llm-eval-planner SKILL.md skillA
llm-eval-planner from pramoddutta/aitesterblueprint4x is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add pramoddutta/aitesterblueprint4x/llm-eval-planner@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- pramoddutta/aitesterblueprint4x
- Path
chapter_14_MCP_Create_VIBE/testskill-finder-mcp/skills/framework-packs/llm-eval-pack/llm-eval-planner/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0.0, committed Oct 10, 2026
- Size
- 4,022 bytes
- Repository stars
- 14
- License
- none declared
Plans an evaluation strategy for an LLM feature before anyone writes eval code. Use when an SDET or QA lead says "how do we test this LLM feature", "plan our evals", "what metrics should we track for the chatbot", or describes a GenAI feature about to ship. Produces a draft eval plan (quality dimensions, metrics, datasets, offline vs online eval, thresholds, regression gates) for the team to review and adjust.
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
# LLM Eval Planner You turn "is the bot good?" into **a measurable eval plan with explicit release gates**. You decide what to measure, on which data, and which score drop blocks a merge. ## When to use - A new LLM feature (chatbot, summarizer, RAG search, extractor) needs a test strategy. - Prompt or model changes ship with no regression signal beyond "looks fine to me". - A lead asks "how do we prove the new model is not worse than the old one?" ## Workflow 1. **Frame the feature.** Capture the task, users, inputs, outputs, model/provider, and the worst realistic failure (wrong refund policy, leaked PII). Ask for anything unknown. 2. **Pick quality dimensions.** Choose 4-6 that matter here: correctness, faithfulness, relevancy, safety, format/schema validity, tone, latency, cost. Drop any dimension nobody will act on. 3. **Map each dimension to a metric and method.** Deterministic checks first (regex, JSON schema, exact match), then reference-based scores, then LLM-as-a-judge only where meaning matters. Note which metrics need human labels. 4. **Define datasets.** A versioned golden set, an adversarial/edge set, and a sampled …
Read the whole file at its exact version.
How to install
mdr add pramoddutta/aitesterblueprint4x/llm-eval-planner@sha256:d1b2098b8c97ed3cThe line at the top of this page pins the label v1.0.0, 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_h62pojuoza4ks57d)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 10, 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 (4022 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
pramoddutta/aitesterblueprint4x · 14 stars · license none declared · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_h62pojuoza4ks57d GET https://markdownregistry.com/api/v1/resolve?ref=pramoddutta/aitesterblueprint4x/llm-eval-planner GET https://markdownregistry.com/api/v1/blob/d1b2098b8c97ed3cca4116933c588ea144447824bd0665b362a753667defc682
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.