· 2026-06-30 ·main@HEAD (package v3.1.0, skill-v3.8.0)

impeccable

pbakaus/impeccable

🛠

68 / 100Available

🛠

⚛

→

⚗

→

🧬

🛑

0–29

⚠️

30–49

🛠

50–79

🏭

80–100

▼

🛠· 68 / 100

✓5 claims passed, no critical failures
✓MIT / Apache / etc., installable per deployment.install_methods
✓release_pipeline_score=3 + pushed in 90-day window
⚪EN-only or ZH-only README
⚪compound layer needs a logged scenario run

#1👤

#2🎯

#3🧭

#4⇄


`npx impeccable install`	Node.js (Claude Code, Cursor, Codex, Gemini CLI, +10 harnesses)	easy
`git submodule + linked provider build`	teams wanting vendored installs	moderate

📡

Your existing AI agent (Claude/GPT/Gemini)

Runs the LLM-driven commands (critique, polish, craft, etc.)

Uses your agent's own model/quota. Deterministic detector + CLI need no model at all.

· 7

5 2

	+40
	+7
	+15
	+9
	-3
	0

5 / 7

passed claim-001

passed claim-002

passed claim-003

untested claim-101

untested claim-102

`input_contract`
`output_contract`
`determinism`
`idempotence`
`no_skill_callouts`
`failure_mode_clarity`

`workflow_correctness`
`declared_call_graph`
`stop_conditions`
`handoff_points`
`atom_evidence`
`error_propagation`
`partial_failure_handling`

`goal_achievement`
`direction_judgment`
`quality_judgment`
`meaningful_autonomy`
`handoff_timing`
`observed_call_graph`
`failure_recovery`

core user-facing layer untested → capped at 'usable'
hybrid-repo rule: archetype 'hybrid-skill' requires end-to-end evaluation of the user-facing layer
evidence_completeness='partial' (not portable) → capped at 'usable'

only 1/2 critical claims covered

archetype: hybrid-skill→core_layer_tested? False→evidence: partial→recommended: usable→final: usable

ceiling 1 · core user-facing layer untested → capped at 'usable'

ceiling 2 · hybrid-repo rule: archetype 'hybrid-skill' requires end-to-end evaluation of the user-facing layer

ceiling 3 · evidence_completeness='partial' (not portable) → capped at 'usable'


claim-001	确定性 detector 无 API key 运行成功	critical	support-detector	● passed
claim-002	规则数量与 README 声明一致或更多	high	support-detector	● passed
claim-003	23 命令存在且有 reference 文档	high	support-skill-integrity	● passed
claim-004	SKILL.md 相对引用完整	medium	support-skill-integrity	● passed
claim-005	跨 harness 安装	medium	support-install	● passed
claim-101	真实 LLM 会话产出达到质量契约	critical	core-llm	○ untested	需要真实多 harness LLM 会话生成 UI 并逐项打分；本次为静态 + 单次确定性 detector 评估，未做 live design-generation run。compound 层天花板因此未解锁。
claim-102	Anti-slop 规则在真实产出中被遵守	high	core-llm	○ untested	同 claim-101，依赖 live run。

0.00s

# Final Verdict

## Repo

- **Name**:
- **Version tested**:
- **Date**:
- **Archetype**:
- **Layer**: (atom | molecule | compound)
- **Score**:  /100  (from `verdict_calculator.py`, not judgement)
- **Category**:  (🏭 Production-ready / 🛠 Available / ⚠️ Risky / 🛑 Don't use)
- **Tier**: (recommend ≥90 / team ≥80 / self ≥65 / try ≥50 / risky ≥30 / broken <30)

## Plain English

Two sentences max. What does the user get if they adopt this repo today, and what would make them regret it?

- Outcome if adopted:
- Regret scenario:

## Why This Score

State the user-visible outcome first, mechanism second. Lead with what the repo *does* for the user, then the evidence.

### Top 3 score drivers

What earned or cost the most points. Reference `breakdown` from the calculator output.

- +/- :
- +/- :
- +/- :

### Core outcome
What observably works end-to-end? What observably does not?

### Scenario breadth
How many real inputs has it been tested against? Which dimensions vary (platform, data shape, scale)?

### Repeatability
Same input twice → same result? Filesystem-level or only log-level?

### Failure transparency
When it fails, do you learn something actionable, or does it swallow the error?

## What Would Move The Score Up

Concrete, testable next actions in score-impact order. Not "be better" — "add X test against Y fixture showing Z (lifts ~+N)".

1. (~+N)
2. (~+N)
3. (~+N)

## Remaining Risks

Ranked. Each risk with severity + impact + mitigation if known.

| Risk | Severity | Impact | Mitigation |
|---|---|---|---|

## Related Artifacts

- Claim map:
- Plan:
- Runs:
- Verdict calculator input:
- Rendered HTML dossier: