SKILLEMALL.ai
GitHub ↗ RU Sign in

CC paper2poster

Render a pre-extracted paper's structured 9-section spec (`paper_spec.md`) into a single-page HTML academic poster, fit the layout to the page via an iterative measured-fill loop, and export it to print-ready PDF + PNG thumbnail. Requires the upstream `paper2assets` skill to have produced an output bundle with `manifest.json` at the root and an `assets/` folder holding the paper metadata and media. Use when the user wants an HTML poster, PDF/PNG export, or PPTX from extracted paper assets, for example "render the poster", "make the poster from this spec", "export poster to PDF", or "paper2poster". The three skills paper2assets → paper2poster → html2pptx run in sequence, each invokable on its own.

microsoft/ResearchStudio Agent Skills author: microsoft 67 files · 24 scripts body ≈ 21 046 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Render a pre-extracted paper's structured 9-section spec (paperspec.md) into a single-page HTML academic poster, fit the layout to the page via an iterative…

As a process C 53/100 · Has gaps — References files that are not bundled: assets/layouts/{full,half,3col}.html, assets/layouts_portrait/{full,half}.html, assets/styles/*.css

GeneratorPowerPointSlackData and analyticsDesignMedia and videotype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
81/100
safety, quality, tests
Safety 60%
86
Quality 40%
74
Run on models
none yet
Process rating
C
53/100
Has gaps
References files that are not bundled: assets/layouts/{full,half,3col}.html, assets/layouts_portrait/{full,half}.html, assets/styles/*.css
Tools and files w 18
0
Result and completion w 14
0
Execution cost w 6
10
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. 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 · 6

✓ No critical or high findings

Medium and low: 6
  • medium Dangerous commands cmd-autorun-instruction references/staged_fill.md:95
    Instructs the agent to auto-run a script on every session
    1. **Measure** — first run `check_poster.py autofit <outdir>/poster.html` (deterministically closes the continuous-lever gaps a machine can size exactly: every `.grow`-card row-gap gap AND the scan-to
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash(*)
    allowed-tools: Bash(*) Read Write Edit Grep Glob AskUserQuestion WebFetch WebSearch
  • low Secrets in code secret-high-entropy-token assets/katex/katex.min.js:1
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    !function(e,t){"object"==typeof exports&&"object"==typeof module?module.exports=t():"function"==typeof define&&define.amd?define([],t):"object"==typeof exports?exports.katex=t():e.katex=t()}("undefine
    detector
  • low Secrets in code secret-high-entropy-token scripts/render_poster.py:1456
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    state_name = "__pa…ate"
    quoted
  • low Concealment en-hide-from-user SKILL.md:165
    Instruction to hide actions from the user (negated — the text forbids it)
    **Optional files `<outdir>/assets/logos/` and `<outdir>/assets/qr/` may be absent** — but **DO NOT silently delete the logo/QR HTML blocks** just because the directory is missing. Two common reasons t
    negated
  • low Dangerous commands cmd-autorun-instruction SKILL.md:417
    Instructs the agent to auto-run a script on every session (security demo / example)
    The lean initial render usually leaves some sections under-filled. Grow content with an **iterative loop** until every section reads `FULL` (`fullRatio` 90–100% of the card height, padding included).
    demo

Files scanned: 67. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 21046 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: assets/layouts/{full,half,3col}.html
  • warning missing-ref reference to a missing file: assets/layouts_portrait/{full,half}.html
  • warning missing-ref reference to a missing file: assets/styles/*.css
  • warning missing-ref reference to a missing file: assets/headers/{v1,v2,v3,v4,v5,v6,v7}.html
  • warning missing-ref reference to a missing file: assets/headers_portrait/{pv1,pv2,pv3,pv4,pv5,pv6,pv7}.html
  • warning missing-ref reference to a missing file: assets/scan/*.html
  • warning missing-ref reference to a missing file: assets/logos/_venue.png
  • warning missing-ref reference to a missing file: assets/layouts/<layout>.html
  • warning missing-ref reference to a missing file: assets/layouts_portrait/<layout>.html
  • warning missing-ref reference to a missing file: assets/styles/<style>.css
  • warning missing-ref reference to a missing file: assets/headers/<v>.html
  • warning missing-ref reference to a missing file: assets/headers_portrait/<pv>.html
  • warning missing-ref reference to a missing file: assets/scan/<variant>.html
  • warning missing-ref reference to a missing file: assets/{layouts,layouts_portrait,styles,headers,headers_portrait,scan}/
  • warning missing-ref reference to a missing file: assets/qr/*.png
  • warning missing-ref reference to a missing file: assets/meta/figure_selection.json
  • warning missing-ref reference to a missing file: assets/audio/<id>.mp3
  • warning missing-ref reference to a missing file: assets/logos/logos.json
  • warning missing-ref reference to a missing file: assets/logos/
  • warning missing-ref reference to a missing file: scripts/font_embedder.py
  • note edit-residue the text marks something as outdated (lines 123, 228, 388, 444, 470, 482): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 53/100

Will not run. References files that are not bundled: assets/layouts/{full,half,3col}.html, assets/layouts_portrait/{full,half}.html, assets/styles/*.css
  • 0Tools and files. 20 referenced file(s) missing: assets/layouts/{full,half,3col}.html, assets/layouts_portrait/{full,half}.html, assets/styles/*.css
  • 0Result and completion. Does not say what the result is
  • 10Execution cost. Instruction body is 21046 tokens: crowds the task out of the window
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 127 steps, 3 vague phrases
  • 100Failures and branches. 8 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (68 tags): a typed call is more reliable

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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 4 example trigger phrases
  • +3Description length 705: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 127 items
  • +4Has examples (15 code blocks)
  • +4Reference files are cited in the instructions (6 of 6)
  • +3All 4 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.