# Evidence Synthesis

> Builds research findings from inspected sources while preserving uncertainty and provenance.

- **Type:** Skill
- **Install:** `agentstack add skill-storious-agent-playbook-evidence-synthesis`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [storious](https://agentstack.voostack.com/s/storious)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [storious](https://github.com/storious)
- **Source:** https://github.com/storious/agent-playbook/tree/main/examples/pi-research-copilot/.agents/skills/evidence-synthesis

## Install

```sh
agentstack add skill-storious-agent-playbook-evidence-synthesis
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Evidence Synthesis

1. Start from the decision the research must support, not from a generic topic summary.
2. Record the source type and date beside every material claim.
3. Label inferences as inferences and do not convert snippets into evidence.
4. End with the next source or experiment that would change the conclusion.

Record the relevant evidence, decision, and verification result in the working
set or handoff. This skill does not grant tools or bypass host permissions.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [storious](https://github.com/storious)
- **Source:** [storious/agent-playbook](https://github.com/storious/agent-playbook)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-storious-agent-playbook-evidence-synthesis
- Seller: https://agentstack.voostack.com/s/storious
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.