cheat-recommend

从 candidates.md 里按当前 rubric 排序推荐 top N 选题，每条带 composite + 一句 rationale + 锚点对比。**candidates 不存在时给引导而非报错**。触发词："推荐选题"/"next topic"/"下一篇做什么"/"recommend topics"/"挑一个选题"。

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 skill body is highly actionable with a clear, checkpointed multi-phase workflow and well-signaled external references. Its main weakness is conciseness — several long inlined templates and guidance blocks could be trimmed or factored out to respect the token budget.

Suggestions

Move the full green/orange/red/blue buffer output templates into a single parameterized template or a referenced file, keeping only the structural skeleton inline to reduce token usage.

Tighten the '无候选池引导' block — the seed-vs-trends distinction can be summarized in one line instead of a multi-bullet sub-explanation.

Consider extracting the long Phase-4 example output into a separate example file referenced one level deep, retaining only a compact representative snippet in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not explain concepts Claude already knows, but it is noticeably long — fully inlined output templates (green/orange/red/blue buffer variants) and the lengthy '无候选池引导' seed-vs-trends block could be tightened; it sits at the 'mostly efficient but could be tightened' anchor rather than the lean 4-anchor.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: exact filter rules, a buffer-color override table, and a complete example output block with real dimension scores, rationales, and anchors — matching the 5-anchor of copy-paste-ready examples covering common cases.	5 / 5
Workflow Clarity	A clearly sequenced Phase 0→1→2→2.5→3→4 flow with explicit checkpoints (existence check, filter gates, buffer override, fallback when no experimental candidate exists) and feedback/recovery handling, matching the 5-anchor of clear sequence with validation steps and error-recovery loops.	5 / 5
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep references to cadence-protocol.md and candidate-schema.md, but several large blocks (full output templates, the no-pool guidance) are inlined rather than split out, leaving it just short of the clean 5-anchor split.	4 / 5
	Total	17 / 20 Passed

Description

95%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, complete, and rich with natural bilingual trigger phrases; it clearly conveys both the action and the triggering context. Its only gap is that the action list, while specific, is not as comprehensively enumerated as the top anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('按当前 rubric 排序推荐 top N', '每条带 composite + 一句 rationale + 锚点对比', 'candidates 不存在时给引导而非报错') but stops short of the fully comprehensive multi-action list of the 5-anchor.	4 / 5
Completeness	Explicitly answers both 'what' (sort candidates by composite and recommend top N with rationale + anchors) and 'when' via an explicit 触发词 trigger clause, matching the 5-anchor of clear what-and-when with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases in both Chinese and English ('推荐选题', 'next topic', '下一篇做什么', 'recommend topics', '挑一个选题') that users would naturally say, matching the 5-anchor's full coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (candidate-pool ranking with composite/anchor framing) with distinct, specific triggers unlikely to fire for unrelated skills, matching the 5-anchor's minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	13 / 16 Passed

Repository: XBuilderLAB/cheat-on-content
Path: skills/cheat-recommend/SKILL.md
Commit: 86823e1

Reviewed: 4 days 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.