prompt-evaluation SKILL.md skillA
prompt-evaluation from aniruddhadas1/oniroute_swarmagents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add aniruddhadas1/oniroute_swarmagents/prompt-evaluation@git:20260804.c3b625aPins git:20260804.c3b625a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- aniruddhadas1/oniroute_swarmagents
- Path
skills/official/ai/prompt-evaluation/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260804.c3b625a, committed Aug 4, 2026
- Size
- 4,681 bytes
- Repository stars
- 2
- License
- Apache-2.0
Evaluate instruction quality through representative cases, criteria, and failure analysis. Use for planning, evaluation, governance, or review of prompt evaluation; do not use as framework-specific or provider-specific implementation guidance.
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
# Prompt Evaluation ## Purpose Evaluate instruction quality through representative cases, criteria, and failure analysis. ## Problem Statement Prompt Evaluation decisions often fail when teams optimize one visible concern while leaving ownership, evidence, dependencies, failure behavior, or change cost implicit. ## Core Concepts - Outcome: the decision or behavior this capability must support. - Boundary: what is inside scope, outside scope, and owned elsewhere. - Evidence: requirements, measurements, risks, and uncertainty. - Contract: inputs, outputs, invariants, and failure conditions. - Evolution: compatibility, migration, reversibility, and review triggers. ## Engineering Principles - Begin with explicit outcomes and accountable ownership. - Match controls and rigor to evidenced impact and risk. - Keep provider and framework choices outside the universal contract. - Prefer observable, reversible decisions with clear failure handling. - Record assumptions, alternatives, and conditions for reconsideration. ## Decision Framework …
Read the whole file at its exact version.
How to install
mdr add aniruddhadas1/oniroute_swarmagents/prompt-evaluation@sha256:a7c89f4ee5f8fc76The line at the top of this page pins the label git:20260804.c3b625a, 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.
[](https://markdownregistry.com/a/art_wqombypexxb7mk4c)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 4, 2026.
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 (4681 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
aniruddhadas1/oniroute_swarmagents · 2 stars · license Apache-2.0 · pushed 2026-09-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wqombypexxb7mk4c GET https://markdownregistry.com/api/v1/resolve?ref=aniruddhadas1/oniroute_swarmagents/prompt-evaluation GET https://markdownregistry.com/api/v1/blob/a7c89f4ee5f8fc7658714e4f562966fe05b78ed83bfe00de043ba42865a107dc
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.