CtrlK
BlogDocsLog inGet started
Tessl Logo

contributor-onboarding

Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.

68

Quality

83%

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

100%

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 tight, executable workflow: exact CI-mirrored commands, strong validation checkpoints around risky/batch steps, and a read-only/explicit-only safety posture enforced at each stage. It assumes Claude's competence and avoids concept re-explanation, with content appropriately inline for a focused onboarding skill.

DimensionReasoningScore

Conciseness

Lean and action-oriented throughout; it assumes Claude knows git/cargo (no explanations of what rebase or clippy is) and every section — including the safety-focused Non-goals and the known-flake note — earns its place rather than padding.

3 / 3

Actionability

Fully executable, copy-paste-ready commands throughout (git rev-parse/status/rev-list, cargo build --release -p ..., cargo fmt --check, clippy with exact allow-list flags, cargo test --workspace, git log -n 20, ./target/release/codewhale exec --help).

3 / 3

Workflow Clarity

Six clearly sequenced steps with explicit validation checkpoints: build failure halts before the gate, the gate must actually pass before the optional dogfood step, a dirty tree yields an ordered recovery plan, and reporting forbids inferring "passed".

3 / 3

Progressive Disclosure

No bundle files exist, so the single-file skill is judged on organization; sections (Invocation, Non-goals, Workflow 1–6, Reporting, Credit) are well-structured, self-contained for their scope, and the only references (ci.yml, CHANGELOG.md) are real repo files clearly signaled and one level deep.

3 / 3

Total

12

/

12

Passed

Description

67%

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 and distinctive, naming four concrete onboarding actions and carving a clear read-only/explicit-only niche. It is held back by an implied-only trigger: there is no explicit "Use when…" clause, which caps trigger quality and completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when a new contributor has cloned the repo and wants to confirm they are current, that it builds and passes, and what recently changed."

Soften jargon in the description ("verification gate", "sync state against main") toward language a contributor would naturally say, while keeping the precise terms in the body.

Consider listing the natural trigger terms ("am I current", "does it build", "does it pass", "what changed") that already appear in the body.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest" — matching the anchor for listing several specific actions.

3 / 3

Completeness

It clearly answers *what* the skill does, but *when* to use it is only implied by "Help a new contributor get productive on this checkout"; the missing explicit "Use when…" trigger caps completeness at 2 per the rubric.

2 / 3

Trigger Term Quality

"new contributor", "get productive", and "build" are natural user terms, but "verification gate" and "sync state against main" lean jargon and common variations/"Use when" framing are absent.

2 / 3

Distinctiveness Conflict Risk

A clear niche — first-run contributor onboarding on a single checkout with a read-only/explicit-only philosophy ("Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.") — makes conflict with generic git/build skills unlikely.

3 / 3

Total

10

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Hmbown/CodeWhale
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.