Developer reference for building applications, tools, and agents on the Pi Durable agent harness (@earendil-works/pi-durable) and the pi-ai model layer. Use when writing or debugging code that imports @earendil-works/pi-durable or pi-ai: assembling a Harness over memory/SQLite/JSONL/Durable Object storage, submitting input and waiting for answers, defining tools with TypeBox schemas and structured output, calling tools from tools, hooks and guards, durable tasks with checkpoints and ownership, subagents and child tasks, documents and migrations, code mode, tool search, per-conversation environments, compaction, recovery after a crash, storage and environment conformance tests, or choosing models and providers. Also use for durable-runtime behavior questions: what survives a restart, why an input stayed queued, why a task is blocked or orphaned, how abort cascades, or what the Pico5 specification requires.
Plugin pi-durable-dev-rules from marketplace 365-skills in Agents365-ai/365-skills. Commands read from the repo's manifest — 10 days ago.
pi-durable-dev-rulesDeveloper reference for building applications, tools, and agents on the Pi Durable agent harness (@earendil-works/pi-durable) and the pi-ai model layer. Use when writing or debugging code that imports @earendil-works/pi-durable or pi-ai: assembling a Harness over memory/SQLite/JSONL/Durable Object s
Drive the Pi coding agent from Claude Code — model-agnostic delegation and code review. /pi:review with structured findings, /pi:adversarial-review, /pi:rescue, /pi:parallel-rescue, racing/fallback across providers, incremental review.
3 skills · 8 commands · 1 agent · hooks
CLI design for AI agents — evaluate, design, and refactor CLIs so they reliably serve humans, AI agents, and orchestration systems simultaneously. Structured output, self-description, delegated auth, safety tiers, and a complete 8-phase interaction loop.
1 skill
Search free commercial-use creative assets — photos, illustrations, icons, video footage, music, sound effects, and fonts across Pexels, Unsplash, Pixabay, Iconify, Freesound, Google Fonts and more, with API-backed search where available
1 skill
Ai2 Asta MCP — Semantic Scholar academic graph over MCP (no Python). Intent-to-tool routing, safe fields defaults to avoid context blowups, citation traversal, author lookup, snippet evidence retrieval, and DOI/arXiv/PMID via externalIds.
1 skill
Bilibili anime frame & character organizer — download a bangumi/UP video (or local file), extract scene-change keyframes, split scenery vs character crops (anime person detection), then either cluster everyone by CCIP identity or pull ONE character out via a reference folder (one-vs-rest, distance-prefixed matches). Agent-native JSON envelope CLI with --dry-run, --schema, stable exit codes; optional OCR+LaMa subtitle/watermark removal.
1 skill
Fetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Collect, download, export, and analyze comments on a Bilibili video (BV号 / URL / UID), producing JSONL + summary.json suitable for further analysis (sentiment, keywords, audience trends). Read-only; does not post/edit/delete.
1 skill
Context window saver for 10 coding agents. Local and free: sandboxed code execution, FTS5 search, session continuity.
3 skills · 1 MCP server
Turn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task plan (refusing vague goals with forcing questions), and a JSON-backed loop controller drives execute->verify->close with retry caps, controller-run verification (no verification theater), human escalation on exhausted budgets, and a close gate that refuses while any task is unverified or unwaived. Ships 3 stdlib Python tools, 18 committed per-domain harness manifests + JSON schema, 3 references citing the 2024-2026 agent-harness canon (Anthropic long-running harnesses, verifier's law, SWE-agent, Ralph loop, Cognition), harness-runner agent + /cs-harness command. Use when an agent or subagent should pick up a goal, define its tasks, complete and verify them, and close the loop.
1 skill · 1 command · 1 agent
Audits or prunes agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong or guidance needs slimming. Not for application bugs or PR review.
1 skill · 3 agents
Reusable agent skills maintained by YYLO. The canonical, independently versioned source for skills used by YYLO CLI and YYLO Ledger: ledger task management, wiki, workflow and artifact records, project understanding, planning, and the Ralph execution loop.
8 skills
PI Pathfinder - Finds the path through 229 plugins. Automatically picks the best plugin for your task, extracts its skills, and applies them. You don't pick plugins, PI does. Part of our initiative to update all plugins with appropriate skill sets.
1 skill
Build an AI-ready engineering system for safe coding-agent delivery and continuous software improvement.
11 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.