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.

72

Quality

91%

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 tight, well-structured instruction skill: every phase has concrete prompts, exact formatting rules, and an executable write procedure. The only gaps are the absence of a filled example of the final org-mode output and of any validation step before writing the file.

Suggestions

Add a short filled example of the final org-mode output for one sample concept (e.g., a few lines of the 历史 and 压缩 sections) so the expected result is demonstrated, not just templated.

Add a validation checkpoint before the 写入 step, e.g. 'write 前检查输出中不残留 **bold**、反引号等 markdown 语法;发现则改写后再写入', mirroring the zero-exception format rules.

Handle the missing-directory case in the write step (e.g., create ~/Documents/notes/ if it does not exist) so the final step never fails silently.

DimensionReasoningScore

Conciseness

The body is lean and directive: each of the eight dimensions gets a single arrow-chained line ('最早从哪冒出来 → 怎么变的 → 哪一步拐成了今天的意思'), format rules are terse ('每刀 2-3 句,只留筋骨,不带水分'), and nothing explains concepts Claude already knows. Every token earns its place; nothing to trim.

5 / 5

Actionability

Concrete, executable guidance throughout: an explicit org-mode skeleton, zero-exception formatting rules ('加粗用 *bold*…代码用 ~code~'), the exact command `date +%Y%m%dT%H%M%S`, and an exact output path pattern '…--概念解剖-{概念名}__concept.org'. Not 5 because there is no filled worked example of a completed report, and the analysis prompts are directions rather than a demonstrated output.

4 / 5

Workflow Clarity

The five-phase sequence (定锚 → 八刀 → 内观 → 压缩 → 写入) is clearly ordered with per-phase sub-steps and a definite terminal step ('报告路径,完成'). Not 5 because there is no validation checkpoint (e.g., verifying no markdown syntax leaked before writing) — though the operation is a single non-destructive file write, so the batch/destructive cap does not apply.

4 / 5

Progressive Disclosure

This is a compact single-purpose skill with clean ## / ### sectioning and no external references; nothing belongs in a separate file, no reference paths are cited, and no bundle files exist to dangle. The single-file organization is exactly appropriate for its size, so the simple-skill exception applies.

5 / 5

Total

18

/

20

Passed

Description

92%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: third-person, specific, and complete with an explicit 'Use when' clause, bilingual trigger terms, and a unique command trigger. Its only weakness is trigger coverage that omits a few natural English phrasings like 'what is X'.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the full pipeline — 'deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy)', 'compresses insights into an epiphany', 'Produces org-mode output' — with the dimensions individually enumerated. It is written in third person ('Deep concept anatomist that deconstructs') and coverage is comprehensive for what the skill does; not score 4 because there are no meaningful gaps in the action list.

5 / 5

Completeness

Both questions are answered explicitly: 'what' is the 8-dimension deconstruction ending in an epiphany with org-mode output, and 'when' is stated verbatim — 'Use when user asks to explain, dissect, or deeply understand a concept, term, or idea' — backed by concrete trigger phrases. This matches the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Good natural-term coverage: 'explain concept', 'learn concept', 'deeply understand', 'dissect', plus bilingual triggers '解剖概念' / '概念解剖' and the explicit '/ljg-learn' command. Not 5 because common phrasings users would actually say are missing, e.g. 'what is X', 'tell me about X', 'analyze idea'.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (deep multi-lens conceptual dissection with org-mode note output) with distinctive triggers including a unique slash command '/ljg-learn' and Chinese-language keywords. Overlap risk with generic explanation skills is low; it would not naturally fire for unrelated tasks.

5 / 5

Total

19

/

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.

Validation — 16 / 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.