agent-exploration

Featured

Coordinate native explorers for explicitly requested multi-area research with scoped written results and an evidence-backed synthesis.

AI & Automation 2,894 stars 189 forks Updated today MIT

Install

View on GitHub

Quality Score: 99/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Agent Exploration Use when explicitly requested for research across independent areas with written results. Use the current harness's native explorers and configured model/effort; an explicit user override wins. Do not invoke an external runtime or create an agent registry for this workflow. ## Scope and dispatch 1. Resolve the question and output path from the request or active task. Ask only for genuinely missing scope; creating the requested directory needs no additional confirmation. Default an unspecified artifact location to `.audits/exploration/<timestamp>/` and state it. 2. Reuse current grounding. Scout only enough to identify independent questions; no tool-call or source-count quota. Choose as many useful slices as capacity and scope justify, up to 8; `--agents` is an upper bound, not a target to pad. 3. Read `references/dispatch-rules.md` and `assets/explorer-prompt.md` once when preparing dispatch. Send each explorer its question, source scope, exact output path, and the scoped-write contract once. Include `assets/analysis-template.md` when a structured artifact is needed; do not duplicate the contract in several embedded documents. 4. Create the output directory, then dispatch independent slices as capacity permits. Prompts need durable copies only for a long/resumable run. Every worker is read-only except for its named analysis file; no commits or unrelated edits. 5. Inspect each completed artifact and its material citations. A failed slice does not invalid...

Details

Author
compozy
Repository
compozy/compozy
Created
7 months ago
Last Updated
today
Language
Go
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category