docs/archive/2026-07-ai-artifacts/claude-skills/integration-pipeline-preview/06-devex-review/SKILL.md
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: 06-devex-review description: Runs the DevEx review (produce → review-quality) without a human pause; advances automatically when the review passes the rubric. kind: process executor: haiku model: claude-haiku-4-5-20251001 --- # DevEx review Produces a DevEx review
npx skillsauth add neohaskell/neohaskell docs/archive/2026-07-ai-artifacts/claude-skills/integration-pipeline-preview/06-devex-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE. Superseded by
codemap/+ rootAGENTS.md. Scheduled for deletion once the pipeline is verified (Phase 6). Manifest:docs/archive/2026-07-ai-artifacts/MANIFEST.md
Produces a DevEx review of the design draft, then independently validates that review against the DevEx quality rubric. The pipeline advances only when the rubric verdict is pass.
./01-produce/SKILL.md and follow it on the design draft at .integration-pipeline/integration-design.md and the findings at .integration-pipeline/findings-04.json + .integration-pipeline/findings-05.json. Verify: .integration-pipeline/devex-review.md exists and contains a ## Per-criterion verdicts section../02-review-quality/SKILL.md and follow it against the produced review plus the design draft. Verify: stdout contains RUBRIC: pass or RUBRIC: fail; the rubric record is written to .integration-pipeline/devex-review-rubric.json.pipeline.py complete 6 call on RUBRIC: pass. If the rubric records fail, the leaf has already refused — the orchestrator stops the pipeline at this step.Walk these steps in order. After each, run the verify check before continuing. If a verify fails, stop and surface.
RUBRIC: pass.fail, the rubric file names the failing checks and the producer step must be re-run after the issues are fixed.development
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-style-guide description: NeoHaskell coding style reference and enforcement rules. Load when writing, reviewing, or modifying any Haskell code in the NeoHaskell project. Triggers on 'NeoHaskell style', 'NeoHaskell conventions', 'how to write NeoHaskell', '
development
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-security-review description: Security & Code Quality review for NeoHaskell. Use when reviewing code changes, PRs, or architectural decisions for security implications. Evaluates OWASP, NIST, EU compliance. Handles pipeline phases 2 (ADR review) and 10 (im
development
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-qa-designer description: Testing QA Designer for NeoHaskell. Designs comprehensive test specifications with exhaustive edge cases, boundary conditions, and happy paths BEFORE implementation. Handles pipeline phase 6 (Test Spec Design). Outside-in TDD meth
development
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-performance-review description: Performance review for NeoHaskell targeting 50k req/s throughput. Use when reviewing code for performance implications, INLINE pragmas, strictness, and allocation patterns. Handles pipeline phases 3 (ADR review) and 11 (imp