CtrlK
BlogDocsLog inGet started
Tessl Logo

harness-accept

Generate an Acceptance Demo HTML for non-engineer vibecoders right before ship/wait/reject decision. Reads back the acceptance_criteria that were stored as personal-preference.v1 by harness-plan-brief (joined by user_request_hash), then renders a single-file HTML showing each criterion as verified or unverified along with a ship/wait/reject recommendation. Use when the user asks for an acceptance review, wants to decide whether to ship a delivered task, or says: acceptance demo, accept demo, 受け入れ判断, 受入レビュー, ship/wait/reject 判定, 検収レビュー. Do NOT load for: implementation, code review, release work.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced body with concrete commands, schemas, and explicit failure handling. The main weakness is progressive disclosure: the body points to scripts/, schemas/, and templates/ files that are not actually present in the bundle.

Suggestions

Ship the referenced bundle files (scripts/render-html.sh, scripts/accept-past-issues.sh, scripts/load-cross-project-groups.sh, scripts/plan-brief-open.sh, schemas/acceptance-context.v1.schema.json, templates/html/accept.html.template) so the one-level-deep references resolve.

Trim the Quick Reference section, which duplicates trigger terms already present in the frontmatter description, to tighten token efficiency.

Consider moving the full inline acceptance-context.v1 schema block fully into the referenced schema file and keeping only a short field summary inline, to reduce duplication between body and bundle.

DimensionReasoningScore

Conciseness

Dense and actionable with little generic-concept padding; prose covers a bespoke internal harness system Claude would not already know. Minor redundancy (Quick Reference repeats triggers) keeps it just short of perfect, but every section earns its place.

3 / 3

Actionability

Provides fully executable bash (git rev-parse, sha256sum), exact MCP search parameters, concrete render-html.sh invocation, a full schema block, and explicit recommendation thresholds with formulas — copy-paste ready guidance throughout.

3 / 3

Workflow Clarity

Clear Step 1–8 sequence with a dedicated failure-handling table specifying per-failure behavior and feedback (e.g. render-html.sh failure -> exit 1; mem-search unreachable -> continue with empty array), giving explicit checkpoints and error-recovery paths.

3 / 3

Progressive Disclosure

Section structure and one-level-deep references are well-signaled (scripts/*, schemas/*, templates/*), but the referenced bundle files do not exist in the skill bundle, so the disclosure chain points to missing materials rather than resolving cleanly.

2 / 3

Total

11

/

12

Passed

Description

100%

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, well-scoped description: it states concrete actions in third person, gives explicit trigger guidance with natural (and bilingual) keywords, and disambiguates against adjacent skills via a clear 'do NOT load for' clause. No significant gaps.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Generate an Acceptance Demo HTML', 'Reads back the acceptance_criteria ... stored as personal-preference.v1', 'renders a single-file HTML showing each criterion as verified or unverified') in third-person voice, matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both 'what' (generate/read/render the HTML) and 'when' via an explicit 'Use when the user asks for an acceptance review ... or says: ...' clause.

3 / 3

Trigger Term Quality

Good coverage of natural terms a user would say, including Japanese variants ('acceptance demo', 'accept demo', '受け入れ判断', '受入レビュー', 'ship/wait/reject 判定', '検収レビュー'); not merely technical jargon.

3 / 3

Distinctiveness Conflict Risk

Clear niche (acceptance review for ship/wait/reject) with distinct triggers plus an explicit negative-scope clause ('Do NOT load for: implementation, code review, release work.'), making wrong-skill conflicts unlikely.

3 / 3

Total

12

/

12

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing, 1 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 12 missing

Warning

Total

14

/

16

Passed

Repository
Chachamaru127/claude-code-harness
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.