GitHub collection
invergent-ai/surogates
Imported from GitHub — is this yours?
21 skills imported from this repository.
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 yo
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).
brainstorming
You MUST use this before any creative work — creating features, building components, drafting documents, designing workflows, or modifying behavior. Explores your human partner's intent, requirements, and design before any implementation begins.
dispatching-parallel-agents
Use when facing 2+ independent tasks or investigations that can be worked on without shared state or sequential dependencies — fan out to specialized sub-agents with isolated context, then synthesize the results.
executing-plans
Use when you have a written implementation plan to execute inline in the current session with review checkpoints. Prefer subagent-driven-development when sub-agent dispatch is available.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code or producing output. Turns a design into bite-sized, copy-pasteable tasks with exact paths and complete code.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment. Applies Test-Driven Development to process documentation — watch agents fail without the skill, write the skill that addresses those failures, then close loopholes.
consolidate-memory
Reflective pass over your memory — merge duplicates, fix stale facts, prune what no longer matters. Use when the user asks to clean up or review what you remember, or when memory has grown cluttered or contradictory.
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration
docx
When the office_edit tool is available and the document is in the workspace, use the office skill instead: the user watches the edit live. Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers includ
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
pptx
When the office_edit tool is available and the deck is a .pptx in the workspace, use the office skill instead: the user watches the slides arrive live. Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide
schedule
Create, change or cancel a prompt that runs on a schedule, in whatever language the user asks. Use when the user says things like "every weekday at 8:30", "în fiecare zi lucrătoare la 8:30", "each morning", "remind me at noon", or wants to reschedule, edit or stop a scheduled tas
xlsx
When the office_edit tool is available and the spreadsheet is a .xlsx in the workspace, use the office skill instead: the user watches the edit live. Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read
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 coor
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 hel
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
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.
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, confi
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 compon
Commands (1)
-
/index— Commands are user messages that start with `/`. The harness handles builtin source