Ready to supercharge your AI agents?

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

Get Started Free →

Policy Brief Writing · brycewang-stanford | DecimalAI

documentationby brycewang-stanford

Policy Brief Writing

brycewang-stanford/policy-brief-writing

Source brycewang-stanford/Auto-Empirical-Research-Skills ↗License NOASSERTION

Create concise policy briefs that translate research into actionable recommendations for policymakers and stakeholders.

SkillScore78Maintained

Automatic

Government & Public Sector pack

Last verified 8/8/2026

What it changes

Passed 18 of 23 test cases with the skill, and 17 of 23 without it.

Without skill74%

With skill78%

Checks it passed that the model alone missed

Identifies outlining structure and messaging as the step immediately following audience clarification.

1 fixed17 passed either way5 still failing0 broke

Pass-rate lift: +4 pp
Tokens: -17%
Agent turns: 0%
Response time: -22%

Model gemini-3.6-flashMeasured 8/8/2026v118 of 23 cases passed with skill

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/brycewang-stanford-policy-brief-writing/SKILL.md https://app.decimal.ai/s/brycewang-stanford-policy-brief-writing/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-policy-brief-writing, 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/brycewang-stanford-policy-brief-writing/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-policy-brief-writing

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

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-policy-brief-writing/SKILL.md https://app.decimal.ai/s/brycewang-stanford-policy-brief-writing/SKILL.md

Raw file: /s/brycewang-stanford-policy-brief-writing/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-policy-brief-writing.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

I am working on a policy brief regarding port automation for supply chain task forces. I already clarified my target audience and purpose. What is the next step in the standard policy brief workflow?

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies outlining structure and messaging as the step immediately following audience clarification.	Missed	Passed

case-16 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md11 linessingle file

Purpose

Guide the drafting, structuring and polishing of policy briefs targeted to decision-makers.

Workflow

Clarify purpose and audience.
Outline structure and messaging.
Draft sections with clear evidence and recommendations.
Design visuals and talking points.
Review, iterate, and prepare final deliverables.

Track record

Benchmark

18 / 23

test cases passed, vs 17 / 23 without

Adoption

Users: 2
Times used: 17

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

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

brycewang-stanford / Auto-Empirical-Research-Skills

skills/19-CuellarC05-vera-economic-intelligence/research/policy-brief-writing/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1

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