CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-think

追本之箭——纵向深钻思维工具。给一个观点、现象或问题,像箭一样一路向下钻到不可再分的本质。Use when user says '想透', '追本', '本质是什么', '为什么会这样', '深挖', '钻到底', 'think deep', 'drill down', or wants to trace any idea/phenomenon vertically to its irreducible root. Also trigger when user provides a statement and wants depth analysis, not breadth survey.

62

Quality

73%

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/ljg-think/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-3

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

The body is well-organized and its output mechanics are genuinely executable, but the core drilling method leans on metaphor and atmospheric framing rather than a tight, fully operationalized procedure. The end-to-end workflow is implied rather than unified, which caps workflow clarity below the top level.

Suggestions

Tighten or relocate the poetic preamble (你是什么 / 钻的逻辑): keep one concise framing line and move the rest of the token budget into the operational method.

Operationalize '怎么钻': replace '脚下的地面' metaphor with an explicit per-layer procedure (e.g., state the current assumption, ask 'why is this true?', restate the deeper frame) so the method is repeatable.

Add a brief unified end-to-end sequence (drill each layer → apply 到底 check → write notes → report path) so the implicit workflow becomes one explicit, checkpointed flow.

DimensionReasoningScore

Conciseness

The body is mostly efficient and does not lecture on concepts Claude already knows, but the atmospheric preamble ('一支离弦之箭...') and analogies (地质学家/物理学家) add tokens that don't directly advance execution. Not a 1 because there is no generic padding; not a 3 because not every token earns its place.

2 / 3

Actionability

Concrete, copy-paste-ready output steps ('date +%Y%m%dT%H%M%S', the notes path, org-mode, no markdown) and specific writing rules (每层有命名, 层间有裂缝) are present, but the core method '找到当前这层脚下的地面,然后钻进那个地面' is metaphorical rather than a fully operationalized procedure. Solid guidance with some abstraction remaining.

2 / 3

Workflow Clarity

A clear termination criterion ('到底的标志') and a clean 4-step output sequence are present, but the end-to-end flow (drill → check bottom → write) is implied across sections rather than presented as one checkpointed sequence. Not a 1 because stopping criteria and ordered output steps exist; not a 3 because the overall workflow isn't unified with explicit feedback checkpoints.

2 / 3

Progressive Disclosure

A single-purpose thinking skill with no external references and no bundle files, organized into clear, well-delimited sections (怎么钻 / 什么算到底 / 怎么写 / 输出). Per the simple-skill carve-out, well-organized sections with no need for external references score 3.

3 / 3

Total

9

/

12

Passed

Description

90%Weight 40%Scale 1-3

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 description: it defines a clear niche, supplies abundant natural trigger terms in both languages, and explicitly covers both what the skill does and when to use it. The only soft spot is specificity — its 'actions' are conceptual (drill to essence) rather than enumerated concrete operations, which is inherent to a thinking tool.

DimensionReasoningScore

Specificity

Names a clear domain ('纵向深钻思维工具') and a core action ('像箭一样一路向下钻到不可再分的本质'), but for a conceptual tool the actions remain abstract rather than 'multiple specific concrete actions'. Not a 1 because it is far more concrete than 'helps with documents'; not a 3 because it lists no enumerated concrete operations.

2 / 3

Completeness

Explicitly answers 'what' ('纵向深钻思维工具...钻到不可再分的本质') and 'when' via an explicit 'Use when user says...' plus 'Also trigger when...' clause, matching the top anchor for both what AND when with explicit triggers.

3 / 3

Trigger Term Quality

Includes a rich, natural set of triggers a user would actually say — '想透','追本','本质是什么','为什么会这样','深挖','钻到底','think deep','drill down' — covering both Chinese and English phrasings. Matches the 'good coverage of natural terms' anchor.

3 / 3

Distinctiveness Conflict Risk

Triggers are highly distinctive and the 'depth analysis, not breadth survey' phrase explicitly disambiguates it from survey/summary skills, giving it a clear niche unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

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.

Validation15 / 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
lijigang/ljg-skills
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.