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.

73

Quality

90%

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

93%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 body is an exceptionally tight, highly actionable single-purpose skill with clear sectioning and concrete templates. The only gap is the absence of an explicit validation/verification step on the final file write, which keeps workflow clarity just below full marks.

Suggestions

Add a validation checkpoint in the 写入 step, e.g. verify the written org file parses (or re-read it to confirm headings/format) before reporting completion.

Consider a brief self-check that the ASCII skeleton uses only the allowed character set before finalizing, since the format rule is marked '零例外'.

DimensionReasoningScore

Conciseness

Lean, efficient Chinese prose with zero padding and no explanation of concepts Claude already knows; the directive '只留筋骨,不带水分' embodies the token-efficiency mindset.

5 / 5

Actionability

Fully actionable: an explicit 8-dimension checklist with per-dimension prompts, a concrete org-mode template, exact file-path pattern, and a specific date command — copy-paste ready guidance covering the common case.

5 / 5

Workflow Clarity

Clear numbered sequence (定锚 → 八刀 → 内观 → 压缩 → 写入) with concrete write commands, but the file-write step lacks an explicit validation checkpoint confirming the org-mode output is well-formed or the file was written correctly.

4 / 5

Progressive Disclosure

Single-purpose, self-contained skill (~75 lines) with no external references needed, organized into clear named sections; meets the simple-skill exception for full marks on progressive disclosure.

5 / 5

Total

19

/

20

Passed

Description

87%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: third-person voice, explicit what-and-when guidance, and a strong set of multilingual trigger phrases targeting a distinctive niche. Its only weakness is that the stated capabilities lean slightly abstract rather than enumerating fully concrete operations.

Suggestions

Make the concrete outputs more tangible in the 'what' clause, e.g. 'generates an 8-section org-mode report with an ASCII concept skeleton and a one-line epiphany'.

Add a couple of natural English synonyms such as 'analyze concept' or 'break down a concept' to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions (deconstruct through 8 named dimensions, compress into an epiphany, produce org-mode output) but the actions are somewhat abstract rather than a comprehensive set of concrete operations, so it falls just short of anchor 5.

4 / 5

Completeness

Explicitly answers both what (deconstructs concepts through 8 dimensions, compresses to an epiphany, org-mode output) and when ('Use when user asks to explain, dissect, or deeply understand a concept') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good keyword coverage with explicit natural trigger phrases across Chinese ('解剖概念', '概念解剖'), English ('explain concept', 'learn concept'), and a slash command, missing only a few synonyms like 'analyze concept'.

4 / 5

Distinctiveness Conflict Risk

Clear niche (8-dimension concept dissection producing org-mode output) with distinctive, specific trigger phrases and minimal overlap risk with other skills.

5 / 5

Total

18

/

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
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.