CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

principal-agent

当用户选择职业/组织/合作方式、困惑「为什么大公司磨洋工/小公司拼命」「该不该自己干」时调用。 核心理念: 委托人(主人)会把事做好, 代理人会为自己利益优化; 收益与创造价值绑得越紧, 越像委托人; 别让媒体洗脑你需要代理人。 不适用于: 具体薪酬谈判数字、组织架构设计细节。 Triggers: 激励/代理/主人/打工 vs 创业/利益绑定/principal/agent/incentive

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./books/naval-almanack-skill/principal-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 tightly structured single-file skill: methodology, past cases, trigger scenarios, executable steps with completion criteria, and honest boundary/limitation sections. Weaknesses are minor — a dangling test-results.md reference, internal audit metadata, and one vague step.

Suggestions

Remove or fix the '见 test-results.md' reference — the file does not exist in the bundle (no references/, scripts/, or assets/ directories).

Drop or compress the audit footer ('验证通过: V1 ✓ / V2 ✓ / V3 ✓ (v07)', '蒸馏时间') — it is internal metadata that spends tokens without helping the reader.

Make step 4 concrete: specify where and in what format the diagnosis conclusion should be recorded (e.g., '追加到 notes/career-log.md,含日期、绑定程度评级、下一步动作').

DimensionReasoningScore

Conciseness

The ~100-line body is lean and well-sectioned with no padding explaining concepts Claude already knows; the book quote serves as source material. Minor waste remains in the audit footer ('验证通过: V1 ✓ / V2 ✓ / V3 ✓ (v07)', '蒸馏时间: 2026-08-01') and the dangling '见 test-results.md' reference, fitting anchor 4 rather than 5.

4 / 5

Actionability

The E section gives four concrete steps with explicit 完成标准 and a 判停条件 ('若发现纯代理结构(收益完全脱钩)且无法改变,标记为高风险合作') — mostly executable guidance for an instruction-only skill. Step 4 ('记录本次诊断结论') is vague about where/how to record, keeping it below the fully executable anchor 5.

4 / 5

Workflow Clarity

The four steps are clearly sequenced, each with a completion criterion acting as an explicit checkpoint, plus one stop condition. There is no validate-then-fix feedback loop, but the skill involves no destructive or batch operation, so the cap does not apply; minor gap versus anchor 5.

4 / 5

Progressive Disclosure

A single, well-organized file of appropriate size with clear sections and no nested references. The one reference to an external file ('见 test-results.md') points to a file that does not exist in the bundle, a minor organization gap that keeps it at anchor 4.

4 / 5

Total

16

/

20

Passed

Description

75%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 well-crafted description that explicitly covers what (core principal-agent model), when (concrete scenarios plus a bilingual trigger list), and what not (exclusions). Main residual weaknesses are the absence of concrete action verbs and a few missing natural trigger synonyms.

Suggestions

State what the skill does in action form (e.g., '分析用户当前是委托人还是代理人、评估收益与价值的绑定程度') in addition to stating the core idea.

Add missing natural trigger variants such as 'ownership', '股权', '分红', '拿提成还是拿股份' to the Triggers line.

DimensionReasoningScore

Specificity

States the core model concretely ('委托人(主人)会把事做好, 代理人会为自己利益优化; 收益与创造价值绑得越紧, 越像委托人') plus explicit exclusions ('不适用于: 具体薪酬谈判数字、组织架构设计细节'), but describes the conceptual lens rather than listing concrete actions the skill performs. Between anchors 3 and 4, noticeably above the midpoint, so 4.

4 / 5

Completeness

'When' is fully explicit ('当用户选择职业/组织/合作方式…时调用' plus a Triggers line), and 'what' is present via the 核心理念 statement. However the 'what' describes the philosophy rather than what the skill does (e.g., identify/diagnose the user's principal-vs-agent position), so it does not clearly match the fully explicit anchor 5.

4 / 5

Trigger Term Quality

Includes scenario phrases users would naturally say ('为什么大公司磨洋工/小公司拼命', '该不该自己干') and a bilingual trigger list '激励/代理/主人/打工 vs 创业/利益绑定/principal/agent/incentive'. Coverage is good but misses common variants like 'ownership', '股权', '分红', so it fits anchor 4 rather than the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (principal-agent incentive lens) with an explicit negative-scope line reducing wrong-trigger risk. Minor overlap remains with closely related skills — '利益绑定/激励' overlaps the adjacent wealth-structure skill (the body itself notes 股权绑定 as their intersection) — fitting anchor 4 rather than 5.

4 / 5

Total

16

/

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.

Validation — 15 / 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

kangarooking/cangjie-skill

Path

books/naval-almanack-skill/principal-agent/SKILL.md

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.