CtrlK
BlogDocsLog inGet started
Tessl Logo

intermediary-rescue-mission

Use when rescuing someone from legal trouble through trusted intermediaries. Based on Tao Zhu Gong's attempt to save his son via Zhuang Sheng: provide resources without strings, give clear instructions, leave immediately, trust the intermediary's method, and never interfere mid-process.

68

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 concise, well-organized instruction-only skill with a clear sequenced workflow and verification steps. Tightening the slight redundancy between Steps and Critical Warning, and adding an explicit recovery loop, would push it higher.

DimensionReasoningScore

Conciseness

Lean and efficient with no padding or explanation of concepts Claude already knows; only minor redundancy between the Steps and the Critical Warning section keeps it from a 5.

4 / 5

Actionability

Provides concrete, specific guidance including a quoted direct instruction ("Give the gold, do whatever you think best, do not argue or interfere"); minor gaps only, and absence of code is appropriate for an instruction-only skill.

4 / 5

Workflow Clarity

A clearly sequenced six-step process with an explicit Verification section providing checkpoints; the destructive-outcome context is acknowledged but lacks a formal validate-fix-retry feedback loop.

4 / 5

Progressive Disclosure

A short, single-purpose skill under 50 lines with no bundle files and no need for external references; its well-organized sections satisfy the simple-skill exception for a top score.

5 / 5

Total

17

/

20

Passed

Description

87%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, well-structured description that names the domain, lists concrete actions, and provides an explicit 'Use when' trigger, with low conflict risk. Minor improvement possible by adding a few more natural synonyms.

DimensionReasoningScore

Specificity

Lists several concrete actions ("provide resources without strings, give clear instructions, leave immediately, trust the intermediary's method, and never interfere mid-process") rather than vague language, with only minor gaps in coverage.

4 / 5

Completeness

Explicitly answers both what (the procedure's concrete actions) and when ("Use when rescuing someone from legal trouble through trusted intermediaries") with a concrete trigger phrase.

5 / 5

Trigger Term Quality

Natural phrases like "rescuing someone from legal trouble" and "trusted intermediaries" would plausibly be said by a user, though a few synonymous trigger terms are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (legal-trouble rescue via intermediaries) with distinct triggers and minimal risk of firing for the wrong skill.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
baojie/shiji-kb
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.