Runs Pi non-interactively and parses its JSON event stream for repository tasks. Use when the user asks to delegate a bounded analysis or implementation task to Pi.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add CherryHQ/cherry-studio --skill code-mate-pi --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Code Mate Pi?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/cherryhq-code-mate-pi)More formats (shields.io, HTML) on the badges page.
---
name: code-mate-pi
description: Runs Pi non-interactively and parses its JSON event stream for repository tasks. Use when the user asks to delegate a bounded analysis or implementation task to Pi.
---
# Pi
## Run
1. Set the Bash working directory to the exact project the user named and set a finite timeout, normally 10 minutes.
2. Check availability with `command -v pi`. If it is missing, stop and ask the user to install Pi in Code Mate.
3. Run one sessionless task:
```bash
pi --mode json --no-session "<prompt>"
```
Pass the prompt as one quoted argument. Parse stdout as JSONL and inspect error events; Pi can report model or tool failure in the event stream, so process exit alone is insufficient. Never start interactive Pi or `/login`.
## Authentication And Permissions
If Pi reports missing login, model, provider, or API configuration, stop and ask the user to configure Pi in Code Mate. Never request, read, print, or copy credentials.
Pi has no tool-approval prompt and normally exposes read, write, edit, and Bash tools. For analysis, append `--tools read,grep,find,ls`. Include write, edit, or Bash only when the user explicitly requested workspace changes, and keep the tool list and working directory as narrow as possible.
Example: run a read-only diagnosis with `--tools read,grep,find,ls`, then use the final JSONL message only if no error event occurred.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.