CtrlK
BlogDocsLog inGet started
Tessl Logo

cheat-seed

跟用户对话讨论选题——**默认一次一个**,用户主动给主题或经历,AI 围绕用户的输入深挖、提炼角度、写一份 draft。不是 AI 拿三个开放问题追用户,也不是一次给 5 个候选。触发词:"找选题"/"我想做一条 X"/"最近有个想法"/"seed"/"启动种子"。可选 batch 模式:`/cheat-seed --batch 5` 走旧的 brainstorm 5 候选 + 写 5 draft 流程。

60

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/cheat-seed/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 thorough, actionable workflow with strong validation loops and real self-check code, scoring well on actionability and workflow clarity. It is held back by repetition that inflates length and by monolithic inlining with dangling references to bundle files that are not present, capping conciseness and progressive disclosure.

Suggestions

De-duplicate the recurring design mantras (AI 不主动开放问, 一次一个选题, humanizer 只去 AI 味不替用户改写) into a single Constants/Rules section and reference it instead of restating per phase.

Move the data-source routing and candidate-schema detail into local reference files under references/ and link to them, so the body stays an overview; remove or fix the broken ../../shared-references/ links.

Either spell out the Batch Mode brainstorm steps inline or point to a real bundled reference, rather than deferring to "commit history", which is not actionable at runtime.

DimensionReasoningScore

Conciseness

Mostly efficient domain-specific guidance with concrete ❌/✅ examples, but it repeats the design rationale many times (the "not 5 candidates / AI 不主动开放问 / humanizer 只去 AI 味" points each appear 3-4 times across phases) and over-narrates intent, which a competent Claude already grasps from one statement.

3 / 5

Actionability

Largely executable: concrete awk/grep line-format self-check with a real threshold (avg_chars_per_line < 15 且 line_count >= 8), explicit draft header template, candidate id formula (sha256[:12]), and deterministic Phase 4.5a/4.5b steps; minor gaps where external skill behavior and trend routing are referenced rather than specified.

4 / 5

Workflow Clarity

Clear phased sequence (0 through 5) with a Mode A/B/C/Batch routing tree, explicit turn caps (MAX_DEEP_DIVE_TURNS=4, MODE_B_MAX_REPROBE_TURNS=2), and validation checkpoints (line-format self-check, humanizer gate, user-confirmation gates); Batch Mode's 15-candidate step is outsourced to commit history rather than spelled out, slightly weakening the sequence.

4 / 5

Progressive Disclosure

Well-sectioned body with clear headers, but it is a monolithic ~430-line wall of inlined process detail; several clearly referenceable chunks (data-source routing, candidate schema, rubric notes) are pointed to shared-references/ paths that do not exist in this bundle, and no local reference files are present to offload the dense inline material.

3 / 5

Total

14

/

20

Passed

Description

82%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 dense, trigger-rich description that clearly conveys the conversational single-topic seed workflow and its batch escape hatch with real user phrases. It loses a point on completeness and specificity because the run-on, parenthetical phrasing buries the crisp what/when and capability list rather than stating them cleanly.

Suggestions

Split into two sentences: one stating the concrete capabilities (deep-dive user input, extract angles, write one draft) and one stating trigger words and the optional batch mode, so the what/when split is explicit.

Trim the meta-commentary ("不是 AI 拿三个开放问题追用户,也不是一次给 5 个候选") into the body; the description should state what it does, not defend the design.

Add a brief distinctiveness clause distinguishing /cheat-seed from /cheat-trends to reduce sibling-skill overlap risk at the description level.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions (discuss topics, deep-dive, extract angles, write a draft, optional batch brainstorm), but phrasing is process-narrative rather than a tight list of discrete capabilities.

4 / 5

Completeness

Clearly answers both what (discussion + angle extraction + draft) and when (trigger words + batch mode), but the dense run-on structure makes the what/when split implicit rather than crisp, so it stops just short of the explicit-clause anchor.

4 / 5

Trigger Term Quality

Comprehensive natural trigger phrases a user would actually say ("找选题", "我想做一条 X", "最近有个想法", "seed", "启动种子") plus the explicit --batch flag, covering synonyms and invocation forms.

5 / 5

Distinctiveness Conflict Risk

Distinct niche (single-topic discussion seed vs. batch brainstorm) with specific triggers; minor overlap risk with sibling /cheat-trends, which the body explicitly disambiguates but the description does not.

4 / 5

Total

17

/

20

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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: 6 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

12

/

16

Passed

Repository
XBuilderLAB/cheat-on-content
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.