CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-read

Reading companion agent. Accompanies user through any text (books, articles, essays, papers, news) with translation, structural annotation, deep questioning, and cross-domain insights. Detects language, translates English to Chinese (faithfulness-expressiveness-elegance), guides reader to understand the author and encounter real questions. Use when user says '伴读', '陪我读', '读这篇', 'read with me', 'companion read', or shares a text/URL wanting guided reading.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

A richly operational instruction-only skill with strong actionability and a clearly sequenced, feedback-loop-driven workflow. Conciseness is slightly reduced by philosophical framing, and progressive disclosure is capped at 2 because everything lives inline in one large file with no external references.

Suggestions

Move the org-mode file template and the detailed Phase 2 branching logic into separate reference files (e.g. references/org-template.org, references/collision-branches.md) referenced one level deep from SKILL.md to improve progressive disclosure.

Trim the philosophical framing in '核心理念' and section openers to pure operational guidance to lift conciseness toward score 3.

Consider adding a short validation step after org-file write (e.g. verify the file exists and reports the path) to make the terminal workflow checkpoint explicit.

DimensionReasoningScore

Conciseness

Mostly efficient operational prose that assumes Claude's competence and avoids explaining known concepts, but the philosophical framing ('不是替你读,是陪你走进去', '核心理念') and some elaborate branching could be tightened; not score 3 because not every token is purely operational, not score 1 because it is not padded with concepts Claude already knows.

2 / 3

Actionability

Provides concrete executable guidance — exact shell commands ('date +%Y%m%dT%H%M%S'), a concrete output path pattern, a full org-mode file template, paragraph tags [骨][肌][筋], three-tier translation layers, and verbatim questions to ask; not score 2 because guidance is specific and copy-ready rather than pseudocode or vague direction.

3 / 3

Workflow Clarity

Sequences a clear Phase 0→1→2→3→4 flow with explicit feedback checkpoints (读者接不住→回到注疏; 说清了/仍说不清 branches) and a mandatory non-skippable step ('读后一句话(不可跳过)'); not score 2 because validation/feedback loops are explicit rather than implicit or missing.

3 / 3

Progressive Disclosure

Well-organized into clear sections but is a monolithic ~270-line single file with no bundle references, keeping all detail (org template, branching logic) inline; not score 3 because it is not an overview pointing to one-level-deep reference files, not score 1 because sections are clearly labeled and navigable rather than a disorganized wall of text.

2 / 3

Total

10

/

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 description: third-person voice, concrete capabilities, explicit bilingual trigger terms, and a clear Use-when clause covering both what and when. No first/second-person voice penalty applies.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'translation, structural annotation, deep questioning, and cross-domain insights', 'Detects language, translates English to Chinese', 'guides reader to understand the author and encounter real questions' — matching the score-3 anchor for several specific concrete actions; not score 2 because it goes well beyond naming only a domain and some actions.

3 / 3

Completeness

Clearly answers both what (reading companion with translation/annotation/questioning/insights) and when via an explicit 'Use when user says ... or shares a text/URL wanting guided reading' clause; not score 2 because the trigger guidance is explicit rather than merely implied.

3 / 3

Trigger Term Quality

Provides natural bilingual triggers users would actually say — '伴读', '陪我读', '读这篇', 'read with me', 'companion read' — covering common variations rather than jargon; not score 2 because coverage is broad and phrased as things a user would naturally say.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (guided reading companion with English-to-Chinese translation focus) anchored by distinctive triggers like '伴读' and 'companion read', making conflict with other skills unlikely; not score 2 because the niche and triggers are sharply distinguishable rather than only somewhat specific.

3 / 3

Total

12

/

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.