CtrlK
BlogDocsLog inGet started
Tessl Logo

investigation-first

触发:当你准备下判断、做决策或提出建议,但事实、上下文或一手信息还不充分时优先调用;常见信号包括 unknowns、信息缺口、证据不足、领域陌生、需要先摸清现状。 English: Trigger before making claims or decisions when context is incomplete, evidence is weak, or the domain is unfamiliar. Use this skill to investigate first, gather firsthand facts, and let reality shape the conclusion.

60

Quality

69%

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 ./skills/investigation-first/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 well-structured with a genuinely actionable operation protocol and clear workflow, but it is weakened by redundancy across three overlapping sections, decorative quotation padding, and a broken reference to a missing original-texts.md file.

Suggestions

Create the referenced original-texts.md (or remove the dangling reference) so progressive disclosure is not broken.

Collapse the 方法流程, 七项注意, and 常见错误 sections into a single consolidated flow to remove redundancy and tighten conciseness.

Trim decorative Mao quotations to one or two anchors per section so the guidance, not the framing, dominates the token budget.

DimensionReasoningScore

Conciseness

The body is mostly organized but carries notable redundancy — the six-step 方法流程, 七项注意, and 常见错误 table restate the same points — and decorates many sections with Mao quotations that pad rather than instruct.

3 / 5

Actionability

The 操作规程 gives concrete, near copy-paste guidance (a checkbox investigation outline plus a fixed 调查结论 template), though surrounding sections remain abstract principle statements.

4 / 5

Workflow Clarity

A clear six-step sequence plus a four-step operation protocol with a checklist (checkboxes marked [x]) and a guard ('调查结论必须先于任何行动方案出现'); lacks an explicit error-recovery feedback loop, so it stops short of 5.

4 / 5

Progressive Disclosure

Section structure is reasonable, but the sole external reference ('详细原著依据见 original-texts.md') points to a file that does not exist in references/, and the quote material it would hold is inlined rather than split out.

3 / 5

Total

14

/

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.

The description is explicit and bilingual with strong 'when' trigger guidance and natural keywords, scoring well on completeness and trigger quality. It is held back by abstract rather than granular action specificity and moderate overlap risk with related reasoning skills.

DimensionReasoningScore

Specificity

Names the investigation domain and a few concrete actions ('investigate first, gather firsthand facts, and let reality shape the conclusion'), but these are abstract behavioral directives rather than the comprehensive, granular actions a 4 or 5 would list.

3 / 5

Completeness

Explicitly answers both what ('investigate first, gather firsthand facts, and let reality shape the conclusion') and when ('Trigger before making claims or decisions when context is incomplete...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage in both languages ('unknowns、信息缺口、证据不足、领域陌生' and 'context is incomplete, evidence is weak, or the domain is unfamiliar'), matching phrases users would actually voice; a few synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The 'investigate before deciding' trigger is somewhat specific, but as a broad meta-cognitive skill it overlaps with sibling reasoning skills (矛盾分析, 实践认识论) referenced in the body, leaving real overlap risk.

3 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HughYau/qiushi-skill
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.