CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-figure

Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.

76

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear validated workflow and lean, executable guidance, scoring top marks on conciseness, actionability, and workflow clarity. The only weakness is progressive disclosure: a long monolithic file with no offloaded reference material, where some sections could be split into separate files.

Suggestions

Move the Figure Type Reference table (and/or the full quality checklist) into a references/ file (e.g. FIGURE_TYPES.md) and link to it one level deep, removing the duplication with the Step 3 decision tree.

Split the shared paper_plot_style.py and per-figure generation templates into a scripts/ bundle referenced from SKILL.md so the overview stays a concise pointer.

Consolidate the 'Key Rules' with the Step 8 checklist to eliminate restated guidance (e.g. vector PDF, no titles inside figures) and tighten token use.

DimensionReasoningScore

Conciseness

The body is dense with executable code, tables, and checklists and avoids explaining concepts Claude already knows; the only redundancy is the Figure Type Reference table echoing the earlier decision tree, which is minor rather than padded verbosity.

3 / 3

Actionability

Fully executable Python (paper_plot_style.py, gen_fig2, gen_fig3), concrete LaTeX, a bash run loop, and a specific MCP codex call with config are copy-paste ready, matching the top anchor.

3 / 3

Workflow Clarity

Eight explicit numbered steps include a render-then-verify validation checkpoint (Step 5) placed before the Step 7 review and a reviewer feedback loop, with a partitioned quality checklist — a clear sequence with explicit validation.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is one ~305-line file; large reference-like content (the Figure Type Reference table, the full checklist, LaTeX templates) is inline rather than split into one-level-deep references, matching the 'content that should be separate is inline' anchor.

2 / 3

Total

11

/

12

Passed

Description

100%

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 concise and hits all four top anchors: concrete actions, natural bilingual triggers, explicit what-and-when, and a clearly distinct niche. No vague fluff or over-claims are present.

DimensionReasoningScore

Specificity

"Generate publication-quality figures and tables from experiment results" names multiple concrete deliverables (figures, tables) and a concrete source (experiment results) in third person, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

It clearly answers both 'what' (generate publication-quality figures and tables from experiment results) and 'when' (explicit 'Use when...' clause), matching the top anchor.

3 / 3

Trigger Term Quality

Explicit natural triggers "画图", "作图", "generate figures", "paper figures", and "needs plots for a paper" give broad coverage of terms a user would actually say, in both Chinese and English.

3 / 3

Distinctiveness Conflict Risk

The niche is specific (publication figures/tables from experiment data) with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
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.