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.

70

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 lean, well-structured instruction-only skill body: the drilling method, termination criteria, and output procedure are all concrete, and nothing pads the token budget. It misses the top marks only on actionability and workflow clarity, where a worked example and a directory-existence check before writing would close the gaps.

Suggestions

Add one short worked example (3-layer run on a sample statement showing layer names, the crack question, and the terminal layer) so the layered output format is copy-paste concrete rather than described.

Prepend a directory check to the output steps (e.g., `mkdir -p ~/Documents/notes` before writing the timestamped file) so step 4 cannot fail on a missing path.

Include a minimal org-mode skeleton for the output file, since the body mandates org syntax but shows no org structure to follow.

DimensionReasoningScore

Conciseness

The body is lean with zero padding: no concept explanations Claude would already know, no background, and every section (钻的逻辑, 怎么钻, 什么算到底, 怎么写, 输出) carries instruction. The persona metaphors are brief and functional (they define output tone), so every token earns its place.

5 / 5

Actionability

Concrete guidance is present throughout: three named rules, an explicit domain-ladder ('从社会学掉进心理学...从数学掉进逻辑本身'), four terminal categories with a termination test, and exact output commands (`date +%Y%m%dT%H%M%S`) plus a file path template. It falls short of anchor 5 only because there is no worked example of a layered output or a sample org-mode file to copy from.

4 / 5

Workflow Clarity

The sequence is coherent and well-ordered: drilling method → termination criteria → writing style → numbered output procedure with exact commands. Not a destructive or batch operation, so no validation cap applies; the gap that keeps it below 5 is that it never ensures `~/Documents/notes/` exists before writing, nor verifies the file was written before reporting the path.

4 / 5

Progressive Disclosure

This is a short, single-purpose skill with no external references needed; no bundle files (references/, scripts/, assets/) exist. Sections are clearly headed and each addresses one concern, which per the rubric's simple-skill guidance earns a 5 on well-organized structure alone.

5 / 5

Total

18

/

20

Passed

Description

86%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 strong description: it clearly and explicitly states both what the skill does and when to use it, with unusually thorough bilingual trigger terms. Its only weakness is that the capability statement is wrapped in poetic metaphor ('像箭一样一路向下钻') rather than plain concrete actions.

DimensionReasoningScore

Specificity

The description names its domain ('纵向深钻思维工具') and one concrete capability ('trace any idea/phenomenon vertically to its irreducible root'), but the arrow metaphor and poetic framing pad the statement of what is actually a single action. It is not vague enough for a 2 (domain and action are named), but it lacks the multiple specific actions of a 4.

3 / 5

Completeness

Explicitly answers both questions: the what ('给一个观点、现象或问题...钻到不可再分的本质') and a fully explicit when ('Use when user says...', 'Also trigger when user provides a statement and wants depth analysis, not breadth survey'). The 'when' clause includes concrete trigger phrases, matching the anchor 5 example structure.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage in both Chinese ('想透', '追本', '本质是什么', '为什么会这样', '深挖', '钻到底') and English ('think deep', 'drill down'), all phrases a user would plausibly say. File extensions are inapplicable to a thinking skill, so synonyms coverage is effectively complete.

5 / 5

Distinctiveness Conflict Risk

The explicit contrast 'depth analysis, not breadth survey' plus distinctive Chinese trigger phrases carve out a clear niche with minimal conflict risk against most skills. It could still overlap with generic reasoning/analysis skills, which keeps it just below anchor 5.

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
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.