433 tagged pi, measured the same way as everything else here.
Browse within: coding-agent 179pi-coding-agent 113harness 79gemini 69coding-agents 66effect 53explicit 53patterns 53rules 53agent 48pi-agent 48addons 39opencode 39packages 39
Skill Claude CodeCodex
How to write modern Swift well — modeling with value types, Swift 6 data-race safety and approachable concurrency (@concurrent, main-actor-by-default, actors, task groups), protocols and generics (some vs any), API design, performance and ARC, Swift Testing, macros, and the modern language features agents don't know…
Skill Claude CodeCodex
Operate pi-subagents jobs safely, including direct-work decisions, least-privilege tools and attachments, thinking levels, delegation, bidirectional messaging, parallel starts, timeouts, waiting, cancellation, result handling, verification, and writer isolation.
Skill Claude CodeCodex
Create or update Agent Skills (SKILL.md plus optional scripts, references, or assets). Use when someone asks to design a new Agent Skill, refine an existing one, or structure skills for Pi discovery, packaging, or other Agent Skills-compatible clients.
Skill Claude Code
Supervise shell commands and bounded task output from Python host calls to Jev TypeScript programs, with explicit optional typed decisions. Use for foreground/background shell workflows, semantic routing, verification, and per-turn advisors without a reasoning-model turn per event.
Skill Claude CodeCodex
Use when a user's request is vague, ambiguous, or underspecified. Runs recon-first clarification — codebase exploration before questions, then one bundled question round with defensible defaults — and outputs a Goal Contract for the durable /goal runtime. Triggers on "I want to...", "I need...", "let's build...", "can…
Skill Claude CodeCodex
Read this skill if you see {# FOLDED} markers in your context (e.g. {#3f9a2c FOLDED}), or if earlier parts of your context look summarized. Accordion is a desktop tool that may compact older context blocks to keep you under a token budget. The unfold tool restores a folded block (open from your next turn); the recall…
Skill Claude CodeCodex
Gym mode for agentic coding. When active, hands off implementation exercises to the human instead of completing them. Tracks difficulty and reviews submitted work.
Skill Claude CodeCodex
Plan this week's budget split between projects from the portfolio snapshot and priorities.md, then report it to the operator.
Skill Claude Code
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
Skill Claude CodeCodex
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.
Skill Claude CodeCodex
Use when executing implementation plans with independent tasks in the current session.
Skill Claude CodeCodex
Create distinctive, crafted TUI components for pi using @mariozechner/pi-tui and @mariozechner/pi-coding-agent. Use when building interactive terminal UIs — custom components, overlays, dialogs, dashboards, widgets, data visualizations, animated elements, game-like interfaces, or any visual TUI work inside pi…
Skill Claude CodeCodex
Plan delegation with the task tool: complete handoffs, reviewer context, parallel work, and task resumption.
Skill Claude CodeCodex
Standalone persistent memory for Pi — smart search, symbol clustering, dedup, auto-recovery, trust scoring. Zero Python dependency.
Skill Claude CodeCodex
Use askuser as a decision, research, and requirements gate before ambiguous or high-stakes choices.
gvkhosla/compound-engineering-pi
Skill Claude CodeCodex
Fetches and analyzes GitHub issues to surface recurring themes, pain patterns, and severity trends. Use when understanding a project's issue landscape, analyzing bug patterns for ideation, or summarizing what users are reporting.
Skill Claude Code
Plan, draft, and execute Exa deep-research workflows. Use when the user wants staged research planning, cost-aware discovery before deep synthesis, or an explicit deep-research report. Also use when the user asks to refine a research question, compare options, explore a market or technical landscape, gather sources…
Skill Claude CodeCodex
Build typed HTTP APIs with Effect's HttpApi — endpoints with schemas, handlers, security middleware, OpenAPI docs, derived clients, and handler unit tests. Use when building HTTP servers, REST APIs, or typed HTTP clients with Effect v4.
Skill Claude CodeCodex
Set up and run an autonomous experiment loop for any optimisation target. Use when asked to run autoresearch, optimise a workload in a loop, or start experiments.
Skill Claude Code
Use when checking whether an IronLint adapter still matches its coding harness's current contract — auditing adapter/harness drift, verifying hook payload shapes, plugin manifest schemas, lifecycle events, or tool names are up to date, or doing periodic adapter maintenance. Takes a harness name (claude-code, codex…
Skill Claude CodeCodex
Explain Outfitter and help users compose, inspect, and maintain .agents resources, agents and their loadouts, personas, skills, and settings. Use when a user asks about Outfitter itself — the .agents protocol, agent profiles and personas, catalogs, skills, state persistence, launch configuration — or asks to set up…
Skill Claude CodeCodex
Multi-agent workflow (tracer/resolver/bypass) for secure code review, exploitability triage, and PoC validation in codebases. Use when conducting structured security research or penetration test analysis.
Skill Claude CodeCodex
Navigating LLM tooling workflows. Use when choosing recall, search, SQLite, MCP, secret-safety, or skill validation tools.
Skill Claude CodeCodex
Amends and extends the live run narrative one beat at a time while a deadreckon run is in flight. Output is one JSON object.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: