ai-architect-mcp-spec SKILL.md skillA
ai-architect-mcp-spec from cdeust/ai-architect-mcp-spec is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add cdeust/ai-architect-mcp-spec/ai-architect-mcp-spec@v0.8.0Pins v0.8.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- cdeust/ai-architect-mcp-spec
- Path
packages/skill/SKILL.md- Versions recorded
- 5
- Latest version
- v0.8.0, committed Aug 10, 2026
- First version recorded
- Jul 27, 2026
- Size
- 20,938 bytes
- Repository stars
- 6
- License
- MIT
Action-driven PRD generation. The MCP server runs a stateless 20-step pipeline reducer (11 PRD-generation steps + 9 opt-in implementation steps behind a human gate); the host (Claude Code) executes each substantive action and feeds the result back via submit_action_result, looping until done. Multi-judge verification combines genius reasoning patterns with zetetic team subagents. Grounded in the ai-architect ecosystem (ai-architect-mcp-codebase MCP, Cortex MCP, zetetic-team-subagents).
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
# AI Architect MCP Spec (v0.8.0) — Dispatcher Protocol
You (the host) drive a loop:
1. Call `start_pipeline` → receive an envelope with `{ run_id, messages, action, ... }`.
2. Display every entry in `messages` to the user.
3. Execute `action` per the dispatch table below.
4. Call `submit_action_result(run_id, result)` → receive next envelope.
5. Repeat until `action.kind === "done"` or `action.kind === "failed"`.
**`emit_message` is never returned to the host as `action`.** The runner coalesces all status messages into the `messages` array; the `action` field always carries something the host actually has to do.
---
## ENVELOPE SHAPE
Every response from `start_pipeline` and `submit_action_result` has this shape:
```json
{
"run_id": "run_abc_123",
"current_step": "context_detection",
"messages": [
{ "text": "🟢 PRD Spec Generator — TRIAL TIER\n...", "level": "info" }
],
"action": { "kind": "ask_user" | "call_pipeline_tool" | ... , ... },
"state_summary": { "sections": [...], "clarification_rounds": 3, "errors": 0 }
}
```
- `run_id` — handle for `submit_action_result` and `get_pipeline_state`. Caputre once from the first response and reuse.
…Read the whole file at its exact version.
How to install
mdr add cdeust/ai-architect-mcp-spec/ai-architect-mcp-spec@sha256:e569e5d74e49c9e3The line at the top of this page pins the label v0.8.0, 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_3wfdkgpjaxz24uyl)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 27, 2026 and Aug 10, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.8.0 latest | 2026-08-10 | 288dc4f | 20,938 B | A | view · diff |
| v0.7.0 | 2026-08-04 | 640080e | 20,938 B | A | view · diff |
| v0.7.0 | 2026-08-04 | a883cec | 21,017 B | A | view · diff |
| v0.6.1 | 2026-08-03 | 7546dd6 | 21,006 B | A | view · diff |
| v0.6.1 | 2026-07-27 | b0d06e3 | 21,006 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 (20938 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
cdeust/ai-architect-mcp-spec · 6 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_3wfdkgpjaxz24uyl GET https://markdownregistry.com/api/v1/resolve?ref=cdeust/ai-architect-mcp-spec/ai-architect-mcp-spec GET https://markdownregistry.com/api/v1/blob/e569e5d74e49c9e3edc95442a996492a59ea971886a4a8c27b645318c334d97d
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.