PR-first adversarial code review for Codex. Use after implementation or refactorpass on an open draft PR, especially when the user asks to critique, review hard, find bugs, or run the platform review chain. Posts verified findings inline before fixing, then…
loomantix/codex-platform
SkillsMP has collected 17 skills from loomantix/codex-platform. Open a skill to review its source and details.
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 17
- GitHub stars
- 2
- GitHub forks
- 0
Skills in this repository
Showing 17 of 17 collected skills.
High-fidelity PR-first Codex review chain that opens or reuses a draft PR, records verified findings inline before fixes, and runs critique deep — preceded by refactorpass on this engine's first pass only. Rounds 3+ run in convergence mode. Runs only when the…
Post-push AI review orchestrator for pull requests. Use when the user asks Codex to run AI review on a PR, address Gemini or Copilot findings, dedupe reviewer comments, push fixes, reply in PR threads, or complete the platform review chain. Both modes fire…
PR-first cleanup pass for Codex. Use when the user asks for refactoring, cleanup, simplification, or the platform review chain on an open draft PR. Posts verified cleanup suggestions inline before editing, skips docs/config-only changesets, runs a structured…
Cross-engine deep review of an existing PR. Run when you want a second engine's deep adversarial pass on a PR another engine (or you) already opened — typically after the authoring engine's own critique/reviewit. Runs the deep review matrix on the PR diff,…
Autonomous issue implementation loop with strict issue allowlisting, one linked worktree per issue, draft-PR-first local Codex and Claude review hooks, inline finding traceability, bounded convergence, and fresh-base validation. Use when Codex should…
GitHub issue workflow — ready queue with dependency resolution, claim, start, close, link
Disciplined diagnosis loop for hard bugs and performance regressions. Use when something is broken, throwing, failing, flaky, or slow, or when the user says debug, diagnose, or "why is this happening".
A relentless pre-code interview that stress-tests a plan or design until nothing is silently assumed. Use when the user asks to grill an idea, pressure-test a design, or work out what to build before any code exists.
Prepare, bootstrap, publish, and verify npm package releases with GitHub Actions Trusted Publishing or a tightly gated first manual publication. Use when Codex needs to create or harden an npm release workflow, configure npm package trust and GitHub…
Mark an approved draft pull request ready, merge it into a staging base branch, mark linked issues as on-staging, fast-forward the local staging reference checkout, and post a short Google Chat notification. Use when the user asks to ship, merge, or deploy a…
Audit an org's GitHub Actions minute consumption — build a month-over-month minutes-by-repo matrix from the billing usage API, attribute a spike to repos and workflows, and surface concrete cut opportunities. Use when an Actions/billing alert fires or you…
Prepare and refine a GitHub backlog for autonomous agent-loop completion—assess each open issue against the agent-readiness rubric, rewrite agent-shaped issues with acceptance criteria and file/out-of-scope pointers, tag dev: agent, classify exclusions with…
Build a release APK from the consumer repo and install it on a tethered Android device over wireless ADB. Use for phone sideload smoke tests, including consumer-specific build env overrides documented in the consumer repo. Accepts an ADB port and optional…
Address GitHub Copilot code review comments on a PR systematically
Guided feature development with codebase understanding and architecture focus
Execute an implementation Task Packet end-to-end (code, tests, GitHub issue, PR, and closure)