Loading...
Loading...
Found 9,634 Skills
Unified review skill — auto-detects plan or code, assembles the right panel, runs a bounded review-fix loop with severity gating. Use when a plan or implementation needs review.
Meeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要".
Grow a component package into a high-quality, sourceable reusable design in Zener. Use when translating a datasheet, application note, or eval design into circuitry that should live with the component package itself — including checking for existing reusable packages first, extracting evidence, choosing sourceable passives, documenting the design in the `.zen` docstring, and validating with `pcb build`.
Canonical Zener HDL semantics, package rules, manifests, and high-value stdlib APIs. Covers `Module()`, `io()`, `config()`, imports, `pcb.toml`, `pcb.sum`, stdlib interfaces and units, and package APIs.
Prepare and, after explicit approval, publish social posts through the PostPlus platform-owned Postiz workspace.
Research the codebase to answer questions. Search for relevant files, gather context, and provide clear answers.
Implement one task or scoped change: make the change, add valuable tests, and verify it works.
Stage changes, draft conventional commit messages, and commit with user confirmation. Use when user types /commit, asks to commit changes, or mentions creating a git commit.
Discover and use shared team skills stored in PostHog. Use when the user asks to list, browse, load, or manage "shared skills", "team skills", or references the "skills store" / "skill store".
Create Git commits with Conventional Commits analysis, safe staging, and concise message generation. Use when the user asks to commit changes or create a git commit.
Use prefered practices when using git. Use when Codex needs to perform actions with git or Github.
Submit or run an ML experiment on a compute environment (local, SLURM HPC, RunAI/Kubernetes). Use when the user wants to launch a training run, submit a job, run ablations, or execute an experiment script on any compute cluster.