skill-evaluation-workbench skillA
skill-evaluation-workbench is agent-read markdown (skill) from yeaight7/agent-powerups: Use when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or MCP-backed cases..
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
# Skill Evaluation Workbench ## When To Use - A skill or prompt needs repeatable quality checks across models or configurations. - A workflow needs file-based graders, command traces, or local artifact checks. - A tool or MCP skill needs a hidden service fixture or sandboxed test workspace. - A previous agent attempt failed and you need trace-driven diagnosis before editing instructions. ## Requirements / Checks - Confirm an eval runner exists locally before running anything. Do not install deps without approval. - Prefer local deterministic graders over model-graded assertions. - If Docker, remote models, API keys, or live services are involved, ask before execution. - Treat traces, result files, preserved workspaces, and stdout as potentially sensitive. ## Minimal Suite Structure Every suite should have at least three cases: | Case | Purpose | |---|---| | Positive (golden path) | Skill handles the normal use case correctly | | Edge case | Skill handles an important boundary condition | | Control (no-tool-needed) | Skill does not over-trigger on a clearly unrelated input | …
Read the whole file at its exact version.
How to install
mdr add yeaight7/agent-powerups/skill-evaluation-workbench@git:20260606.7d1394fmdr add yeaight7/agent-powerups/skill-evaluation-workbench@sha256:14989d856574a288Pin 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_fn2xhuw5y2ngaon4)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260606.7d1394f latest | 2026-06-06 | 7d1394f | 3,940 B | A | view · diff |
| git:20260515.56c80fe | 2026-05-15 | 56c80fe | 3,935 B | A | view · diff |
| git:20260505.26d22fe | 2026-05-05 | 26d22fe | 2,471 B | A | view |
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 (3940 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
yeaight7/agent-powerups · 6 stars · license Apache-2.0 · pushed 2026-09-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fn2xhuw5y2ngaon4 GET https://markdownregistry.com/api/v1/resolve?ref=yeaight7/agent-powerups/skill-evaluation-workbench GET https://markdownregistry.com/api/v1/blob/14989d856574a288295d38db1895e5196b2ed490e5b8d0a17cf3c52e1b3d4dff
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 yeaight7/agent-powerups
Every file in yeaight7/agent-powerups