CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-learn

Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or idea. Triggers on '解剖概念', '概念解剖', 'explain concept', 'learn concept', '/ljg-learn'. Produces org-mode output.

76

Quality

93%

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

87%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.

Concise, actionable, and well-structured with concrete commands and a copy-paste template; the main gap is the absence of any validation/verification checkpoint in the write-out workflow.

Suggestions

Add a brief verification step after writing the org-mode file, e.g. confirm the file exists at the reported path and that required top-level headings (* 定锚, * 八刀, etc.) are present.

Include a minimal completed example (a short解剖 of a simple concept like '熵') so the expected output shape is unambiguous beyond the empty template.

Clarify the failure path if date +%Y%m%dT%H%M%S or the ~/Documents/notes directory is unavailable, to close the workflow feedback loop.

DimensionReasoningScore

Conciseness

Lean and directive throughout—each dimension is 2-3 lines, no padding, no explaining of concepts Claude already knows; every section earns its place ('只留筋骨,不带水分').

3 / 3

Actionability

Provides concrete executable guidance: a shell command (date +%Y%m%dT%H%M%S), an exact output path, a copy-paste org-mode template, and a precise ASCII charset constraint for diagrams.

3 / 3

Workflow Clarity

The five phases (定锚→八刀→内观→压缩→写入) are clearly sequenced, but there are no validation or feedback checkpoints (e.g., verifying the org file was written or is well-formed), matching the 'steps listed but checkpoints missing' anchor.

2 / 3

Progressive Disclosure

A single self-contained skill with well-organized sections and no external bundle files; nothing needs to be split off, so the inline structure is appropriate.

3 / 3

Total

11

/

12

Passed

Description

100%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, well-rounded description: third-person, concrete, with explicit 'what' and 'when' guidance and rich bilingual trigger terms anchored by a unique slash command. No notable weaknesses.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—deconstructing a concept through eight named dimensions (history, dialectics, phenomenology, etc.), compressing insights into an epiphany, and producing org-mode output—rather than vague abstractions.

3 / 3

Completeness

Explicitly states what the skill does (8-dimension dissection compressed into an epiphany, org-mode output) and when to use it ('Use when user asks to explain, dissect, or deeply understand a concept'), answering both halves with an explicit trigger clause.

3 / 3

Trigger Term Quality

Covers natural user phrasings in both Chinese ('解剖概念', '概念解剖') and English ('explain concept', 'learn concept') plus the slash command '/ljg-learn', giving broad keyword coverage users would actually say.

3 / 3

Distinctiveness Conflict Risk

The philosophical concept-anatomy niche with a unique slash trigger and org-mode output is clearly distinguishable and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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
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.