CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-as-harness

证据确认重复摩擦后修 harness。Use: 历史重复已确认。Not: 未确认重复、首次 bug、review 反馈。Output: 未确认不强制 block;需 operator 决策发 interactive,否则行动后发 card(均含根因、证据、处置)。

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./cat-cafe-skills/code-as-harness/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 delivers an exceptionally actionable, well-sequenced diagnostic workflow with explicit gates, templates, and failure-mode checklists. Its weaknesses are token efficiency — recurring dated anecdotes, quoted staging clauses, and un-sectioned time-sensitive references — and a monolithic single-file layout that inlines two sizable sub-topics that belong in reference files.

Suggestions

Move the 猫侧主动上报/雨刮器条款细则 and Taste 信号路径 (F221) sections into reference files, leaving a one-line pointer plus the core rule in SKILL.md; this would cut roughly a third of the body.

Strip narrative provenance and anecdotes (来源 lines, 汉弗莱喵案, list_recent 实测 story) down to the operative rule they motivated, and relocate dated references (2026-06-01, 2026-07-15, 2026-10-26/27) to a changelog or deprecated section.

Consolidate the three separate 'why this exists' framings (价值门禁, 核心原则, 触发判定铁律) into one statement of the evidence-first principle to remove repeated emphasis.

DimensionReasoningScore

Conciseness

The body is noticeably verbose: dated anecdotes and provenance notes are inlined ("来源:2026-06-01~02 PoE brainstorm", "2026-10-26 汉弗莱喵案", "实测:list_recent 模板噪音税全家付了多日…"), a ~120-token staging clause is quoted verbatim, and time-sensitive dates appear throughout with no old-patterns/deprecated section. This is more than 'some' tightening, so it sits below anchor 3, though the decision tables themselves are dense and earn their tokens.

2 / 5

Actionability

Fully executable guidance for an instruction-only skill: exact YAML templates for the interactive and card blocks, a complete F128 initialMessage template, the marker format "[爪感差: 工具名+现象一句话]", and named tool invocations with arguments (search_evidence with keyword, cat_cafe_propose_thread with preferredCats). Specific examples cover the common diagnostic cases.

5 / 5

Workflow Clarity

Phases 1–5 are clearly sequenced with an explicit evidence-verification gate before diagnosis ("关键词只触发'去核实',不直接弹卡"), a state-to-action output contract table, gray-zone recovery handling, and a Common Mistakes failure-mode checklist. Validation checkpoints and feedback loops are explicit throughout.

5 / 5

Progressive Disclosure

The skill is a single ~320-line file with no bundle; section headers make it navigable, but substantial sub-documents (the 雨刮器/paw-feel reporting细则 and the taste-lane routing guide) are inlined where separate reference files would fit. This matches anchor 3 — good structure, but content that should be separate is inline.

3 / 5

Total

15

/

20

Passed

Description

71%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 compact, well-structured description with an explicit what/when/when-not/output contract and strong boundary fencing against neighboring skills. Its main weakness is that natural trigger phrases live in the frontmatter triggers field instead of the description, leaving the when-clause condition-based rather than phrase-based.

Suggestions

Fold one or two natural user phrases into the description itself (e.g., 'Use: 历史重复已确认,如 "又忘了"/"每次都"') so the when-clause carries concrete trigger language, not just a condition.

Briefly name the diagnostic action that precedes the fix (e.g., '搜证据确认重复 → 分类根因 → 修 harness') so the 'what' covers the workflow, not only the outputs.

DimensionReasoningScore

Specificity

The description names concrete actions and outputs — "修 harness", "发 interactive", "行动后发 card(均含根因、证据、处置)" — covering what is produced and how. It falls short of anchor 5 because the core 'what' is a single terse action phrase with minor coverage gaps around what '修 harness' concretely entails.

4 / 5

Completeness

Both 'what' (fix harness after evidence-confirmed repeated friction, with interactive/card outputs containing root cause, evidence, disposition) and 'when' ("Use: 历史重复已确认" plus explicit "Not:" exclusions) are present. Not anchor 5 because the 'when' clause states a condition rather than concrete trigger phrases a user would say.

4 / 5

Trigger Term Quality

Trigger guidance is condition-based ("Use: 历史重复已确认") rather than natural user phrases; the genuinely natural trigger phrases ("又忘了", "每次都", "怎么还") exist only in the separate triggers field, not the description itself. It is above anchor 2 because the Use/Not clauses still carry real discriminating trigger semantics.

3 / 5

Distinctiveness Conflict Risk

"Not: 未确认重复、首次 bug、review 反馈" explicitly fences off the debugging and receive-review overlap, and the niche (evidence-confirmed repeated friction → code-level harness fixes) is distinct with minimal conflict risk.

5 / 5

Total

16

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

zts212653/clowder-ai

Path

cat-cafe-skills/code-as-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.