paper-illustration-image2

Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to `paper-illustration`, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/paper-illustration-image2/SKILL.md

Quality

Content

77%

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

The skill is highly actionable with a clear, well-validated iterative workflow and concrete executable commands throughout. Its weaknesses are token inefficiency from a large decorative diagram and inline style guide, and a monolithic structure that underuses progressive disclosure.

Suggestions

Move the CVPR/ICLR/NeurIPS style guide into a separate references file (e.g., STYLE.md) and link to it, keeping SKILL.md as a lean overview.

Replace the ~50-line ASCII box-art workflow diagram with a compact numbered list or a much smaller schematic to recover context-window budget.

Trim the 13-item Key Rules list, which largely restates the workflow steps, or consolidate it into the relevant steps to remove duplication.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable but padded: a ~50-line decorative ASCII workflow diagram, an inline top-tier conference style guide, emoji checklists, and a 13-item Key Rules list that repeats content already stated in the step sections.	2 / 3
Actionability	Provides fully executable commands (preflight/finalize/verify with exact args), concrete MCP call signatures with parameters, copy-paste LaTeX, and specific refinement feedback examples — copy-paste ready.	3 / 3
Workflow Clarity	A clearly sequenced multi-stage iterative workflow with explicit validation checkpoints: preflight ok=true gate, Step 5 score >= 9 acceptance gate, verify-before-success, and a repair path feedback loop for error recovery.	3 / 3
Progressive Disclosure	The ~390-line SKILL.md is largely monolithic; the inline CVPR/ICLR style guide and constants could live in separate reference files, and several referenced paths (shared-references/integration-contract.md, tools/ shim) are not present in the bundle.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and well-differentiated from sibling skills, clearly stating concrete capabilities. Its main weaknesses are the lack of an explicit "Use when..." trigger clause and incomplete coverage of the natural terms users would say.

Suggestions

Add an explicit "Use when..." clause listing trigger situations (e.g., when the user asks for an architecture diagram, method illustration, or pipeline figure for a paper).

Expand trigger terms to include natural phrasings like "paper figure", "architecture diagram", "method illustration", and "pipeline diagram" that a user would actually say.

Trim the meta-context about being an experimental alternative to paper-illustration; lead with the concrete capability and when-to-use triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Generate publication-quality academic illustrations", "local Codex app-server bridge", "Codex native image generation" — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	The "what" is clear, but there is no explicit "Use when..." trigger; the "when" is only implied by "intended for Claude Code users who want a GPT-image-style renderer", which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Includes "publication-quality academic illustrations" and "paper" but omits natural user terms like "figure", "diagram", "architecture diagram", or "method illustration", so coverage is only partial.	2 / 3
Distinctiveness Conflict Risk	Explicitly positions itself as "a separate experimental alternative to `paper-illustration`... without modifying the original skill" and ties to a specific Codex bridge, giving it a clear niche unlikely to trigger the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/paper-illustration-image2/SKILL.md
Commit: c5f3d5b

Reviewed: about 1 hour ago

Table of Contents

Discovery Implementation Validation

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.