Ready to supercharge your AI agents?

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

Get Started Free →

synthesize-brief · understudy-ai | DecimalAI

Registry skillby understudy-ai

synthesize-brief

understudy-ai/synthesize-brief

Source understudy-ai/understudy ↗License MIT

Turn context findings into a summary packet and short brief.

SkillScore69Maintained

Automatic

Research pack

Last verified 8/19/2026

What it changes

Passed 15 of 22 test cases with the skill, and 9 of 22 without it.

Without skill42%

With skill69%

Checks it passed that the model alone missed

File generation uses shell.
The synthesis outputs brief.md.
The synthesis outputs summary.json.

and 9 more in the full report

10 fixed8 passed either way5 still failing3 broke

Pass-rate lift: +27 pp
Tokens: -48%
Agent turns: 0%
Response time: -61%

Model gemini-3.6-flashMeasured 8/19/2026v118 of 26 cases passed with skill · 22 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-synthesize-brief/SKILL.md https://app.decimal.ai/s/understudy-ai-synthesize-brief/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add understudy-ai-synthesize-brief, 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-synthesize-brief/ and pins it in .decimal/skills.lock

decimalai skills add understudy-ai-synthesize-brief

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

List all three mandatory metrics scored during step 2 of the brief synthesis process.

What was checked, without and with the skill
Checked	Without skill	With skill
The metrics scored are usefulness, polish, and first-run clarity.	Missed	Passed

case-24 · 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.md36 linessingle file

synthesize-brief

Overall Goal

Convert the exploration context into a concise verdict, summary packet, and short brief.

Inputs

findings.md
highlights.json
limitations.json
context.md

Outputs

summary.json
brief.md

Staged Workflow

Merge the baseline and exploration findings into a concise summary.
Score usefulness, polish, and first-run clarity.
Write summary.json and brief.md.

Tool Route Options

shell for deterministic file generation
memory for reusing prior scoring language

Detailed GUI Replay Hints

None. This stage should stay artifact-first and deterministic.

Failure Policy

If findings are incomplete, produce a conservative summary with explicit uncertainty notes.

Track record

Benchmark

15 / 22

test cases passed, vs 9 / 22 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/synthesize-brief/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

synthesize-brief

Overall Goal

Inputs

Outputs

Staged Workflow

Tool Route Options

Detailed GUI Replay Hints

Failure Policy

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills