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.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%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-structured, highly actionable multi-step workflow with strong validation and error-recovery guidance. Its main weakness is conciseness — duplicated triggers and pervasive internal phase annotations add tokens that don't aid execution.

Suggestions

Remove the 'Quick Reference' trigger list since those triggers already appear in the frontmatter description, or trim it to a single example phrase.

Strip the inline 'Phase 65.1.x / 134.4 / 137.2' version annotations from prose; move provenance to a single changelog line or drop it entirely, as it does not guide Claude's actions.

Consider moving the full 'Recommendation 算出ロジック' pseudocode and the acceptance-context.v1 schema into references/ (linked from SKILL.md) so the body stays a lean overview, keeping only the threshold summary inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded in places: the 'Quick Reference' duplicates triggers already in the description, internal 'Phase 134.4 / 137.2' annotations read like commit-log noise that doesn't help Claude act, and the plan-brief-open.sh historical-name note plus the verbose relative-path-rewriting explanation could be trimmed.	3 / 5
Actionability	Fully executable guidance throughout — concrete bash (git rev-parse, sha256sum), exact MCP search parameters, a complete JSON schema, and copy-paste-ready script invocations with flags covering the common cases.	5 / 5
Workflow Clarity	Steps 1–8 are clearly sequenced with explicit validation checkpoints (Step 4 evidence collection with pending/artifact-missing handling, TDD verification rules), a failure-mode table, and feedback loops that downgrade ship→wait→reject on missing evidence.	5 / 5
Progressive Disclosure	Good structure with a clearly signaled one-level-deep reference to references/blind-evaluator.md (which exists) and an inline schema that is appropriate for a core skill, though the full recommendation-computation block and schema are dense enough that they could live in a separate reference.	4 / 5
	Total	17 / 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.

The description is concrete, trigger-rich, and fully answers both what the skill does and when to use it, with explicit negative triggers to avoid misfires. It is a strong, well-scoped skill description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Reads back the acceptance_criteria', 'renders a single-file HTML showing each criterion as verified or unverified', 'ship/wait/reject recommendation' — giving comprehensive coverage of the skill's behavior.	5 / 5
Completeness	Explicitly answers both 'what' (generate Acceptance Demo HTML, read criteria, render verified/unverified, produce recommendation) and 'when' ('Use when the user asks for an acceptance review, wants to decide whether to ship a delivered task, or says: ...'), plus negative triggers ('Do NOT load for: implementation, code review, release work').	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and file/task language in both English and Japanese ('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'), matching what a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (acceptance review at the ship/wait/reject decision point) with distinct triggers and explicit exclusion of implementation, code review, and release work, minimizing overlap with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 4 missing, 4 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 15 missing	Warning

	Total	14 / 16 Passed

Repository: Chachamaru127/claude-code-harness
Path: opencode/skills/harness-accept/SKILL.md
Commit: 7d8deba

Reviewed: about 15 hours ago

Table of Contents

Discovery Implementation Validation

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.