Dicklesworthstone

Speeds up pi_agent_rust development and verification workflows. Use when editing providers, tools, sessions, extensions, installer/uninstaller logic, or triaging regressions in this repo.

Example skill loaded from resources_discover

Discovers and executes MCP tools on-demand via agentsbox_* tools. Use when you need to find the right tool, when a user asks to use a tool you don’t have in context, or when troubleshooting MCP/tool availability.

Load and parse session transcripts from shittycodingagent.ai/buildwithpi.ai/buildwithpi.com (pi-share) URLs. Fetches gists, decodes embedded session data, and extracts conversation history.

Use `uv` instead of pip/python/venv. Run scripts with `uv run script.py`, add deps with `uv add`, use inline script metadata for standalone scripts.

Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.

Create or update Pi skills (SKILL.md plus optional scripts, references, or assets). Use when someone asks to design a new Pi skill, refine an existing one, or structure skills for Pi discovery or packaging.

Guide for extending Pi — decide between skills, extensions, prompt templates, themes, context files, or custom models, then create and package them. Use when someone wants to extend Pi, add capabilities, create a skill, build an extension, or make a Pi package.

The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interchangeable agents outperform specialized role-based systems at scale.

Jeffrey Emanuel's multi-agent implementation workflow using NTM, Agent Mail, Beads, and BV. The execution phase that follows planning and bead creation. Includes exact prompts used.

Named Tmux Manager - Multi-agent orchestration for Claude Code, Codex, and Gemini in tiled tmux panes. Visual dashboards, command palette, context rotation, robot mode API, work assignment, safety system. Go CLI.

MCP Agent Mail - Mail-like coordination layer for multi-agent workflows. Identities, inbox/outbox, file reservations, contact policies, threaded messaging, pre-commit guard, Human Overseer, static exports, disaster recovery. Git+SQLite backed. Python/FastMCP.

Converting markdown plans into beads (tasks with dependencies) and polishing them until they're implementation-ready. The bridge between planning and agent swarm execution. Includes exact prompts used.

Beads Viewer - Graph-aware triage engine for Beads projects. Computes PageRank, betweenness, critical path, and cycles. Use --robot-* flags for AI agents.

Remove telltale signs of AI-generated 'slop' writing from README files and documentation. Make your docs sound authentically human.

Find opportunities to improve web application code using TanStack libraries (Query, Table, Form, Router, etc.). Avoid man-with-hammer syndrome by applying TanStack after vanilla implementation works.

Use when reviewing causal credit assignments from ee causal ledgers to determine whether measured associations warrant promote/demote/reroute recommendations without moving causal judgment into the Rust CLI.

Use when analyzing whether different ee lab evidence, context packs, or memory interventions might have changed a coding-agent failure outcome without moving counterfactual judgment into the Rust CLI.

Use when reviewing rehearsal dry-run artifacts and producing conservative promotion checklists; requires real ee rehearse output or explicit unavailable degradation.

Use when planning active-learning experiments from ee observation ledgers, learning uncertainty reports, evaluation records, causal/economy/context evidence, or ee.skill_evidence_bundle.v1 artifacts without moving experiment-planning judgment into the Rust ee CLI.

Use when reviewing ee claim or certificate verification manifests, deciding whether a claim is persuasive, stale, overbroad, expired, assumption-bound, or missing evidence without putting qualitative judgment into the Rust CLI.

Use when reviewing pre-task risk from ee evidence matches, preflight JSON, tripwire JSON, dependency audits, project rules, destructive-command warnings, migrations, production deploys, or no-evidence/degraded preflight output before an agent acts.

Use when distilling recorder runs, curation events, procedure records, verification fixtures, or procedure exports into evidence-bound reusable procedures or render-only skill capsules without moving procedure authoring judgment into the Rust ee CLI.

Use when reviewing CASS or ee session evidence to distill observed facts, candidate memories, procedural rules, anti-patterns, and curation candidate files without moving session-review judgment into the Rust ee CLI.

Build terminal UIs with Charmbracelet (Bubble Tea, Lip Gloss, Gum). Use when: Go TUI, shell prompts/spinners, "make CLI prettier", adaptive layouts, async rendering, focus state machines, sparklines, heatmaps, kanban boards, SSH apps.

Foundation for error handling patterns. This is a base skill designed to be extended by language-specific error handling skills.

Common logging patterns and practices. This skill is designed to be included in composite skills via the 'includes' feature.

A comprehensive skill for Rust development that combines error handling, testing, and logging patterns. Demonstrates the 'includes' composition feature by merging content from multiple standalone skills.

Rust-specific error handling patterns, building on the base error handling skill. Demonstrates the 'extends' composition feature.

Common testing patterns and practices. This skill is designed to be included in composite skills via the 'includes' feature.

Craft professional README.md files for GitHub open source projects. Generates hero sections, installation instructions, feature tables, and architecture diagrams. Use when creating or revising a README, documenting a CLI tool, library, or open source project, or when user asks about README structure, badges, or project documentation.

Create OpenGraph and Twitter share images for Next.js applications using next/og ImageResponse. Generates dynamic social preview cards with gradients, SVG icons, and proper dimensions. Use when building OG images, Twitter cards, social previews, meta images, or share images for webapps.

Official skill for beads_rust (`br`), a local-first, dependency-aware issue tracker for AI agents. Use when creating issues, triaging backlogs, managing dependencies, finding ready work, updating status, or syncing to git via JSONL.

Migrate docs from bd (beads) to br (beads_rust). Use when updating AGENTS.md, converting bd commands, "bd sync" → "br sync --flush-only", or beads migration.

Replace Tokio stacks with Asupersync. Use when migrating Tokio/axum/hyper/tonic apps, designing Cx/region services, debugging internals, or classifying proof/ATP evidence.

Replace Tokio Rust stacks with Asupersync. Use when migrating tokio/axum/hyper/tonic apps, designing native Cx/region-based services, or debugging Asupersync internals.

Repo Updater - Multi-repo synchronization with AI-assisted review orchestration. Parallel sync, agent-sweep for dirty repos, ntm integration, git plumbing. 17K LOC Bash CLI.

Review GitHub issues and PRs across repositories using the ru CLI tool. Use when asked to review issues, PRs, or run ru review. CRITICAL - never stash or discard user changes; commit them first if needed.

Remote compilation helper. Use when: rch doctor, workers.toml, "no workers", "compilation slow", admission/why-not-offloaded, proof mode, fleet deploy, self-test, or offload cargo/gcc/bun.

Configure RCH workers, install hooks, fix SSH/daemon issues. Use when setting up remote compilation, adding build machines, troubleshooting rch doctor, or "no workers available".

Destructive Command Guard - High-performance Rust hook for Claude Code that blocks dangerous commands before execution. SIMD-accelerated, modular pack system, whitelist-first architecture. Essential safety layer for agent workflows.

MCP Agent Mail - Mail-like coordination layer for multi-agent workflows. Identities, inbox/outbox, file reservations, contact policies, threaded messaging, pre-commit guard, Human Overseer, static exports, disaster recovery. Git+SQLite backed. Python/FastMCP.

Beads Viewer - Graph-aware triage engine for Beads projects. Computes PageRank, betweenness, critical path, and cycles. Use --robot-* flags for AI agents.

Coding Agent Session Search - unified CLI/TUI to index and search local coding agent history from Claude Code, Codex, Gemini, Cursor, Aider, ChatGPT, Pi-Agent, Factory, and more. Purpose-built for AI agent consumption with robot mode.