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

—

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 specifies the concrete actions (generating conference posters), the technical approach (LaTeX tcbposter), input/output formats, and provides comprehensive bilingual trigger terms. The explicit 'Use when' clause with both Chinese and English trigger phrases ensures reliable skill selection. It serves as a strong example of a well-crafted skill description.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and outputs: generate a conference poster from a compiled paper, specifying the technology 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 the broader condition of wanting to create a poster for a conference presentation).	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'. These are terms users would naturally say when requesting this task.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche: conference poster generation using LaTeX tcbposter with specific output formats. The bilingual trigger terms and specific domain (conference posters from compiled papers) make it very 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 extreme verbosity and poor progressive disclosure: the same warnings are repeated 3-4 times, hundreds of lines of reference material (color tables, card styles, font sizes, full templates) are inline rather than in separate files, and the document is far too long for efficient context window usage. The content quality is high but the packaging is poor.

Suggestions

Extract venue color schemes, card style definitions, font size tables, and layout diagrams into separate reference files (e.g., VENUE_COLORS.md, CARD_STYLES.md, LAYOUT_TEMPLATES.md) and reference them from the main skill with one-level-deep links.

Deduplicate repeated warnings — consolidate all 'NEVER use beamer', 'NEVER use adjustbox', 'NEVER symlink' warnings into the Key Rules section only, removing inline duplicates throughout the workflow phases.

Move the full LaTeX template and the full PPTX generation Python script into separate template files (e.g., poster_template.tex, generate_pptx_template.py) rather than embedding 100+ lines of code inline.

Cut explanatory narrative (e.g., 'This was validated through 5 failed compilation attempts', 'Lesson learned from testing') — state the rule directly without the backstory.

Dimension	Reasoning	Score
Conciseness	This skill is extremely verbose — likely 2000+ lines with massive amounts of repeated information. The same warnings appear multiple times (e.g., 'NEVER use beamer' appears in architecture decisions, key rules, and inline warnings). Color scheme tables, font size tables, layout diagrams, and card style definitions are exhaustively detailed when much of this could be in reference files. Many explanations are redundant (e.g., explaining why pastel colors are bad, why symlinks fail, why adjustbox is problematic — all repeated). The 'lessons learned' framing adds narrative padding.	1 / 3
Actionability	The skill provides highly actionable, executable content: complete LaTeX templates, copy-paste bash commands, full Python scripts for PPTX generation and SVG conversion, specific font sizes, exact hex color codes, and concrete error-handling patterns. Every phase has executable code examples that are ready to use.	3 / 3
Workflow Clarity	The workflow is clearly sequenced across 8 phases (Phase 0-8) with explicit checkpoints marked by '⛔ STOP HERE and wait for user response', state persistence via POSTER_STATE.json, error handling loops with max attempts, and iterative visual review with score thresholds. Validation steps are explicit (pdfinfo verification, visual inspection checklist, compilation error loop).	3 / 3
Progressive Disclosure	This is a monolithic wall of text with no bundle files to offload content to. The venue color scheme table, card style definitions, font size tables, layout diagrams, full LaTeX templates, full Python scripts, and PPTX generation code are all inline in a single massive file. The color tables, card styles, and layout templates should each be in separate reference files. There are some references to external files (integration-contract.md, extract_paper_style.py) but the core content that should be split out remains inline.	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 (1139 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: a425a71

Reviewed: 1 day 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.