CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

judgment-training

当用户需要做方向性判断、评估「该往哪走/这事靠谱吗」、或想提升决策能力时调用。 核心理念: 判断力(知道行为长期后果)比努力重要; 清晰思考=从基础学科重建推理; 收集心智模型(复利/委托代理/可证伪性/基础数学)。 不适用于: 需要立即执行的具体任务步骤。 Triggers: 判断力/方向/第一性原理/心智模型/思维模型/判断靠不靠谱/judgment/mental model/first principles

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/judgment-training/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

The content is a well-structured R-I-A1-A2-E-B conceptual skill with actionable, sequenced execution steps and clear boundaries. Weaker spots are conciseness (a long quote block and time-stamped audit metadata) and the lack of explicit feedback loops, though the latter is largely forgivable for a non-destructive instruction skill.

Suggestions

Trim the full original-text quote block in section R to the single most load-bearing sentence, and remove the time-stamped 审计信息/蒸馏时间 metadata (or move it to a separate audit file) to improve conciseness.

Add an explicit validation/retry note to the E workflow (e.g. after step 2, 'if a core assumption cannot be re-derived, mark unknown and loop back before applying models') to push workflow_clarity toward 5.

Convert the related-skill slugs in the frontmatter and footer into clearly signaled navigable references (e.g. See [decision-heuristics](../decision-heuristics/SKILL.md)) to strengthen progressive_disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient and well-sectioned, but the lengthy original-text quote block and some restated conceptual explanations (e.g. "判断力=知道行为长期后果并据此决策的能力") plus the time-stamped 审计信息/蒸馏时间 (2026-08-01) could be trimmed; not a 4 because several sections restate what the methodology already conveys.

3 / 5

Actionability

The E section gives four concrete steps each with 完成标准 and a 判停条件 in step 2 (e.g. "至少匹配 1–2 个模型...交叉检验", "每周安排 ≥1 天无会议"); mostly executable guidance with only minor gaps, falling short of 5 because guidance is procedural-prose rather than copy-paste-ready.

4 / 5

Workflow Clarity

A clearly numbered 4-step sequence in section E with explicit completion criteria and a stop-condition checkpoint (判停条件: 若...无法推导,标记为「不可信」); not a 5 because there is no explicit validate→fix→retry feedback loop, though the non-destructive nature of the skill means one is not strictly required.

4 / 5

Progressive Disclosure

The body is a self-contained, well-organized single-purpose skill with clear R/I/A1/A2/E/B section headers and no nested or buried references (no bundle files exist); not a 5 because the ~100-line body is somewhat denser than a lean overview and the related-skill slugs are plain text rather than navigable links.

4 / 5

Total

15

/

20

Passed

Description

83%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.

The description is well-constructed: it states core capabilities, gives explicit invocation conditions and trigger terms in both Chinese and English, and carves out a clear non-applicable boundary. Its main limitation is that the described actions are conceptual rather than operational, keeping specificity and distinctiveness just below the top anchor.

DimensionReasoningScore

Specificity

Names the domain and several concrete concepts/actions—"做方向性判断", "评估「该往哪走/这事靠谱吗」", "收集心智模型(复利/委托代理/可证伪性/基础数学)"—with only minor coverage gaps; not a 5 because the listed actions are conceptual rather than operational.

4 / 5

Completeness

Explicitly answers both what ("核心理念: 判断力...清晰思考...收集心智模型") and when ("当用户需要做方向性判断...时调用" plus the Triggers line), with concrete trigger phrases and an explicit 不适用 clause.

5 / 5

Trigger Term Quality

An explicit Triggers line covers natural Chinese phrases ("判断力/方向/第一性原理/心智模型/思维模型/判断靠不靠谱") plus English synonyms (judgment/mental model/first principles); good coverage with synonyms, falling just short of fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

The trigger niche (judgment/mental models/first principles) plus the 不适用于 execution-tasks exclusion make it mostly distinct, though it still risks minor overlap with adjacent skills like decision-heuristics and rational-buddhism that it itself names as composes-with.

4 / 5

Total

17

/

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/judgment-training/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.