SKILLEMALL.ai
GitHub ↗ RU Sign in

BF one-shot-research-poster

Build print-ready academic conference posters from papers, PDFs, LaTeX projects, arXiv/OpenReview/project pages, reference posters, and user assets in one user request with internal render/repair iterations. Use when the agent must deliver a real final poster package, not a browser screenshot: verified paper claims, official venue logistics, conference and affiliation logos, complete paper figures, local assets, exact-size HTML/CSS, final PDF, final PNG preview, editable source, and a gate report. Defaults to a hard-gated posterly-style production pipeline; uses interactive poster editors only as optional layout assistants.

ClawHub Agent Skills author: Shigui Li v0.1.0 MIT-0 2 files body ≈ 2 843 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Build print-ready academic conference posters from papers, PDFs, LaTeX projects, arXiv/OpenReview/project pages, reference posters, and user assets in one…

As a process F 47/100 · Will not run — References files that are not bundled: references/engine-selection.md, references/failure-analysis.md, scripts/figure_edge_audit.py

GeneratorLaTeXDesignResearchSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
83/100
safety, quality, tests
Safety 60%
100
Quality 40%
57
Run on models
none yet
Process rating
F
47/100
Will not run
References files that are not bundled: references/engine-selection.md, references/failure-analysis.md, scripts/figure_edge_audit.py
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Build print-ready academic conference posters from papers, PDFs, L… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning missing-ref reference to a missing file: references/engine-selection.md
  • warning missing-ref reference to a missing file: references/failure-analysis.md
  • warning missing-ref reference to a missing file: scripts/figure_edge_audit.py
  • warning missing-ref reference to a missing file: scripts/logo_asset_plan.py
  • warning missing-ref reference to a missing file: scripts/logo_selection_plan.py
  • warning missing-ref reference to a missing file: scripts/audit_poster_text.py
  • warning missing-ref reference to a missing file: references/logo-discovery.md
  • warning missing-ref reference to a missing file: references/poster-system-comparison.md
  • warning missing-ref reference to a missing file: references/content-qa.md
  • warning missing-ref reference to a missing file: references/visual-qa.md
  • warning missing-ref reference to a missing file: scripts/check_poster_deliverables.py

Process rating: all ten parameters 47/100

Will not run. References files that are not bundled: references/engine-selection.md, references/failure-analysis.md, scripts/figure_edge_audit.py
  • 0Tools and files. 11 referenced file(s) missing: references/engine-selection.md, references/failure-analysis.md, scripts/figure_edge_audit.py
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 8 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (one-shot-research-poster) differs from the folder (1shotposter)
  • 50When it triggers. No condition that starts the skill
  • 100Steps. 83 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Execution cost. Instruction body is 2843 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • +1No license
  • +2Single-language instructions
  • +3Description length 631: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 83 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.

External checks

ClawHub: clean
This skill appears benign: it guides authorized ClawHub staff through content-rights email correspondence with explicit dry-run, signoff, and audit-recording safeguards.
LLM: benign (high) · VirusTotal: · 26 Jun 2026