osolmaz

Remove AI writing tells from prose, headings, openings, and page structure. Use when writing or editing anything meant to read as human-written, including blog posts, site copy, documentation, README text, reports, PR descriptions, and emails. Trigger when…

Use when preparing or updating an implementation plan, documentation, or specification before implementation, including choosing the right repository and applying SimpleDoc conventions.

Use when the user asks to implement a plan end-to-end, test it, run Pi Reviewer against the base branch in a loop until no P0/P1 issues remain, and make sure CI/CD is green before finishing.

Use alongside pi-coding-agent whenever proposing, designing, implementing, reviewing, or debugging a change to Pi behavior through extensions or packages, especially when deciding between a public extension API and Pi core, or when the request asks for an…

Use for any task involving the Pi coding agent, including browsing or installing Pi packages; creating, reviewing, testing, or debugging extensions; managing skills, prompts, themes, settings, sessions, models, providers, SDK integrations, TUI components,…

Use when asked to browse, search, identify, summarize, or verify X/Twitter posts or tweets; find a post the user remembers; inspect a recent discussion or claim from X; or use Onur's private xTap browsing corpus as a source for latest information. Searches…

Use before starting, smoke-testing, benchmarking, compiling, or recovering local LLM inference runtimes such as vLLM, SGLang, llama.cpp, TensorRT-LLM, Ollama, LM Studio CLI, FlashInfer, or modelopt-backed servers. Prevents local OOM incidents through target…

Use when calling, reviewing with, or delegating work to another coding agent through the ACPX CLI, including explicitly human-requested Claude Fable through the default local Claude adapter or an explicitly requested Cursor adapter, one-shot and persistent…

Records or updates an existing selected plan in canonical documentation without implementing it. Use only when the user explicitly asks to run autodoc.

Implements an existing plan end to end, tests it, runs pi-reviewer until no P0/P1 issues remain, and verifies CI/CD. Use only when the user explicitly asks to run autoimplement.

Compares practical solutions with the ideal end state, selects the best in-scope option, and produces an implementation plan. Use only when the user explicitly asks to run autoplan.

Use when creating, reviewing, debugging, starting, inspecting, or controlling pi-workflows; authoring .workflow.ts files; using the workflow tool; handling workflow step contracts, checkpoints, updates, or progress; or deciding how a task should compose…

Use when the user asks for a read-only sanity check of a repository contribution, including whether it is necessary, duplicates existing code, adds justified contracts, or has proportionate scope and tests. Starts the built-in sanity-check workflow and…

Use when the user asks to monitor, watch, track, or periodically check a running command, remote Job, CI run, deployment, publication, or other long-running goal. Starts the built-in Pi monitor workflow immediately and finishes the authorized goal through…

Use unYOLO for GitHub repositories, pull requests, explicit administrator merges, issues, reviews, comments, checks, workflows, releases, and other GitHub API operations when gh-broker is installed. Use instead of gh auth, GH_TOKEN, GITHUB_TOKEN, personal…

Use unYOLO for Hugging Face Hub Git, repositories, datasets, models, Spaces, inference, grants, and typed Hub operations when hf-broker is installed. Use instead of exposing, retrieving, or configuring a Hugging Face access token.

Use unYOLO for approved Unix privilege and identity transitions when sudo-broker is installed. Use for privileged, sudo, root, run-as-user, or cataloged host command requests instead of invoking sudo, su, doas, pkexec, or unrestricted shell escalation…

Alpha test skill

Beta test skill

Skillflag producer/installer usage and install guidance (requires skill-install).

Sync Janitr experiment artifacts from remote to local and publish to Hugging Face experiments repo with single-index and manifest validation.

Create or update documentation in this repo following SimpleDoc conventions. Use when creating docs, plans, logs, or any markdown files.

Use when running Schemator to extract, review, simplify, converge, diff, or report on data models, JSON schemas, API payloads, SQL tables, migrations, TypeScript interfaces, YAML resources, or other field-based schemas.

Use when preparing, publishing, or reviewing a final Schemator run report. Ensures the report includes raw artifacts, schema JSON, source details, decisions, verification, and push links instead of only a narrative summary.

Use when an agent should open, inspect, or monitor a single GitHub issue or pull request with the ghzinga terminal UI.

Create or update documentation in this repo following SimpleDoc conventions.

Use when launching a tmux grid of concurrent localpi Pi demo sessions for live demonstrations, load demos, screen-filling demo walls, side-by-side model output comparisons, or when recording such a demo to video. Triggers include requests to demo localpi,…

Explain ghreplica and teach how to use the ghr CLI for mirrored GitHub reads, git-change inspection, overlap search, text search, and structural code search.

Translation style guide for German (de) and Alman (al) content in the Alman repo. Use when translating, reviewing, or editing any German or Alman text — site pages, spec i18n blocks, UI strings, or examples.

Explain prtags and guide the CLI and API usage for groups, annotations, field definitions, and group-read behavior. Use when work is specifically about prtags behavior or the prtags side of a ghreplica-integrated workflow.