CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

coding-agents-hooks-authoring

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

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

90%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.

An exceptionally dense, operational skill body that captures non-obvious repo constraints (non-recursive bundling, IDE registration matrices, silent-drop gating) with copy-paste-ready commands and fixes. The only structural weakness is that the multi-part authoring workflow is distributed across sections rather than presented as a single ordered sequence with inline checkpoints.

DimensionReasoningScore

Conciseness

The body is lean and entirely composed of non-obvious, repo-specific facts (exact paths with line numbers like "build-bundles.mjs:24" and "run-hook.ts:98", non-recursive build behavior, IDE quirks). It assumes Claude's competence and never explains known concepts, so every token earns its place.

5 / 5

Actionability

Guidance is fully executable: a copy-paste sync command ("venv/bin/python scripts/pre_commit.py"), a copy-paste corrected regex ("/\brm\s+-(?=[a-zA-Z]*[rR])(?=[a-zA-Z]*[fF])[a-zA-Z]+\b/"), and exact file/table/field targets for each step. Not 4: there are no material gaps — concrete commands and specific examples cover the common cases.

5 / 5

Workflow Clarity

The "Adding a SemanticKind" sequence is clearly ordered with an explicit "Order matters" gating explanation, and validation feedback loops exist (regression test "immediately fails" on missing registration; pre_commit runs the full test suite). It falls short of 5 because the end-to-end author → register → test → sync flow is never laid out as one sequence — the reader must assemble checkpoints scattered across sections.

4 / 5

Progressive Disclosure

Well-organized single-file skill with clearly labeled sections and a flat, one-level-deep "Reference files" listing. It is ~80 lines with no bundle files, so the under-50-line exception for a 5 doesn't apply, and everything lives inline in one file with references given as a plain code block rather than navigable links — matching "good structure, minor organization gaps".

4 / 5

Total

18

/

20

Passed

Description

70%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 concise, specific description anchored to a clearly distinct niche, with strong natural trigger phrasing ("debug a hook that won't fire"). Its main weakness is the absence of an explicit "Use when..." trigger clause, which leaves the activation conditions only weakly implied.

Suggestions

Add an explicit trigger clause, e.g., "Use when creating or modifying hooks in src/hooks/, extending TOOL_KINDS with a new tool category, or when a registered hook fails to fire in an IDE."

Include one or two natural synonyms users might say, such as "hooks.json registration" or "IDE hook plugin", to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — "author, register, and test Rosetta hooks", "add a SemanticKind", "debug a hook that won't fire" — with minor gaps in coverage (e.g., registration templates and the sync/build workflow are unmentioned). Not 5 because coverage is not comprehensive; not 3 because it goes well beyond 1-2 actions.

4 / 5

Completeness

The "what" is clear (author, register, test hooks; add a SemanticKind; debug), but there is no explicit "Use when..." clause — the "when" is only weakly implied by the "or debug a hook that won't fire" alternative. Per the judging guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

"debug a hook that won't fire" and "register" are natural phrases users would say, and "Rosetta hooks" names the domain. A few natural terms are missing (e.g., "hooks.json", "plugin", "IDE"), keeping it below the comprehensive-synonym anchor of 5.

4 / 5

Distinctiveness Conflict Risk

"Rosetta hooks" and "SemanticKind" are highly niche, repo-specific terms that would almost never collide with another skill's triggers, giving a clear niche with minimal conflict risk.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.