tmux for coding agents - detached sessions, send-keys input injection, capture-pane polling with a race-free sentinel, formats, completion detection, control mode, and a pitfall checklist
Plugin tmux from marketplace 365-skills in Agents365-ai/365-skills. Commands read from the repo's manifest — 10 days ago.
tmux-skillUse tmux from the command line to run, drive, and monitor terminal programs as a coding agent (detached sessions, send-keys input injection, capture-pane output polling, formats, completion detection, and control mode). Use when a task needs long-running or interactive processes (builds, tests, serv
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
The diff pane as a plugin: /diff opens the session's uncommitted changes beside the transcript, file by file with their hunks, refreshed as Claude edits and runs commands; the first edit opens it where the terminal is wide enough, and a file's ask button rides its hunks on the next prompt.
MCP server for terminal commands, process management, and file operations across text, code, PDF, DOCX, Excel, images, and structured data.
6 skills · 1 MCP server
MCP server for terminal commands, process management, and file operations across text, code, PDF, DOCX, Excel, images, and structured data.
6 skills · 1 MCP server
MCP server for terminal shell commands, process management, and file operations across text, coding, PDF, DOCX, Excel, images, and structured data
6 skills · 1 MCP server
Reviews hires and terminations for jurisdiction-specific risk flags, classifies workers against the controlling state test, tracks leave deadlines before they're missed, runs internal investigations, and drafts policies with state supplements where the law differs.
20 skills · 1 agent · 2 MCP servers
Multi-agent orchestration grounded in an LLM wiki. /dev-loop:orchestrate splits one goal into a dependency graph of parallel Claude Code sessions, each in its own worktree, and supervises them natively on Orca (a tracked Task + Dispatch per phase, pushed worker_done / question / escalation events instead of polling, stall detection; raw tmux fallback). Every plan decision must cite a page in a bundled best-practice wiki of 400+ pages across 10 domains, checked by machine gates and a fresh-context plan reviewer. Insights from your sessions are queued and turned into reviewed wiki PRs when you run /dev-loop:knowledge-flush (automatic flushing is opt-in and never bypasses permission checks).
9 skills · 11 agents · 1 MCP server · hooks
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.