CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

harness-setup

HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI/Codex setup, harness-mem, mirror. Do NOT load for: implementation, review, release, planning.

Quality

81%

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

The canonical home for this skill is harness-setup in Chachamaru127/claude-code-harness

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 a well-organized orchestration hub that dispatches to real, verified reference files with a clear Quick Reference table and an explicit execution-and-validation sequence. Its main weakness is conciseness: reference paths are duplicated across two sections and version-specific policy prose is inlined rather than delegated.

Suggestions

Remove the duplicate Reference Index section (or the per-row paths in the Quick Reference table) so each reference path appears once — keep either the table or a single annotated index.

Move the CC 2.1.120+ / Codex 0.130.0 version-specific policy blockquotes into the corresponding reference files (codex.md, marketplace.md) and leave a one-line pointer in the body.

Add an explicit feedback loop for destructive/batch setup operations (e.g. 'if doctor or sync --check fails, fix and re-run before proceeding') to strengthen workflow_clarity toward 5.

DimensionReasoningScore

Conciseness

Mostly efficient via the Quick Reference table, but the same reference paths are repeated in a separate Reference Index and several version-specific policy blockquotes (CC 2.1.120+, Codex 0.130.0) read as inlined content that could live in references — noticeably more than minor trimming.

3 / 5

Actionability

Provides concrete executable verification commands ('harness doctor', 'bash scripts/sync-skill-mirrors.sh --check', 'bash scripts/ci/check-consistency.sh') and a clear dispatch table; actual procedures delegate to reference files, which is appropriate for an orchestration skill, with only minor gaps.

4 / 5

Workflow Clarity

A numbered 4-step Execution sequence includes an explicit post-setup validation block; sequence is clear with most checkpoints present, though feedback loops for the destructive setup/sync operations are largely deferred to reference files.

4 / 5

Progressive Disclosure

Well-structured overview with one-level-deep references via a Quick Reference table and Reference Index; all 8 referenced files (init.md, ci.md, codex.md, cursor.md, harness-mem.md, mirrors-agents-localize.md, marketplace.md, maintenance.md) exist in references/. Slight path duplication and inlined policy blockquotes keep it just below a 5.

4 / 5

Total

15

/

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.

The description is strong: it explicitly states capabilities, provides concrete trigger terms, answers both what and when, and includes a rare explicit negative-boundary clause that sharply reduces conflict risk. It is concise and avoids fluff.

DimensionReasoningScore

Specificity

Names several concrete action areas ('Project init, tool setup, agent config, memory setup, skill mirror sync') — multiple specific actions with only minor coverage gaps, matching the anchor for several specific actions.

4 / 5

Completeness

Clearly and explicitly answers both 'what' (init/setup/config/sync) and 'when' via a concrete 'Trigger:' clause plus an explicit 'Do NOT load for' negative boundary — both present with concrete trigger phrases.

5 / 5

Trigger Term Quality

Explicit trigger list ('setup, init, new project, CI/Codex setup, harness-mem, mirror') provides good natural-term coverage; a few common synonyms are missing, so it sits just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The 'HAR:' niche prefix and explicit negative boundary ('Do NOT load for: implementation, review, release, planning') give a clear niche with minimal conflict risk.

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: 2 missing, 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

Chachamaru127/claude-code-harness

Path

opencode/skills/harness-setup/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.