Home / okhp3 / skillz · copilot/okhp3-cowork-research-evidence-log/SKILL.md · GitHub

okhp3-cowork-research-evidence-log skillA

okhp3-cowork-research-evidence-log is agent-read markdown (skill) from okhp3/skillz: Build a source-linked research evidence log with confirmed, inferred, and unknown claims. Use when preparing a research brief, comparison, or decision memo from agreed sources. Do not treat search snippets as proof, publish a conclusion, or access sources outside the agreed boundary without approval..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# okhp3-cowork-research-evidence-log

**OverKill Hill P³** · [overkillhill.com](https://overkillhill.com) · [github.com/OKHP3](https://github.com/OKHP3)

Build a research record that lets a reviewer see the claim, its source, and its
uncertainty without rereading every document.

## Scope

| In scope | Out of scope |
| --- | --- |
| Bounded source review, claim ledgers, comparisons, and research briefs | Invented citations, unbounded retrieval, publishing, or specialist decisions presented as advice |

## Host contract

- **Target:** Microsoft Copilot Cowork personal custom skill.
- **Portable core:** classify claims from supplied sources as confirmed,
  inferred, contradicted, or unknown.
- **Cowork adaptation:** use selected organizational context or files only when
  available within the user's permissions. Cowork documents a built-in Deep
  Research skill; use it only within an explicit source boundary.
- **Evidence:** documented Cowork context behavior; no live package run.

## Activation boundary and handoff

- **Interactive and automation boundary:** Use interactively by default. A
  scheduled or event-driven run may produce a draft only; it must not send,
…

Read the whole file at its exact version.

How to install

Latest version
mdr add okhp3/skillz/okhp3-cowork-research-evidence-log@v1.1.0
Exact content
mdr add okhp3/skillz/okhp3-cowork-research-evidence-log@sha256:78323ee9d5a8b8d7

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_umi3fny6nj472c5j.svg)](https://markdownregistry.com/a/art_umi3fny6nj472c5j)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v1.1.0 latest2026-09-01 a02fef7 5,133 BA view · diff
v1.1.02026-09-01 0b68b7f 4,102 BA view · diff
v1.0.02026-09-01 8cf8a41 4,102 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (5133 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

okhp3/skillz · 3 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_umi3fny6nj472c5j
GET https://markdownregistry.com/api/v1/resolve?ref=okhp3/skillz/okhp3-cowork-research-evidence-log
GET https://markdownregistry.com/api/v1/blob/78323ee9d5a8b8d7e72539e204826ca8b682fe07e0b5610a1b6a832b6d5b5a82

Your agent 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.

More from okhp3/skillz

architecture-decision-records skill
okhp3/skillz · .agents/skills/architecture-decision-records/SKILL.md · Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation…
git:20260826.7647b43 · audit A · 3 stars
catalog-integrity skill
okhp3/skillz · .agents/skills/catalog-integrity/SKILL.md · Rebuild and validate Skillz Forge catalog truth, evidence contracts, and provenance without credentials.
git:20260909.3002a99 · audit A · 3 stars
frontend-design skill
okhp3/skillz · .agents/skills/frontend-design/SKILL.md · Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to…
git:20260802.63f3338 · audit A · 3 stars
okhp3-artifact-validation skill
okhp3/skillz · .agents/skills/okhp3-artifact-validation/SKILL.md · Validate a project change, draft, research packet, skill, promotion package, or handoff before it is treated as…
v0.1.0 · audit A · 3 stars
okhp3-as-is-process-capture skill
okhp3/skillz · .agents/skills/okhp3-as-is-process-capture/SKILL.md · Capture and normalise a current-state process description into a structured as-is process YAML with stable step…
v0.1.0 · audit A · 3 stars
okhp3-brand-style-registry skill
okhp3/skillz · .agents/skills/okhp3-brand-style-registry/SKILL.md · OverKill Hill P³ visual style registry and application workflow. Use when a user wants to extract a reusable brand…
v1.3.0 · audit A · 3 stars
okhp3-capture-intake skill
okhp3/skillz · .agents/skills/okhp3-capture-intake/SKILL.md · Preserve one raw idea, file, link, transcript, or request in a project inbox with provenance and minimal handling. Use…
v0.1.0 · audit A · 3 stars
okhp3-chatgpt-project-migration skill
okhp3/skillz · .agents/skills/okhp3-chatgpt-project-migration/SKILL.md · OverKill Hill P³ ChatGPT project migration. Use when migrating, preserving, extracting, inventorying, normalizing…
v1.1.0 · audit A · 3 stars
okhp3-custom-gpt-builder skill
okhp3/skillz · .agents/skills/okhp3-custom-gpt-builder/SKILL.md · Build, audit, and improve OpenAI Custom GPTs with production-grade methodology. Use this skill when the user asks to…
v1.3.0 · audit A · 3 stars
okhp3-custom-gpt-readiness skill
okhp3/skillz · .agents/skills/okhp3-custom-gpt-readiness/SKILL.md · Assess an incomplete or newly proposed Custom GPT concept for build readiness. Use when a user has a GPT idea, partial…
v1.2.0 · audit A · 3 stars
okhp3-decision-model-authoring skill
okhp3/skillz · .agents/skills/okhp3-decision-model-authoring/SKILL.md · Author and validate decision models from PNS decision points using DMN-aligned rule tables. Use this skill when the PNS…
v0.1.0 · audit A · 3 stars
okhp3-elicitation-interviews skill
okhp3/skillz · .agents/skills/okhp3-elicitation-interviews/SKILL.md · Plan and facilitate structured elicitation sessions using BABOK v3 interview and workshop techniques. Use this skill…
v0.1.0 · audit A · 3 stars

Every file in okhp3/skillz

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