/core/skills/coding-agents-hooks-authoring/SKILL.md
Commit: 044d86c

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.