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

90%

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

96%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 an exemplary lean operational reference: concrete paths, commands, and code, with sequenced workflows, explicit validation (test suite, regression guard), and failure-mode fixes. Its only structural limitation is that everything lives inline in SKILL.md with no progressive-disclosure split, which is acceptable at this size but leaves it just short of the top organization anchor.

DimensionReasoningScore

Conciseness

Every line is repo-specific operational fact — build non-recursiveness, template paths, line-numbered gates (`run-hook.ts:316`), a sync command — with zero padding or explanation of concepts Claude already knows. Nothing could be trimmed without losing information, matching the lean-and-efficient anchor.

5 / 5

Actionability

Guidance is fully executable: exact file paths, a runnable command (`venv/bin/python scripts/pre_commit.py`), a copy-paste-ready regex fix with lookaheads, and concrete normalization code (`filePath.replace(/\/+$/, '')`). This covers the common cases the way the copy-paste-ready anchor requires.

5 / 5

Workflow Clarity

The SemanticKind addition is a numbered 4-step sequence with an explicit ordering rationale (matcher passes the event in; toolKinds gates the run), the sync command validates via the full test suite, and the regression guard plus pitfalls-with-fixes provide feedback loops for error recovery. Explicit validation and recovery match the top anchor.

5 / 5

Progressive Disclosure

The body is cleanly sectioned with no nested references and a "Reference files" index, but no bundle files exist and all content is inlined in a ~83-line body — over the 50-line threshold where sections alone would justify a 5. Good structure with minor organization gaps fits anchor 4 rather than the well-signaled one-level-deep-references anchor.

4 / 5

Total

19

/

20

Passed

Description

83%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 action-oriented, mapping one-to-one onto the skill's actual workflows. Its main weakness is trigger phrasing: it relies on a "To…" purpose clause instead of an explicit "Use when…" construction, and it omits several natural keywords (hooks.json, bundle, rosettify, matcher) that users might say.

DimensionReasoningScore

Specificity

"author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire" lists multiple concrete actions that comprehensively cover the skill's workflows (authoring, registration, testing, extending, debugging). It matches the comprehensive-coverage anchor rather than the minor-gaps anchor because every major body section has a corresponding action.

5 / 5

Completeness

The "what" is explicit (author/register/test hooks, add a SemanticKind, debug a non-firing hook) and the "To…" purpose clause supplies equivalent trigger guidance (e.g. firing failure). It is not a 5 because there is no explicit "Use when…" clause with concrete trigger phrases, and not a 3 because the trigger situations are stated directly rather than merely implied.

4 / 5

Trigger Term Quality

Terms like "Rosetta hooks", "SemanticKind", "register", and "debug a hook that won't fire" are natural phrases a repo user would say, but common variations such as "hooks.json", "bundle", "rosettify", "matcher", or "IDE event" are missing. Good coverage with a few natural terms absent fits anchor 4.

4 / 5

Distinctiveness Conflict Risk

"Rosetta hooks" and "SemanticKind" name a highly specific internal niche with distinct triggers, so overlap with other skills is minimal. This clearly matches the clear-niche anchor.

5 / 5

Total

18

/

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/r3/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.