Ready to supercharge your AI agents?

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

Get Started Free →

A5c AI/Brainstorming — measured AI agent skill | DecimalAI

a5c-ai/brainstorming

SkillScore57Maintained

Clarify vague requirements through exploratory questioning and option generation before committing to research or implementation.

by a5c-ai

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

Automatic

Product Management pack

decimalai skills pull a5c-ai-brainstorming

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-brainstorming/SKILL.md

Raw file: /s/a5c-ai-brainstorming/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-brainstorming.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 9d ago

—-57% tokens0% turns18% of whole cases pass with skill (4/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-09	✗→✓	▲ Improved	-59%	0%
case-14	✗→✓	▲ Improved	-79%	0%
case-17	✗→✓	▲ Improved	-74%	0%
case-21	✗→✓	▲ Improved	-1%	0%
case-01	✗→✗	＝ Same ✗	-59%	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 — 7/31/2026

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

a5c-ai / babysitter

library/methodologies/rpikit/skills/brainstorming/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v2

Skill contents

SKILL.md

New features, components, modifications
Even "simple" projects (unexamined assumptions cause wasted work)

Process

Explore project context - files, docs, recent commits
Ask clarifying questions - one at a time, prefer multiple choice
Propose 2-3 approaches - with tradeoffs and recommendation
Present design in sections - get approval after each section
Write design doc - save to docs/plans/YYYY-MM-DD-<topic>-design.md
Transition to writing-plans - the ONLY next step

HARD GATE

Do NOT invoke any implementation, write any code, or take action until design is approved.

Key Principles

One question at a time
YAGNI ruthlessly
Incremental validation
Scale sections to complexity

Agents Used

agents/code-reviewer/ - For design document review
Process agents defined in brainstorming.js

Tool Use

Invoke via babysitter process: methodologies/superpowers/brainstorming

Want to see if a5c-ai/brainstorming 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.