Ready to supercharge your AI agents?

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

A5c AI/Constitution Creation — measured AI agent skill | DecimalAI

a5c-ai/constitution-creation

SkillScore35Maintained

Establish project governing principles including dev guidelines, code quality standards, testing policies, UX requirements, performance benchmarks, and security constraints.

by a5c-ai

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

Automatic

Project Management pack

decimalai skills pull a5c-ai-constitution-creation

Get this skill — curl · raw file

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

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

23 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

Yes — +22% lift-11% tokens0% turns35% of whole cases pass with skill (8/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-12%	0%
case-19	✗→✓	▲ Improved	-13%	0%
case-20	✗→✓	▲ Improved	-69%	0%
case-21	✗→✓	▲ Improved	-69%	0%
case-22	✗→✓	▲ Improved	-49%	0%

Showing 5 of 23 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/constitution-creation/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

Formalizing existing project standards into a constitution
Updating governance principles for an evolving project
Before writing specifications for a new feature area

Distinction from Specification

Constitution: Defines project-wide governance (HOW the project operates)
Specification: Defines feature-level requirements (WHAT to build)

Process

Gather context - Assess project type, audience, compliance needs, existing standards
Define dev guidelines - Coding standards, branching strategy, review process
Set code quality standards - Linting, formatting, complexity limits, naming conventions
Establish testing policies - Coverage thresholds, test types, CI requirements
Specify UX requirements - Accessibility, responsiveness, performance budgets
Define performance benchmarks - Load times, throughput, memory limits
Establish security constraints - Auth, data handling, vulnerability policies
Document architecture principles - Modularity, dependencies, extensibility
Human review - Approve constitution before proceeding

Tool Use

Invoke via babysitter process: methodologies/spec-kit/spec-kit-specification (constitution phase) Full pipeline: methodologies/spec-kit/spec-kit-orchestrator

Want to see if a5c-ai/constitution-creation 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.