paper-poster

Generate a conference poster (article + tcbposter LaTeX → A0/A1 PDF + editable PPTX + SVG) from a compiled paper. Use when user says "做海报", "制作海报", "conference poster", "make poster", "生成poster", "poster session", or wants to create a poster for a conference presentation.

Quality

77%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/paper-poster/SKILL.md

Quality

Discovery

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.

This is an excellent skill description that clearly communicates what the skill does (generates conference posters in multiple formats from compiled papers using LaTeX), when to use it (explicit trigger terms in both English and Chinese), and occupies a very distinct niche. The description is concise yet comprehensive, with strong trigger term coverage and no vague language.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and outputs: generate a conference poster from a compiled paper, specifying the tech stack (article + tcbposter LaTeX), output formats (A0/A1 PDF + editable PPTX + SVG), and the input (compiled paper).	3 / 3
Completeness	Clearly answers both 'what' (generate a conference poster with specific formats from a compiled paper) and 'when' (explicit 'Use when' clause with multiple trigger phrases and a general condition about creating posters for conferences).	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms in both English and Chinese: '做海报', '制作海报', 'conference poster', 'make poster', '生成poster', 'poster session', plus 'conference presentation'. These are terms users would naturally say.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche: conference poster generation using LaTeX tcbposter, with specific output formats. The bilingual trigger terms and the very specific domain (conference posters from papers) make it unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

55%

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

This skill is exceptionally actionable with excellent workflow clarity — every phase has concrete code, explicit checkpoints, and error recovery loops. However, it is severely undermined by its extreme length and lack of progressive disclosure: hundreds of lines of reference material (color tables, full LaTeX templates, card style definitions, font size tables) are inlined rather than split into separate files. Critical warnings are repeated 3-4 times across the document, further inflating token cost.

Suggestions

Extract venue color schemes, card style definitions, and font size tables into a separate POSTER_REFERENCE.md file, keeping only the default venue inline with a pointer to the full table.

Extract the full LaTeX template (Phase 3) into a separate POSTER_TEMPLATE.tex file and reference it, keeping only the key architectural decisions (article class, tcbuselibrary) inline.

Consolidate repeated warnings (beamer prohibition appears 3+ times, adjustbox warning 2+ times, symlink warning 2+ times) into a single 'Key Rules' section — the existing one at the end partially does this but the warnings remain scattered throughout.

Extract the component-based PPTX script (Phase 7, section 6.3) into a standalone Python file reference rather than embedding ~50 lines of Python inline.

Dimension	Reasoning	Score
Conciseness	This skill is extremely verbose — easily 1500+ lines with massive amounts of inline detail that should be in separate reference files. Color scheme tables, full LaTeX templates, card style definitions, font size tables, content budget tables, and multiple layout diagrams are all inlined. Many warnings are repeated multiple times (e.g., 'never use beamer' appears 3+ times, 'never use adjustbox' repeated, symlink warnings repeated). The content budget section alone could be a separate reference file.	1 / 3
Actionability	The skill provides fully executable, copy-paste-ready code throughout: complete LaTeX templates, bash commands for installation and compilation, Python scripts for PPTX generation and SVG conversion, and specific error handling patterns. Every phase has concrete commands and code examples.	3 / 3
Workflow Clarity	The workflow is clearly sequenced across 8 phases with explicit checkpoints (⛔ STOP markers), validation steps (pdfinfo verification, visual review scoring rubric with threshold), error handling loops (max 3 compilation attempts), and iterative refinement (max 5 visual review iterations with score threshold of 9). State persistence via POSTER_STATE.json enables recovery.	3 / 3
Progressive Disclosure	This is a monolithic wall of text with no references to external files for detailed content. The venue color scheme table, full LaTeX template, card style definitions, font size tables, content budget tables, layout diagrams, PPTX generation script, and component-based export script are all inlined in a single massive file. The color tables, card styles, and LaTeX template should each be separate reference files.	1 / 3
	Total	8 / 12 Passed

Validation

72%

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 — 8 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1098 lines); consider splitting into references/ and linking	Warning
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	8 / 11 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Commit: 700fbe2

Reviewed: 2 days 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.