Ready to supercharge your AI agents?

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

Release readiness checklist — measured AI agent skill | DecimalAI

learnprompt/release-readiness-checklist

NewSkillScoreMaintained

Inspect a small npm CLI release candidate and produce a row-by-row release-readiness checklist report with evidence, pass rules, severity, N/A policy, and a final gate. Use when the task is to review a release candidate without publishing it.

DevOpsby learnprompt

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

Automatic

DevOps & SRE pack

decimalai skills pull learnprompt-release-readiness-checklist

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/learnprompt-release-readiness-checklist/SKILL.md

Raw file: /s/learnprompt-release-readiness-checklist/SKILL.md ↗ · machine-readable summary at /s/learnprompt-release-readiness-checklist.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 3h ago

—-18% tokens0% turns83% of whole cases pass with skill (19/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-06	✗→✓	▲ Improved	37%	0%
case-08	✗→✓	▲ Improved	-24%	0%
case-10	✗→✓	▲ Improved	-32%	0%
case-11	✗→✓	▲ Improved	-55%	0%
case-13	✗→✓	▲ Improved	66%	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 — 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

learnprompt / learnprompt

research/articles/checklist-skill-design/showcase/release-readiness-checklist/fixture/.agents/skills/release-readiness-checklist/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 3 files · scripts

Skill contents

scripts/

references/

assets/

SKILL.md

Release readiness checklist

When to use

Use this skill when the user asks for a release-readiness check, release candidate inspection, pre-publish checklist, or dry-run go/no-go decision for a small npm CLI package.

Workflow

Read references/checklist-contract.md.
Run:

bash node .agents/skills/release-readiness-checklist/scripts/collect-evidence.mjs \ --expected-version 1.4.0 \ --output-json reports/release-readiness.json \ --output-md reports/release-readiness.md

Keep the generated report even if the exit code is non-zero. The point is to preserve evidence, not to stop at the first failing row.
Run npm test.
Return only the JSON object requested by the caller schema.

Boundaries

Never run npm publish.
Never edit package.json, CHANGELOG.md, or release/install-command.txt.
Do not replace checklist rows with “looks fine” prose.
If the host blocks the skill or model execution, report that block plainly instead of fabricating a pass.

Want to see if learnprompt/release-readiness-checklist 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.