Ready to supercharge your AI agents?

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

Get Started Free →

target-brief-studio · understudy-ai | DecimalAI

Registry skillby understudy-ai

target-brief-studio

understudy-ai/target-brief-studio

Source understudy-ai/understudy ↗License MIT

Hand-written end-to-end playbook for a reusable target brief workflow.

SkillScore82Maintained

Automatic

Research pack

Last verified 8/19/2026

What it changes

Passed 17 of 21 test cases with the skill, and 4 of 21 without it.

Without skill18%

With skill82%

Checks it passed that the model alone missed

Outputs draft.mp4 as the required video asset
Produces draft.mp4 as the required video output
Generates delivery/preview.json for the final payload

and 15 more in the full report

14 fixed4 passed either way4 still failing0 broke

Pass-rate lift: +64 pp
Tokens: -7%
Agent turns: 0%
Response time: -44%

Model gemini-3.6-flashMeasured 8/19/2026v118 of 22 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

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

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add understudy-ai-target-brief-studio, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

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

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/understudy-ai-target-brief-studio/ and pins it in .decimal/skills.lock

decimalai skills add understudy-ai-target-brief-studio

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

If initial baseline context collection fails due to a network timeout when inspecting target MedTech Global, what retry policy is configured for that step?

What was checked, without and with the skill
Checked	Without skill	With skill
Applies retry_once policy to the initial context collection step	Missed	Passed

case-18 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md45 linessingle file

target-brief-studio

Goal

Produce a delivery-preview-ready first-pass target brief package.

Inputs

targetName
analysisFocus

Child Artifacts

collect-target-context
explore-unfamiliar-target
synthesize-brief
render-brief-assets
compose-summary-video
prepare-delivery-preview

Stage Plan

[skill] collect-target-context -> Collect baseline context | inputs: targetName, artifactsRootDir | outputs: target.json, context.md | retry: retry_once
[worker] explore-unfamiliar-target -> Explore the unfamiliar target | inputs: targetName, artifactsRootDir, analysisFocus | outputs: findings.md, highlights.json, limitations.json, worker-summary.json | retry: pause_for_human | budget: maxMinutes=12
[skill] synthesize-brief -> Convert findings into a summary packet | inputs: findings.md, highlights.json, limitations.json, context.md | outputs: summary.json, brief.md | retry: retry_once
[skill] render-brief-assets -> Render the cover and summary-card images | inputs: target.json, summary.json, brief.md | outputs: cover.png, summary-card.png | retry: retry_once
[skill] compose-summary-video -> Render the draft summary video | inputs: cover.png, summary-card.png, screenshots/*, brief.md | outputs: draft.mp4 | retry: retry_once
[skill] prepare-delivery-preview -> Assemble the delivery preview payload | inputs: target.json, brief.md, draft.mp4, cover.png | outputs: delivery/preview.json | retry: retry_once
[approval] delivery-preview -> Wait for human approval before delivery | outputs: approval.state | approval: delivery_preview

Output Contract

draft.mp4
delivery/preview.json
summary.json
brief.md

Approval Gates

Human review before delivery

Track record

Benchmark

17 / 21

test cases passed, vs 4 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

View 15 scanner checks

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/target-brief-studio/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

target-brief-studio

Goal

Inputs

Child Artifacts

Stage Plan

Output Contract

Approval Gates

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills