CtrlK
BlogDocsLog inGet started
Tessl Logo

organize-threads

猫猫辅助整理未分类 thread,分析标题和元数据,建议合适的标签。 Use when: 用户说"帮我整理"、"分类 thread"、点击整理按钮。 Not for: 删除/编辑标签本身。 Output: 按 thread 的标签建议列表。

68

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

90%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.

A tight, highly actionable instruction skill with concrete tool calls, copy-paste output templates, and a clear sequenced workflow with sensible guardrails. The only gaps are an explicit output-validation/retry loop and marginal room to split content into a reference file.

Suggestions

Add an explicit validation/retry checkpoint for the output JSON (e.g., verify every suggested labelId exists in the fetched label list before emitting the SUGGESTIONS_JSON block) to lift workflow_clarity toward 5.

Since the body is slightly over 50 lines, consider moving the extended '无标签时' template and label-system guidance into a references/ file and linking to it, which would justify a 5 on progressive_disclosure.

DimensionReasoningScore

Conciseness

Lean and efficient: a short flow, two copy-paste output templates, and a tight notes section, with no explanation of concepts Claude already knows. Every section earns its place, matching the 5 anchor; it is above a 4 because there are no padded or over-explained passages to trim.

5 / 5

Actionability

Gives concrete tool names (cat_cafe_list_labels, cat_cafe_list_threads) and exact copy-paste-ready markdown table + JSON templates covering both the labeled and unlabeled cases. Fully actionable instruction guidance matching the 5 anchor; absence of code is not penalized for an instruction skill.

5 / 5

Workflow Clarity

A clear three-step sequence (获取数据 → 分析 → 输出建议) with quality checkpoints (skip uncertain threads, don't force-classify, max 50) and a human-in-the-loop confirmation ("等用户在 modal 中确认"). It is a 4 rather than 5 because there is no explicit output-validation/retry loop, and the batch cap is avoided since validation is present rather than missing.

4 / 5

Progressive Disclosure

Well-organized into 流程, 输出格式, and 注意事项 sections with no nested references and no bundle files; self-contained and easy to navigate. It is a 4 rather than 5 because the body is ~70 lines (above the under-50 simple-skill threshold that would allow a 5 on structure alone) with no one-level-deep reference split.

4 / 5

Total

18

/

20

Passed

Description

78%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 that clearly states capability, trigger conditions, exclusions, and output. Its main limitation is breadth of action coverage and slight generic-verb overlap risk rather than any clarity failure.

DimensionReasoningScore

Specificity

Names the domain (organizing unclassified threads) and two concrete actions — "分析标题和元数据" and "建议合适的标签" — but coverage is not comprehensive, matching the 1-2 concrete actions anchor. It is above a 2 because the actions are specific rather than generic, but below a 4 which requires several actions.

3 / 5

Completeness

Explicitly answers what (analyze titles/metadata, suggest labels) and when ("Use when: 用户说帮我整理、分类 thread、点击整理按钮") with concrete trigger phrases, and adds Not-for/Output bounds. Matches the 5 anchor; the Use-when clause is present so no 3-cap applies.

5 / 5

Trigger Term Quality

Includes natural phrases a user would say ("帮我整理", "分类 thread", "点击整理按钮") plus a triggers list and the English "organize threads". Good natural-term coverage; sits above the 3 anchor (which lacks common variations) but a few synonyms are missing, so not a 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (thread label suggestion for cat_cafe) with specific triggers and a Not-for boundary, so above a 3. It is not a 5 because "整理"/"organize" are fairly generic verbs with minor overlap risk against general categorization skills.

4 / 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.

Validation15 / 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
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.