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.

61

Quality

71%

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 ./kg/ontology/ontology-v1/skus/procedural/skill_113/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, single-file instruction skill with a clear sequence and verification checklist, but it leans on abstract directives and narrative exposition rather than concrete, checkpoint-driven guidance.

Suggestions

Tighten conciseness by condensing the 'Critical Warning' and 'Why Use the Right Person' narrative into terse do/don't rules, cutting the historical retelling while keeping the lesson.

Raise actionability by adding concrete, decision-oriented guidance — e.g. criteria for selecting the intermediary (specific influence/integrity signals) and an exact delivery script the courier should say — rather than abstract directives.

Strengthen workflow clarity by converting the end-of-process Verification list into inline checkpoints after key steps (e.g. verify departure immediately after Step 4) and adding a feedback loop for when a checkpoint fails.

DimensionReasoningScore

Conciseness

The body is mostly efficient but includes narrative exposition — 'The eldest son's mistake: He delivered the gold but stayed, watched events, and reclaimed the gold' and the character-trait reasoning in 'Why Use the Right Person' — that is storytelling/justification rather than direct instruction and could be tightened.

2 / 3

Actionability

Steps give some concrete guidance (including a quoted instruction, 'Give the gold, do whatever you think best, do not argue or interfere') but most directives are abstract ('Find someone with influence and integrity', 'Give gold as trust deposit') with no concrete mechanism, so it describes more than fully instructs.

2 / 3

Workflow Clarity

A clear six-step sequence exists alongside a Verification checklist, but the validation checks are a separate end-of-process section rather than inline checkpoints, and there is no validate-fix-retry feedback loop for the high-stakes mission.

2 / 3

Progressive Disclosure

The skill is under 50 lines, needs no external references, and is well-organized into clearly labeled sections (Overview, Steps, Critical Warning, Why Use the Right Person, Expected Outcomes, Verification), meeting the simple-skill criterion for a top score.

3 / 3

Total

9

/

12

Passed

Description

85%

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, specific description with an explicit trigger and a clear distinct niche; its only weakness is thin trigger-term coverage relying on a single scenario phrasing.

Suggestions

Broaden trigger-term coverage with natural variations a user might say, e.g. 'legal trouble', 'bail someone out', 'negotiate through a fixer', or 'get someone released' alongside the existing phrasing.

Consider trimming the historical backstory ('Based on Tao Zhu Gong's attempt to save his son via Zhuang Sheng') from the description to keep the trigger-focused opening crisp, moving that context into the body.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'provide resources without strings, give clear instructions, leave immediately, trust the intermediary's method, and never interfere mid-process' — matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

It explicitly answers both 'when' (an explicit 'Use when...' clause) and 'what' (the enumerated procedure), satisfying the anchor for clearly answering both with explicit triggers.

3 / 3

Trigger Term Quality

It contains a natural trigger phrase ('rescuing someone from legal trouble through trusted intermediaries') but offers only a single scenario phrasing with no common variations, so coverage is partial rather than comprehensive.

2 / 3

Distinctiveness Conflict Risk

The niche — rescuing someone from legal trouble via trusted intermediaries — is highly specific with distinct triggers and is unlikely to conflict with other skills.

3 / 3

Total

11

/

12

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.

Validation16 / 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.