CtrlK
BlogDocsLog inGet started
Tessl Logo

vision-rescue

绝境反转方法论:当任务似乎没有希望、反复摆动、准备放弃愿景时的五步突破框架。 Use when: 任务看起来无解、多次尝试失败后想放弃、输出投降修辞("现状最优"/"没救了"/"接受现实")、连续 3+ 轮在希望与绝望间摆动。 Not for: 未出现绝境信号的常规 debugging(用 debugging)、常规探索/调研(用 deep-research)、operator 已签字降级的目标、trivial 任务。 Output: Desperation Packet(六问证据评估)+ 新方向行动计划 / operator 升级请求。

73

Quality

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 well-structured, actionable methodology skill with concrete tools, templates, and a validation-gate checklist. Conciseness and progressive disclosure are the only minor weaknesses, driven by some stylistic repetition and an inline case study that could be split out.

Suggestions

Trim stylistic/manifesto lines and consolidate the F198 example to a single inline mention, moving the full "教学案例" walkthrough into a references/ case-study file to reduce repetition.

Move the detailed F198 teaching case to a separate reference file (e.g. references/f198-case.md) and link to it from the body, improving progressive disclosure for this 120-line skill.

Optionally enumerate the five steps briefly in the description so the framework's coverage is explicit without reading the body.

DimensionReasoningScore

Conciseness

Mostly lean with efficient tables and short bullets and minimal over-explanation of known concepts, but some manifesto-style lines ("修辞学暴露你", "不同角度的一只猫 > 同角度的三只猫") and the F198 case referenced inline multiple times could be trimmed.

4 / 5

Actionability

Highly actionable for an instruction skill: concrete tool priority list ("strings <binary>", "grep", experiments, docs, WebFetch), a copy-paste help-request template ("我卡在 X,试过 A/B/C,你能从 Y 角度看看吗?"), and a concrete 6-question Desperation Packet checklist.

5 / 5

Workflow Clarity

A clearly sequenced Step 1–5 framework with an explicit validation gate (the Desperation Packet: "六问全答 → 提交 operator 决策。有空白 → 回去补") providing a validate→fix→retry feedback loop; not a destructive/batch operation so no validation cap applies.

5 / 5

Progressive Disclosure

Well-organized into clear signaled sections with no nested references and no bundle files, but at ~120 lines the detailed inline "教学案例" case study could live in a separate reference file; the under-50-line simple-skill exception does not apply.

4 / 5

Total

18

/

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.

A strong description that crisply states what the skill does, when to use it, when not to, and what it outputs, with rich natural trigger synonyms. The only gap is that the five steps are referenced but not enumerated.

DimensionReasoningScore

Specificity

Names the domain and several concrete outputs ("Desperation Packet(六问证据评估)", "新方向行动计划", "operator 升级请求"), but only references the framework as "五步突破框架" without enumerating the steps, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers what (绝境反转方法论 / 五步突破框架 with concrete outputs) and when ("Use when:" with concrete trigger phrases), plus "Not for" and "Output" clauses.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases with many synonyms a user would actually say when giving up ("没希望"/"没救了"/"无解"/"死胡同"/"不可能"/"走投无路"/"现状最优"/"接受现实"), reinforced by an explicit triggers list.

5 / 5

Distinctiveness Conflict Risk

Clear niche (desperation/vision-rescue) with distinct surrender-rhetoric triggers and an explicit "Not for" boundary against debugging and deep-research, minimizing conflict risk.

5 / 5

Total

19

/

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.