Packs

3 packs

GitHub project operations with quality gates

4 skills · pack

@pwdev-solucoes

Stack-agnostic UI/UX engineering v2.0 — 6 real subagents, 5-phase workflow with gates, Figma integration, WCAG 2.1 AA, audit hooks

10 skills · pack

Sam Superpowers

Fork of obra/superpowers 5.0.7: the 14 core skills (TDD, debugging, collaboration patterns) with the mandatory-gate SessionStart injection replaced by a short judgment-based router. Skills are tools, not gates.

14 skills · pack

Results for “gates”

183 skills

Extract a bounded part of the invoking codebase into a new GitHub repository with private and public-OSS readiness gates

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

iamanacarolinarezende

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

release-marketingclaw-ci

Run, watch, debug, and summarize MarketingClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

agent-validation-v430

Agent validation v4.3.0 — Make agents act effectively by disabling harmful actions, lowering gates, and injecting cross-run learning

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Enforces evidence-based completion claims and rigorous code review practices, including receiving feedback, requesting reviews, and verification gates.

Design or repair a CI/CD pipeline with well-ordered parallel stages, lockfile-keyed caching, quality gates, and build-once artifact promotion.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

project-initialization

`analysis-agent`/`task-agent`/`review-agent`: use for structure, workspace or package bootstrap, config, scripts, or quality gates; skip without an initialization decision.

Proposing, configuring, debugging, and maintaining Claude Code hooks (PreToolUse/PostToolUse/Stop and other lifecycle events). Use for workflow automation or quality gates via hooks.

`analysis-agent`/`task-agent`/`review-agent`: use when CI/CD checks, artifacts, deployment gates, IaC, or Helm behavior changes; skip when pipelines are unaffected.

johnalbertini14-glitch

Interact with Jira issues, sprints, and workflows through a CLI or MCP backend, with safety checks and approval gates.

prince2-documentation-map

Map the PRINCE2 management products and project documentation needed by process, including startup, initiation, stage control, product delivery, stage boundary, direction gates, and closure.

bmad-testarch-ci

Scaffold CI/CD quality pipeline with test execution. Use when the user says "lets setup CI pipeline" or "I want to create quality gates"

dynamic-workflow-mode

Design task-local harnesses, eval gates, and reusable skill extraction for adaptive agent workflows.

hoangnguyen0403

Configure Python tooling, dependency surfaces, static analysis, and verification gates. Use when editing `pyproject.toml`, `requirements.txt`, `pytest.ini`, `ruff`, `pyright`, CI, or Python release checks.

sakamoto-family-smile

hipaa-compliance

Guides HIPAA-specific healthcare privacy and security work, routing to implementation and review skills with decision gates and guardrails.

Guides setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.

frontend-design

Improve the visual design of a frontend by restyling components one at a time, with approval gates and no functional changes.

verification-before-completion

Enforces running verification commands and confirming output before claiming work is complete, fixed, or passing, to prevent false success claims.

create-and-cleanup-migration

Drive end-to-end Convex production migrations with explicit safety gates for destructive operations and cleanup.

AI QA and evaluation specialist for quality gates. Use when the user asks to talk to Moody, requests AI evaluation, or needs regression tests for AI systems.

outreach-draft-pipeline

Generates and delivers all outreach for OUTREACH_READY leads. Automated delivery via Chrome DevTools MCP -- email, LinkedIn, Instagram. Gig leads auto-applied on platform. No approval gates.