Ready to supercharge your AI agents?

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

Get Started Free →

compose-summary-video — measured AI agent skill | DecimalAI

understudy-ai/compose-summary-video

NewSkillScoreMaintained

Compose the final draft summary video from the generated assets and brief.

design-mediaby understudy-ai

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

Automatic

Marketing & Content pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/understudy-ai-compose-summary-video/SKILL.md

decimalai skills pull understudy-ai-compose-summary-video --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/understudy-ai-compose-summary-video/SKILL.md https://app.decimal.ai/s/understudy-ai-compose-summary-video/SKILL.md

Raw file: /s/understudy-ai-compose-summary-video/SKILL.md ↗ · machine-readable summary at /s/understudy-ai-compose-summary-video.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 3h ago

—-51% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	41%	0%
case-07	✗→✓	▲ Improved	-63%	0%
case-12	✗→✓	▲ Improved	-72%	0%
case-13	✗→✓	▲ Improved	-67%	0%
case-15	✗→✓	▲ Improved	-61%	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/compose-summary-video/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

compose-summary-video

Overall Goal

Compose a draft summary video from the generated brief assets.

Inputs

cover.png
summary-card.png
brief.md
screenshots/

Outputs

draft.mp4

Staged Workflow

Pick the screenshots that best support the brief.
Assemble a concise timeline.
Render draft.mp4.

Tool Route Options

shell plus ffmpeg for deterministic composition

Detailed GUI Replay Hints

None. This stage should not require GUI work.

Failure Policy

If video composition fails, keep the still assets and emit a fallback note.

Want to see if understudy-ai/compose-summary-video 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.