Ready to supercharge your AI agents?

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

Get Started Free →

synthesize-brief — measured AI agent skill | DecimalAI

understudy-ai/synthesize-brief

NewSkillScoreMaintained

Turn context findings into a summary packet and short brief.

by understudy-ai

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

Automatic

Research pack

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

pip install decimalai

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

decimalai skills pull understudy-ai-synthesize-brief --out .claude/skills/

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 ↗

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

26 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

Yes — +27% lift-48% tokens0% turns69% of whole cases pass with skill (18/26)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-10	✗→✓	▲ Improved	-62%	0%
case-11	✗→✓	▲ Improved	-71%	0%
case-13	✗→✓	▲ Improved	-55%	0%
case-14	✗→✓	▲ Improved	-62%	0%
case-15	✗→✓	▲ Improved	-37%	0%

Showing 5 of 26 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/synthesize-brief/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

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.

Want to see if understudy-ai/synthesize-brief 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.