Ready to supercharge your AI agents?

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

Get Started Free →

A5c AI/Specification Writing — measured AI agent skill | DecimalAI

a5c-ai/specification-writing

SkillScore32Maintained

Write feature specifications as requirements and user stories with acceptance criteria, focusing on business value and testable conditions.

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-specification-writing

Get this skill — curl · raw file

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

Raw file: /s/a5c-ai-specification-writing/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-specification-writing.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

—+8% tokens0% turns32% of whole cases pass with skill (7/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	24%	0%
case-05	✗→✓	▲ Improved	-10%	0%
case-06	✗→✓	▲ Improved	-19%	0%
case-09	✗→✓	▲ Improved	3%	0%
case-13	✗→✓	▲ Improved	-58%	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/spec-kit/skills/specification-writing/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

Formalizing vague feature requests into structured requirements
Clarifying scope boundaries for a feature area
Establishing acceptance criteria for user stories

Key Principle

Specifications describe desired behavior from the user's perspective. They define what the system should do, not how it should be built. Business value must be explicit in every requirement.

Process

Elicit requirements - Extract functional and non-functional requirements from feature description
Write user stories - Author stories in standard format with personas
Define acceptance criteria - Testable conditions for each story (Given/When/Then)
Identify edge cases - Error scenarios and boundary conditions
Clarify gaps - Surface and resolve ambiguities and contradictions
Document assumptions - Make implicit assumptions explicit
Define scope - Clearly delineate in-scope vs. out-of-scope
Human review - Approve specification before planning

Tool Use

Invoke via babysitter process: methodologies/spec-kit/spec-kit-specification Full pipeline: methodologies/spec-kit/spec-kit-orchestrator

Want to see if a5c-ai/specification-writing 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.