CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

repo-conventions

Repository conventions for this Bun starter — Bun-only tooling, workspace layout, quality gates, Lefthook hooks, Conventional Commits, Tailwind CSS, Storybook, type checking with `bun check`, and reference repositories in repos/. Use when starting work in this repository, choosing tools, running checks, committing, or when AGENTS.md / CLAUDE.md point here.

Quality

91%

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

93%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 conventions skill: terse, entirely repo-specific, and immediately actionable, with an explicit fix-then-stage feedback loop for the pre-commit gate. Its only weakness is that multi-step flows are scattered across sections without a consolidated end-to-end sequence and with limited guidance on recovering from a failing commit-msg hook.

DimensionReasoningScore

Conciseness

Every line carries repo-specific facts Claude could not know (e.g. '`exactOptionalPropertyTypes` is on', hooks 'skip when `CI=true`', 'format is checked, not fixed') with zero padding or explanation of known concepts, matching the lean-and-efficient anchor 5.

5 / 5

Actionability

Copy-paste-ready commands (`bun run verify`, `bun run fmt:check`, `bun run ci`) with exact script paths (`scripts/check-commit-subject.ts`, `scripts/certs.ts`, `scripts/serve-https.ts`) and explicit do/don't rules covering the common cases, matching the fully-executable anchor 5.

5 / 5

Workflow Clarity

The commit workflow is well sequenced with an explicit feedback loop ('format is checked, not fixed — run `bun run fmt` / `md:fmt`, then stage') and hook installation behavior is documented, but workflows are distributed across sections rather than one explicit end-to-end sequence and error recovery beyond 'never bypass hooks' is thin, matching anchor 4.

4 / 5

Progressive Disclosure

A compact, well-sectioned overview with detail appropriately pushed out ('Details in docs/local-https.md', repos listed in `repos.json`) and nothing inlined that belongs in a separate file, matching the clear-overview anchor 5 for a single-file bundle.

5 / 5

Total

19

/

20

Passed

Description

87%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 strong description: it enumerates the skill's concrete scope with specific tool names and provides an explicit, multi-trigger 'Use when' clause that includes the AGENTS.md/CLAUDE.md pointer. The only weakness is minor incompleteness in the capability enumeration and a few missing natural trigger synonyms.

DimensionReasoningScore

Specificity

Enumerates concrete capabilities with real tool names ('Lefthook hooks', 'type checking with `bun check`', 'reference repositories in repos/'), but coverage has minor gaps (e.g. the HTTPS/certs workflow in the body is not mentioned), matching anchor 4 rather than the comprehensive anchor 5.

4 / 5

Completeness

Clearly answers both 'what' (repository conventions enumerated with concrete tools) and 'when' (explicit 'Use when...' clause with multiple concrete trigger phrases including the AGENTS.md/CLAUDE.md pointer), exactly matching anchor 5.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ('starting work in this repository, choosing tools, running checks, committing, or when AGENTS.md / CLAUDE.md point here'), giving good keyword coverage, though a few natural terms users might say (e.g. 'lint', 'verify', 'Tailwind') are missing, so it falls short of the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Anchored to 'this Bun starter' with distinctive markers (`bun check`, repos/, AGENTS.md/CLAUDE.md), a clear niche with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

18

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

15

/

16

Passed

Repository

williamrjribeiro/bun-agentic-starter

Path

.agents/skills/repo-conventions/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.