evaluate SKILL.md skillA
evaluate from cooneycw/claude-power-pack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add cooneycw/claude-power-pack/evaluate@git:20260920.677b300Pins git:20260920.677b300 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- cooneycw/claude-power-pack
- Path
.claude/skills/evaluate/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260920.677b300, committed Sep 20, 2026
- First version recorded
- Aug 16, 2026
- Size
- 4,427 bytes
- Repository stars
- 21
- License
- a license file GitHub does not identify
Domain-aware prompts for multi-model analysis. Use to evaluate an architecture, concept, algorithm, ui-design or workflow, with a Phase 1 divergence scan and Phase 3 validation.
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
# Evaluation Domain Prompts When the `/evaluate:issue` command is triggered, use these domain-specific prompts to frame the multi-model consultation calls to the second-opinion MCP server directly. ## Domain Types Valid domains: `architecture`, `concept`, `algorithm`, `ui-design`, `workflow` ## Phase 1 Prompts (Divergence Scan) ### architecture Evaluate this architecture proposal. Focus on: - Scalability: Can this handle 10x/100x growth? - Reliability: What are the failure modes and recovery paths? - Security: What attack surfaces exist? - Cost: What are the operational cost implications? - Maintainability: How complex is the operational burden? Identify where reasonable architects would disagree on trade-offs. ### concept Evaluate this concept/feature proposal. Focus on: - Feasibility: Is this technically and organizationally achievable? - User Value: Does this solve a real user problem? - Scope: Are the boundaries clear and reasonable? - Competitive Landscape: How does this compare to alternatives? - Risk: What could go wrong? Identify where reasonable stakeholders would disagree. ### algorithm Evaluate this algorithmic approach. Focus on: …
Read the whole file at its exact version.
How to install
mdr add cooneycw/claude-power-pack/evaluate@sha256:eb4502c85e3c913bThe line at the top of this page pins the label git:20260920.677b300, 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_33ch5aldqmrzpkf5)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 16, 2026 and Sep 20, 2026, about one every 35 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260920.677b300 latest | 2026-09-20 | 677b300 | 4,427 B | A | view · diff |
| git:20260816.e816052 | 2026-08-16 | e816052 | 4,432 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 (4427 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
cooneycw/claude-power-pack · 21 stars · license a license file GitHub does not identify · pushed 2026-10-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_33ch5aldqmrzpkf5 GET https://markdownregistry.com/api/v1/resolve?ref=cooneycw/claude-power-pack/evaluate GET https://markdownregistry.com/api/v1/blob/eb4502c85e3c913bda767c7ebd035e23682b8b3a1b6cc865c5ed1db296869619
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.
More from cooneycw/claude-power-pack
Every file in cooneycw/claude-power-pack