project-assessment-evidence skillA
project-assessment-evidence is agent-read markdown (skill) from ulises-jeremias/agent-toolkit: WHAT - Interactive evidence intake for project assessments. Ask the user where each evidence.
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
# Project Assessment Evidence (WHAT) Use this skill before scoring a project assessment. It turns scattered project knowledge into a structured evidence map. This skill is intentionally interactive. Evidence can be outside ClickUp and outside the repository. Ask for source locations instead of assuming where they live. ## Default behavior 1. Ask the user for the systems of record and evidence locations. 2. Collect source links, paths, owners, dates, and freshness for each evidence item. 3. Mark evidence quality: Direct, Indirect, Interview-only, Stale, Missing, or Not applicable. 4. Record confidence for each evidence item: High, Medium, Low, or Not assessed. 5. Do not score indicators. Return the evidence map to **`project-assessment`**, **`technical-unit-assessment`**, or **`management-unit-assessment`**. ## Evidence intake questions Ask only the questions relevant to the assessment scope, but cover each required source class before scoring. ### Scope and systems - What project, product, platform, squad, or delivery scope is being assessed? - What period should evidence cover? - What are the official systems of record? …
Read the whole file at its exact version.
How to install
mdr add ulises-jeremias/agent-toolkit/project-assessment-evidence@git:20260831.856ee57mdr add ulises-jeremias/agent-toolkit/project-assessment-evidence@sha256:f6720f1026d57898Pin 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.
[](https://markdownregistry.com/a/art_55dfxdpg56yejq5i)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3936 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
ulises-jeremias/agent-toolkit · 18 stars · license MIT · pushed 2026-09-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_55dfxdpg56yejq5i GET https://markdownregistry.com/api/v1/resolve?ref=ulises-jeremias/agent-toolkit/project-assessment-evidence GET https://markdownregistry.com/api/v1/blob/f6720f1026d57898e0c67d243c8b8dbf94006befe43a48c24cfb1d2509f6d2be
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.