Skip to content
Productivity
Skill

/usecase-figure-it-out-agent

Run resilient multi-tool problem solving with explicit fallback strategy and auditable execution notes.

From plugin
cowork-os
452155 skills
Install
$ npx -y skills add CoWork-OS/CoWork-OS --skill usecase-figure-it-out-agent --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/usecase-figure-it-out-agent

Context preview

The summary Claude sees to decide when to auto-load this skill.

Run resilient multi-tool problem solving with explicit fallback strategy and auditable execution notes.

SKILL.md

usecase-figure-it-out-agent.SKILL.md
name: usecase-figure-it-out-agent
description: "Run resilient multi-tool problem solving with explicit fallback strategy and auditable execution notes."
version: "1.0.0"
metadata:
  author: CoWork OS Contributors <info@coworkosapp.com>

Figure It Out Agent

Purpose

Run resilient multi-tool problem solving with explicit fallback strategy and auditable execution notes.

Routing

  • Use when: Use when the user asks to solve a task autonomously with fallback behavior when tools fail.
  • Do not use when: Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
  • Outputs: Outcome from Figure It Out Agent: attempt log, verified result status, and fallback handoff plan when blocked.
  • Success criteria: Applies explicit fallback logic, reports evidence-based outcomes, and preserves approval boundaries for risky actions.

Trigger Examples

Positive

  • Use the usecase-figure-it-out-agent skill for this request.
  • Help me with figure it out agent.
  • Use when the user asks to solve a task autonomously with fallback behavior when tools fail.
  • Figure It Out Agent: provide an actionable result.

Negative

  • Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
  • Do not use usecase-figure-it-out-agent for unrelated requests.
  • This request is outside figure it out agent scope.
  • This is conceptual discussion only; no tool workflow is needed.

Parameters

| Name | Type | Required | Description | |---|---|---|---| | objective | string | Yes | Task objective to complete | | fallback_budget | number | No | Maximum fallback attempts after primary attempt | | external_action_policy | select | No | Policy for external irreversible actions | | completion_bar | select | No | How strict to be before calling task complete |

Runtime Prompt

  • Current runtime prompt length: 1160 characters.
  • Runtime prompt is defined directly in `../usecase-figure-it-out-agent.json`.
Read more
Ships withcowork-os

Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.

Get the whole plugin
Stats
450
Stars
77
Forks
Active
Maintenance
TypeScript
Language
MIT
License
6d ago
Last commit
7mo ago
Created

Repo: CoWork-OS/CoWork-OS

Other skills on cowork-os.