Ready to supercharge your AI agents?

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

Deploy · ccplugins | DecimalAI

devopsby ccplugins

Deploy

ccplugins/deploy

Source ccplugins/awesome-claude-code-plugins ↗License Apache-2.0

Use when the user says "ship it", "ready to push", "release", "deploy", or wants pre-push gates (lint, typecheck, build, tests) plus commit/release/push in one flow. Standalone — never auto-invoked; push always requires explicit confirmation.

SkillScore70Maintained

Automatic

DevOps & SRE pack

Last verified 9/24/2026

What it changes

Passed 15 of 21 test cases with the skill, and 7 of 21 without it.

Without skill33%

With skill70%

Checks it passed that the model alone missed

Scans recent commits during the security sweep.
Halts pipeline execution upon typecheck failure.
Applies the fix flag when linting initially fails.

and 13 more in the full report

13 fixed6 passed either way5 still failing3 broke

Pass-rate lift: +37 pp
Tokens: 0%
Agent turns: 0%
Response time: -61%

Model gemini-3.6-flashMeasured 9/24/2026v119 of 27 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/ccplugins-deploy/SKILL.md https://app.decimal.ai/s/ccplugins-deploy/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ccplugins-deploy, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

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

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/ccplugins-deploy/ and pins it in .decimal/skills.lock

decimalai skills add ccplugins-deploy

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

curl -fsSL --create-dirs -o .claude/skills/ccplugins-deploy/SKILL.md https://app.decimal.ai/s/ccplugins-deploy/SKILL.md

Raw file: /s/ccplugins-deploy/SKILL.md ↗ · machine-readable summary at /s/ccplugins-deploy.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

Gate B reported 1 TypeScript error `TS2322: Type 'string' is not assignable to type 'number'`. Should the pipeline run `tsc --fix` or dispatch an automated worker to patch the file and re-run typechecking?

What was checked, without and with the skill
Checked	Without skill	With skill
Refrains from auto-fixing type errors in Gate B.	Passed	Passed
Halts pipeline execution upon typecheck failure.	Missed	Passed

case-23 · gemini-3.6-flash · 9/24/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md118 linessingle file

Deploy

No gate skipped, no failure ignored. If any gate fails, halt and report. Never --no-verify. Never bypass.

Step 1 — Survey State

git status — track uncommitted changes for the commit step
git log origin/<branch>..HEAD --oneline — what's ahead
Detect package manager and project type from .hyperflow/profile.md and root files

Step 2 — Quality Gates (halt on first failure)

Run gates in order. Print Gate <n> — <name> before each.

Gate A — Lint

Dispatch Implementer — running lint.

Detect — npm run lint / pnpm lint / bun run lint / yarn lint / eslint .
On failure — auto-fix via --fix, re-run once. Still failing → halt.
Skip silently if no lint script.

Gate B — Typecheck

Detect — tsc --noEmit / npm run typecheck / project-specific
Skip silently if not a typed project. Halt on failure (no auto-fix).

Gate C — Build

Detect — npm run build / pnpm build / bun run build
Skip silently if no build script. Halt on failure.

Gate D — Tests

Detect runner from .hyperflow/testing.md (vitest, jest, playwright, pytest, etc.)
Run full suite — not just affected. Halt on failure.

See quality-gates.md for gate details.

Step 3 — Security Sweep

Track record

Benchmark

15 / 21

test cases passed, vs 7 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/17/2026

View 15 scanner checks

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

ccplugins / awesome-claude-code-plugins

plugins/hyperflow/skills/deploy/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/17/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Deploy

Step 1 — Survey State

Step 2 — Quality Gates (halt on first failure)

Step 3 — Security Sweep

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills