Run the DQIII8 quality pipeline — format (Black), imports (isort), lint (ruff), tests (pytest), security scan. Used internally by checkpoint and pre-commit flows.
Scanned 6/6/2026
Install via CLI
openskills install senda-labs/DQIII8---
name: quality-gate
description: Run the DQIII8 quality pipeline — format (Black), imports (isort), lint (ruff), tests (pytest), security scan. Used internally by checkpoint and pre-commit flows.
command: /quality-gate
allowed-tools: [Bash]
user-invocable: false
---
# /quality-gate — On-Demand Quality Pipeline
Run the DQIII8 quality pipeline for a file or directory scope.
## Usage
```
/quality-gate [path|.] [--fix] [--strict]
```
- Default target: current directory (`.`)
- `--fix`: allow auto-format/fix where supported (Black, isort)
- `--strict`: treat warnings as errors
## Pipeline
Run these phases in order. Stop on first failure unless `--strict` is passed.
### Phase 1 — Format (Black)
```bash
black --check [path] 2>&1 | tail -15
# With --fix:
black [path]
```
### Phase 2 — Imports (isort, if installed)
```bash
isort --check-only [path] 2>&1 | head -10
# With --fix:
isort [path]
```
### Phase 3 — Lint (ruff)
```bash
ruff check [path] --select E,F,W 2>&1 | head -30
```
Fail on E and F codes. W codes: report only.
### Phase 4 — Tests (pytest)
```bash
python3 -m pytest tests/ -x -q --tb=short 2>&1 | tail -20
```
With `--strict`: fail on warnings too (`-W error`).
### Phase 5 — Security Quick-Scan
```bash
grep -rn "shell=True" [path] --include="*.py" | grep -v "#\|test_"
grep -rn "f['\"].*SELECT\|f['\"].*INSERT\|f['\"].*DELETE" [path] --include="*.py"
```
Both must return empty.
## Output Format
```
QUALITY GATE — [path]
=====================
Phase 1 Format: PASS
Phase 2 Imports: PASS / SKIP (isort not installed)
Phase 3 Lint: PASS / FAIL — 3 errors
Phase 4 Tests: PASS — 12 passed in 0.8s
Phase 5 Security: PASS
RESULT: PASS / BLOCKED
```
## When to Run
- Before every commit
- After `python-specialist` hands off code
- After refactoring (in place of running phases manually)
- As part of `/checkpoint create` flow
## Related
- `verification-loop` skill — more detailed phase-by-phase protocol
- `tdd-workflow` skill — write tests before running this
- `security-review` skill — deeper checklist for auth/secrets code
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.