Ready to supercharge your AI agents?

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

Release Check — measured AI agent skill | DecimalAI

davepoon/release-check

NewSkillScoreMaintained

Pre-release verification checklist. Validates features, tests, docs, security, and quality gates before shipping. Delegates to the Centinela (QA) agent.

by davepoon

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

Automatic

QA & Test Engineering pack

decimalai skills pull davepoon-release-check

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/davepoon-release-check/SKILL.md

Raw file: /s/davepoon-release-check/SKILL.md ↗ · machine-readable summary at /s/davepoon-release-check.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 10h ago

—-12% tokens0% turns64% of whole cases pass with skill (14/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	1314%	0%
case-04	✗→✓	▲ Improved	-17%	0%
case-05	✗→✓	▲ Improved	32%	0%
case-07	✗→✓	▲ Improved	44%	0%
case-08	✗→✓	▲ Improved	33%	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

davepoon / buildwithclaude

plugins/agent-triforce/skills/release-check/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Release Check

Runs pre-release verification using the Centinela (QA) agent. This is the highest-stakes checklist in the system.

When to Use This Skill

Before any release to production
Before tagging a version
As a final quality gate after all features are implemented and reviewed

What This Skill Does

Runs the SIGN IN checklist
TIME OUT 1 — Documentation and Debt Check: verifies CHANGELOG, TECH_DEBT, specs, and docs
TIME OUT 2 — Testing and Quality Gate: runs all tests, code health scan, quality verification
TIME OUT 3 — Security and Release Gate: runs security audit, security verification, release readiness
Writes release assessment to docs/reviews/release-check-{version}.md
Issues final verdict: READY FOR RELEASE or BLOCKED (with specific reasons)

How to Use

Basic Usage

/release-check v1.2.0

Example

User: /release-check v2.0.0

Output: A release assessment at docs/reviews/release-check-v2.0.0.md with:

Documentation completeness check
Test results and quality gate status
Security audit summary
Final verdict with specific blocking reasons if any

Tips

This is the last line of defense before code reaches users
A blocked release here prevents issues from reaching production
Three TIME OUT checkpoints cover docs, quality, and security independently

Want to see if davepoon/release-check 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.