evidence-research SKILL.md skillA

evidence-research from ucsahinn/agentchef is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ucsahinn/agentchef/evidence-research@git:20261006.6a4c0f7

Pins git:20261006.6a4c0f7 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ucsahinn/agentchef
Path
plugins/agentchef/skills/evidence-research/SKILL.md
Versions recorded
2
Latest version
git:20261006.6a4c0f7, committed Oct 6, 2026
First version recorded
Oct 3, 2026
Size
4,068 bytes
Repository stars
6
License
MIT

Source-traceable deep research for decisions, comparisons, landscapes, and evidence reviews. Use when a request needs a research charter, current primary sources, claim-level citations, disagreement and uncertainty analysis, or a decision-ready evidence package.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Evidence Research

Produce decision-ready research whose material claims trace to checked sources.
Do not turn a broad web search into an imitation systematic review.

## Invocation

- Direct: `$evidence-research <question>`.
- Plugin: `$agentchef:evidence-research <question>`.
- Implicit activation is allowed for clear deep, literature, market, landscape,
  comparative, or evidence-synthesis requests, not ordinary factual lookup.

## Research Contract

Read [scoping-and-charter.md](references/scoping-and-charter.md) first. State
the decision, primary question, focused sub-questions, audience, scope,
exclusions, geography, time horizon, deadline, evidence standard, stopping
rule, and deliverable. Use a bounded labeled default when missing inputs do not
materially change authority, cost, or method.

Separate `fact`, `inference`, and `recommendation`. Every material claim needs
checked source IDs, confidence, uncertainty, and relevant disagreement.

## Workflow

1. Choose orientation, decision-support, landscape, implementation,
   evidence-review, or original-analysis mode.
2. Design concepts, queries, source classes, inclusion/exclusion rules, and a
   reproducible log with
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ucsahinn/agentchef/evidence-research@sha256:dc466b92b405d143

The line at the top of this page pins the label git:20261006.6a4c0f7, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_mx4savxn7rpmmten.svg)](https://markdownregistry.com/a/art_mx4savxn7rpmmten)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Oct 3, 2026 and Oct 6, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20261006.6a4c0f7 latest2026-10-06 6a4c0f7 4,068 BA view · diff
git:20261003.dd106462026-10-03 dd10646 4,205 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4068 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ucsahinn/agentchef · 6 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_mx4savxn7rpmmten
GET https://markdownregistry.com/api/v1/resolve?ref=ucsahinn/agentchef/evidence-research
GET https://markdownregistry.com/api/v1/blob/dc466b92b405d143471aa7e0ff6a6a05a278ac8421ee814c31a9a7ec02d538c3

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from ucsahinn/agentchef

AGENTS.md AGENTS.md file
ucsahinn/agentchef · AGENTS.md
git:20261002.450976a · audit A · 6 stars
CLAUDE.md CLAUDE.md file
ucsahinn/agentchef · CLAUDE.md
git:20260918.338227d · audit A · 6 stars
llms.txt llms.txt file
ucsahinn/agentchef · llms.txt
git:20261006.6a4c0f7 · audit A · 6 stars
adaptive-agent-routing SKILL.md skill
ucsahinn/agentchef · plugins/agentchef/skills/adaptive-agent-routing/SKILL.md · Select the narrowest useful agent, skill, MCP, and config route for non-trivial work. Use when delegation, context…
git:20261019.77261b3 · audit A · 6 stars
agent-brief SKILL.md skill
ucsahinn/agentchef · plugins/agentchef/skills/agent-brief/SKILL.md · Write the task brief an orchestrator hands to another agent (subagent, Codex worker, or peer session) and check the…
git:20261019.77261b3 · audit A · 6 stars
agentchef-operator SKILL.md skill
ucsahinn/agentchef · plugins/agentchef/skills/agentchef-operator/SKILL.md · Maintain, audit, and improve AgentChef setup repositories. Use for README/docs/template/catalog/installer/validation…
git:20261003.dd10646 · audit A · 6 stars
context-budget-planner SKILL.md skill
ucsahinn/agentchef · plugins/agentchef/skills/context-budget-planner/SKILL.md · Plan token and context usage before broad agent work. Use for repo-wide, research-heavy, multi-agent…
git:20261003.dd10646 · audit A · 6 stars
external-review-workflow SKILL.md skill
ucsahinn/agentchef · plugins/agentchef/skills/external-review-workflow/SKILL.md · Prepare a secret-safe, hash-pinned repository snapshot for manual review by an external model, generate a local handoff…
git:20261003.dd10646 · audit A · 6 stars
fetch SKILL.md skill
ucsahinn/agentchef · plugins/agentchef/skills/fetch/SKILL.md · Reconstruct an authorized reference website from a supplied URL with high visual, responsive, interaction, and behavior…
git:20261006.6a4c0f7 · audit A · 6 stars
gptpro-handoff SKILL.md skill
ucsahinn/agentchef · plugins/agentchef/skills/gptpro-handoff/SKILL.md · Author a manifest-bound GPT Pro (ChatGPT Project) prompt and verify the returned report against the live repository…
git:20261006.6a4c0f7 · audit A · 6 stars
gptpro SKILL.md skill
ucsahinn/agentchef · plugins/agentchef/skills/gptpro/SKILL.md · Prepare a repository for a manual GPT Pro (ChatGPT Project) deep review as safe, architecture-aware text bundles plus a…
git:20261006.6a4c0f7 · audit A · 6 stars
offline-diagram-triplet SKILL.md skill
ucsahinn/agentchef · plugins/agentchef/skills/offline-diagram-triplet/SKILL.md · Create editable offline diagrams from an English description or Mermaid source. Use when the agent should emit a…
git:20261003.dd10646 · audit A · 6 stars

Every file in ucsahinn/agentchef

Other files named evidence-research

evidence-research SKILL.md skill
rizwanzafaris/product-manager-os · skills/runtime/evidence-research/SKILL.md · Gather source-backed evidence with provenance. Use when a product decision needs claims separated from observations and…
git:20260903.05afd61 · audit A · 4 stars

Browse by kind, by grade A, or by owner.