Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

render-brief-assets — measured AI agent skill | DecimalAI

understudy-ai/render-brief-assets

NewSkillScoreMaintained

Render polished cover and summary-card image assets for the brief package.

by understudy-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Design & UX Review pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/understudy-ai-render-brief-assets/SKILL.md

decimalai skills pull understudy-ai-render-brief-assets --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/understudy-ai-render-brief-assets/SKILL.md https://app.decimal.ai/s/understudy-ai-render-brief-assets/SKILL.md

Raw file: /s/understudy-ai-render-brief-assets/SKILL.md ↗ · machine-readable summary at /s/understudy-ai-render-brief-assets.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

—-59% tokens0% turns64% of whole cases pass with skill (14/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-05	✗→✓	▲ Improved	-75%	0%
case-08	✗→✓	▲ Improved	-77%	0%
case-09	✗→✓	▲ Improved	-83%	0%
case-10	✗→✓	▲ Improved	-77%	0%
case-11	✗→✓	▲ Improved	-63%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

understudy-ai / understudy

packages/gateway/src/__tests__/fixtures/handwritten-playbook-demo/skills/render-brief-assets/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

render-brief-assets

Overall Goal

Render the final visual assets for the brief package from the target context and summary.

Inputs

target.json
summary.json
brief.md
highlights.json

Outputs

cover.png
summary-card.png

Staged Workflow

Read the target metadata and summary.
Render the cover with the target title and verdict.
Render the summary-card image with ratings and highlights.

Tool Route Options

shell plus ffmpeg for deterministic rendering

Detailed GUI Replay Hints

None. This stage should not depend on GUI state.

Failure Policy

If one asset fails, keep the successful asset and surface a recovery note.

Want to see if understudy-ai/render-brief-assets would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.