surogates

In the author's own words, from each skill's SKILL.md.

• subagent-task-orchestrator

  Decomposition playbook and anti-temptation rules for an orchestrator agent that routes work through the Surogates subagent task layer. Pair this skill with an AgentDef whose tool filter strips the implementation tools (terminal, file, web, code) — that's how 'don't do the work yourself' is enforced structurally, not just behaviorally.

  skills/kanban/subagent-task-orchestrator/SKILL.md on GitHub (opens in a new tab)

• subagent-task-worker

  Pitfalls, examples, and edge cases for workers executing a Surogates subagent task. Loaded automatically when the dispatcher spawns a session bound to a Task (Session.task_id is set).

  skills/kanban/subagent-task-worker/SKILL.md on GitHub (opens in a new tab)

• brainstorming

  Agree the design of a large, open-ended build with the user before building it.

  skills/process/brainstorming/SKILL.md on GitHub (opens in a new tab)

• dispatching-parallel-agents

  Split 2+ independent investigations or tasks across sub-agents (delegate_task) and merge the results.

  skills/process/dispatching-parallel-agents/SKILL.md on GitHub (opens in a new tab)

• executing-plans

  Carry out an existing written implementation plan step by step with checkpoints.

  skills/process/executing-plans/SKILL.md on GitHub (opens in a new tab)

• writing-plans

  Turn an agreed spec for a large multi-step build into a step-by-step implementation plan.

  skills/process/writing-plans/SKILL.md on GitHub (opens in a new tab)

• writing-skills

  Create or edit a skill (SKILL.md) when the user asks for one.

  skills/process/writing-skills/SKILL.md on GitHub (opens in a new tab)

• consolidate-memory

  Clean up memory (merge duplicates, fix or remove stale entries) when the user asks.

  skills/productivity/consolidate-memory/SKILL.md on GitHub (opens in a new tab)

• doc-coauthoring

  Co-write a long structured document (proposal, spec, decision doc) with the user over several rounds, when they want to collaborate on it.

  skills/productivity/doc-coauthoring/SKILL.md on GitHub (opens in a new tab)

• docx

  Create, edit or convert Word documents (.docx/.dotx), including tracked changes, comments, images and formatting.

  skills/productivity/docx/SKILL.md on GitHub (opens in a new tab)

• import-memory

  Import a memory export from another assistant (ChatGPT, Gemini, Claude, ...) into memory.

  skills/productivity/import-memory/SKILL.md on GitHub (opens in a new tab)

• maps

  Geocoding, places, routes and timezones via OpenStreetMap/OSRM.

  skills/productivity/maps/SKILL.md on GitHub (opens in a new tab)

• office

  Use whenever a Word document (.docx), spreadsheet (.xlsx), slide deck (.pptx) or PDF in the workspace is to be written, filled in, edited or commented on and the office_edit tool is available: the user watches your edits appear live in the file pane, under your name, and may edit beside you. Covers drafting a document section by section, filling and formatting sheets, building slides in the Claud…

  skills/productivity/office/SKILL.md on GitHub (opens in a new tab)

• pdf-forms

  Fill PDF forms, annotate or redact a PDF, or add, remove or rotate pages.

  skills/productivity/pdf-forms/SKILL.md on GitHub (opens in a new tab)

• pdf-reading

  Read a PDF when read_file fails or returns garbled text, or for figures, layout, images, attachments or form-field values.

  skills/productivity/pdf-reading/SKILL.md on GitHub (opens in a new tab)

• pdf

  Create PDFs, or merge, split, watermark, encrypt/decrypt, extract tables/images from, or OCR existing ones.

  skills/productivity/pdf/SKILL.md on GitHub (opens in a new tab)

• pptx

  Create, edit or read PowerPoint decks (.pptx/.potx), from scratch or from a template.

  skills/productivity/pptx/SKILL.md on GitHub (opens in a new tab)

• schedule

  Create, change, pause or cancel a prompt that runs on a schedule ("every weekday at 8:30", "remind me at noon").

  skills/productivity/schedule/SKILL.md on GitHub (opens in a new tab)

• xlsx

  Create or edit spreadsheets (.xlsx/.xlsm/.csv) with formulas, formatting and charts, or clean messy tabular data into one.

  skills/productivity/xlsx/SKILL.md on GitHub (opens in a new tab)

• arbor-coordinator

  The Arbor research-coordinator protocol: the OBSERVE -> IDEATE -> SELECT -> DISPATCH -> DECIDE cycle over a durable Idea Tree. Preloaded automatically on /auto-research sessions. The coordinator never edits code or runs commands — executors do that in isolated worktrees; the coordinator steers the tree with idea_tree / dispatch_experiments / merge_experiment.

  skills/research/arbor-coordinator/SKILL.md on GitHub (opens in a new tab)

• arbor-executor

  The Arbor executor workflow: clone the repo from the git bundle your brief hands you, implement and evaluate exactly ONE hypothesis with the file tools, then report structured results via worker_complete. Preloaded automatically on arbor-executor task workers. Never touch the held-out test split.

  skills/research/arbor-executor/SKILL.md on GitHub (opens in a new tab)

• arbor-ideate

  Hard-gated ideation for an Arbor research run. Load at the START of every IDEATE round, before drafting any hypothesis. Enforces the PI mindset (mechanism over knob), the four-question first-principles probe, the kill-filter, and the four-line hypothesis format. Ported from Arbor's idea_drafting + first_principles_probe.

  skills/research/arbor-ideate/SKILL.md on GitHub (opens in a new tab)

• arbor-merge-discipline

  DECIDE-phase doctrine for an Arbor research run: when to merge, prune, combine, or finalize; how the held-out merge gate works; and the rule that the final report uses TEST scores. Load before deciding what to do with completed experiments.

  skills/research/arbor-merge-discipline/SKILL.md on GitHub (opens in a new tab)

• arbor-research

  Intake for an autonomous research run (Arbor). Use when the user wants to optimize a metric in a repo over many isolated experiments — 'optimize this benchmark', 'improve the model F1 overnight', 'beat the leaderboard'. Discovers the repo/eval/splits, measures the baseline, confirms a Research Contract, then emits a ready-to-send /auto-research command. Does NOT start the run itself.

  skills/research/arbor-research/SKILL.md on GitHub (opens in a new tab)

• shadcn

  Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".

  web/.agents/skills/shadcn/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• hiveby aden-hive Multi-Agent Harness for Production AI 11.1k stars · 24 skills
• paperclipby paperclipai The open-source app everyone uses to manage agents at work 111k stars · 30 skills
• open-code-reviewby alibaba Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, preci… 49.4k stars · 2 skills
• cogneeby topoteretes Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free 33.1k stars · 23 skills
• eigentby eigent-ai Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex 15.7k stars · 6 skills
• openrigby mvschwarz Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work. 8.6k stars · 29 skills