Ready to supercharge your AI agents?

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

Get Started Free →

Decision Record (ADR) — measured AI agent skill | DecimalAI

archive228/decision-record

SkillScore95Maintained

Capture an architectural decision so the next session (or engineer) knows WHY. Use after any non-obvious technical choice.

Documentationby archive228

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

Automatic

Doc Ops pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/archive228-decision-record/SKILL.md

decimalai skills pull archive228-decision-record --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/archive228-decision-record/SKILL.md https://app.decimal.ai/s/archive228-decision-record/SKILL.md

Raw file: /s/archive228-decision-record/SKILL.md ↗ · machine-readable summary at /s/archive228-decision-record.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 6h ago

Yes — +82% lift-35% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-43%	0%
case-02	✗→✓	▲ Improved	-53%	0%
case-03	✗→✓	▲ Improved	-44%	0%
case-07	✗→✓	▲ Improved	20%	0%
case-08	✗→✓	▲ Improved	-41%	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 — 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

archive228 / loopkit

skills/decision-record/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Decision Record (ADR)

Write a short file docs/decisions/NNN-<slug>.md:

Context — what forced a decision. The constraints.
Options — the 2-3 real candidates, one line each.
Decision — what you picked, dated.
Why — the tradeoff. What you gave up. "We picked Postgres over Mongo because we need real joins; we accept heavier ops."
Consequences — what this now makes easy and hard.

Hard-to-reverse choices (schema, auth, data store) MUST get one. Future-you will ask "why on earth did we do this" — answer it now.

Want to see if archive228/decision-record 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.