CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

setup-codebase-harness

Master skill — set up the full agent harness for any repo so an agent can work it reliably: legible (map-not-manual docs + custom lints), executable (one-command dev stack), verifiable (e2e gate + a verify-before-ship loop), plus commit hygiene and entropy control. Use when onboarding a new/unfamiliar codebase to agent-driven development — "set up the harness", "make this repo agent-ready", "harness this codebase".

Quality

88%

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

75%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.

A well-structured orchestrator skill: clear pillar workflow, concrete named artifacts, and sensible delegation to sub-skills. Minor gains available from trimming editorial framing and adding explicit validation checkpoints in the setup sequence.

Suggestions

Trim the editorial intro and aphorisms ("Humans steer; agents execute", "Don't boil the ocean") to tighten token efficiency toward a lean 5.

Add an explicit validate-then-proceed checkpoint after each pillar (e.g., confirm dev-local stack is healthy before scaffolding e2e) to push workflow clarity to 5.

Move the crabbox rationale and lint-remediation detail into a short reference file so the body stays a clean overview pointing one level deep.

DimensionReasoningScore

Conciseness

Dense and assumes Claude's competence without explaining basics, but the editorial intro ("Harness engineering: the model is fixed… Humans steer; agents execute") and aphorisms ("Don't boil the ocean") are minor over-explanation that could be trimmed. Not a 5 because a few framing tokens don't earn their place; not a 3 because nothing pads basic concepts.

4 / 5

Actionability

Names concrete artifacts and commands (scripts/dev-local.sh up, docs/index.md, one lint per invariant with fix-injected error messages, named sub-skills) and gives specific directional guidance. Missing copy-paste code blocks, but as a coordination/instruction skill its guidance is actionable, so absence of code is not penalized.

4 / 5

Workflow Clarity

Clear sequenced pillars (0 Assess → 1 Legible → 2 Executable → 3 Verifiable → 4 Others) plus an explicit "Order & what you leave behind" ordering section, and the /verify loop supplies a feedback loop. Not a 5 because the setup flow itself lacks explicit validate-then-proceed checkpoints.

4 / 5

Progressive Disclosure

Well-organized into numbered sections and delegates depth to named sub-skills (dev-local-setup, e2e-setup, crabbox-setup, verifier-setup) one level deep, clearly signaled. No bundle files exist to verify, and some detail (crabbox rationale, lint examples) is inlined rather than split out, keeping it at 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

100%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: concrete, third-person, with explicit what/when structure and natural trigger phrases. It avoids fluff and clearly delineates its niche.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — legible (map-not-manual docs + custom lints), executable (one-command dev stack), verifiable (e2e gate + verify-before-ship loop), plus commit hygiene and entropy control — giving comprehensive coverage of distinct actions.

5 / 5

Completeness

Explicitly answers both what (full harness: legible/executable/verifiable + commit hygiene + entropy control) and when ("Use when onboarding a new/unfamiliar codebase to agent-driven development") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases a user would actually say — "set up the harness", "make this repo agent-ready", "harness this codebase", plus "onboarding a new/unfamiliar codebase" — covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (agent-harness setup for codebases) with distinct triggers; unlikely to fire for unrelated skills.

5 / 5

Total

20

/

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: 2 missing

Warning

Total

14

/

16

Passed

Repository

AI-Builder-Club/skills

Path

skills/setup-codebase-harness/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.