Loading...
Loading...
Found 1,660 Skills
Run an autonomous Humanize-governed vLLM SOTA performance loop for one LLM model: first perform the fixed fair vLLM/SGLang/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches vLLM code, optionally uses ncu-report-skill for kernel evidence, and revalidates until vLLM matches or beats the best observed framework under the same workload and SLA.
Scaffold the test framework and CI/CD pipeline for the project's engine. Creates the tests/ directory structure, engine-specific test runner configuration, and GitHub Actions workflow. Run once during Technical Setup phase before the first sprint begins.
Run the full deal lifecycle from CLI — discover pipelines/stages, qualify MQLs into deals with associations, advance/reassign in bulk, hunt stalled deals, and close.
Submit a code review to GitHub via the GitHub API. Use this as the final step in a code review pipeline to post review findings to a PR.
Eight-axis judgment code review for the current diff — Correctness, Simplification, Tests, Documentation, Style, Intent, Design/API, Performance (+ Coherence on metadata changes). Five-phase pipeline scope → deterministic tool battery (npx/uvx-preferred, zero-install for the JS + Python majority) → 8 parallel LLM axis reviewers → Haiku validators on sub-80 findings (verbatim rubric, ≥80 threshold) → synthesis with no-silent-drop + Conventional Comments JSONL. Every report closes with "What I did NOT check" (security → /security-review, runtime perf, flaky detection). Opt-in flags `--verify-build`, `--mutation-test`, `--reconcile`, `--apply-safe`. Public-skill posture — zero auto-install, graceful skip on missing native tools.
Triage and orchestrate code reviews. Analyzes PR intent, identifies touched surfaces, assesses risk, and routes to specialist skills. Does NOT perform detailed review - delegates to specialists. Supports full pipeline with "Review PR <number>" command.
Automatically discover CI/CD and automation skills when working with GitHub Actions, Jenkins, GitLab CI, pipelines, continuous integration, continuous deployment, or automated testing. Activates for CI/CD development tasks.
Create marketing content organized by funnel stage with content strategy, distribution plans, and SEO/AEO strategy. Use when the user says "content strategy", "marketing content", "blog post", "case study", "social posts", "content calendar", "SEO strategy", or needs to create content that drives pipeline.
Create, edit, and pipeline game assets using MeowArt, including pixel sprites, HD assets, backgrounds, UI mockups, seamless loops, texture tiles, dual-grid tilesets, background removal, pixel cleanup, simple animations, sound effects, and music/BGM generation. Use this when Codex needs to produce or refine game art or audio assets in the project, especially when selecting MeowArt commands, setting canvas sizes, choosing templates, generating music or SFX, or converting generated assets into game-ready files.
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
This skill covers implementing Software Composition Analysis (SCA) using Snyk to detect vulnerable open-source dependencies in CI/CD pipelines. It addresses scanning package manifests and lockfiles, automated fix pull request generation, license compliance checking, continuous monitoring of deployed applications, and integration with GitHub, GitLab, and Jenkins pipelines.
Decide where files live in an ML experimentation project: reusable code in `src/<pkg>/`, one `# %%` script per experiment in `experiments/`, design notes + index in `journal/`, reports in `reports/`, agent-only probes in `scratch/`, narrative digest in `overview/summary.md`. Owns the layout, the file-creation rules (one file per experiment, ask before editing), and the jupytext `# %%` script convention. Never imposes `data/` — the user owns that. TRIGGER — any of: - Starting a new ML project / scaffolding a workspace. - About to create the first experiment file in a project. - About to create `src/<pkg>/data.py` / `features.py` / `pipeline.py` / `evaluate.py` for the first time. - About to write a `.ipynb` for experimentation — redirect to a `# %%` script under `experiments/`. - User asks where something should live, how to organize the project, or how to set up the workspace. - About to add a new experiment iteration — decide new file vs edit existing (ask the user). SKIP when: the file is clearly part of an already-populated module (e.g., adding a function to existing `features.py`); pure refactor inside a single existing file; pipeline declaration mechanics (`build-ml-pipeline`); evaluation mechanics (`evaluate-ml-pipeline`); skore symbol lookup (`python-api`). HOW TO USE: **first run the Detection table** below — if any signal matches, glue to existing conventions (do not rename or move folders). If no signal matches, scaffold the default layout. **Emit the Pre-flight checklist as visible text and read the Stop conditions before any file is created or edited.** Use templates in `templates/`; copy and adapt, do not rewrite from scratch.