AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Mb Analysis

skill-mrvladd-d-memobank-mb-analysis · by mrvladd-d

>

No reviews yet
0 installs
34 views
0.0% view→install

Install

$ agentstack add skill-mrvladd-d-memobank-mb-analysis

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-mrvladd-d-memobank-mb-analysis)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Mb Analysis? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

mb-analysis - Optional Analysis before PRD

  • What it does: adds a lightweight Analysis phase before /prd when the idea is vague, unstable, or needs explicit product framing.
  • Use /analysis when: you need a router that inspects current Memory Bank state and recommends the next command.
  • Use /brainstorm when: the idea is raw and needs facilitated ideation. The AI acts as a coach; the user's product intent and choices remain the source of truth.
  • Use /brief when: the concept is clear enough to produce a concise Product Brief, or after a brainstorming report exists.
  • Output: optional artifacts under .memory-bank/analysis/.

Analysis is optional. Raw PRD text or an existing external PRD should pass /constitution first when project principles are not ratified/partial, then be normalized and checked through /write-prd, producing .memory-bank/prd.md with type: prd, clarification_status: complete, and constitution_checked: true; then /spec-init prepares the lightweight SDD route map before /prd decomposes it. After /prd, /spec-design is mandatory but adaptive: simple T0/T1 scope may record a minimal backbone, while shared/T2/T3 scope records the needed domain/model/contracts/state/security/runtime design. Brownfield projects should map the current codebase first with /map-codebase before planning deltas.

/brief creates the Product Brief as the input contract for /constitution and /write-prd. It is not a PRD, backlog, research report, or marketing document.

The normal planning path is:

/analysis -> /brief -> /constitution -> /write-prd -> /spec-init -> /prd -> /spec-design -> /spec-improve FT- -> /prd-to-tasks FT-

Use /brainstorm before /brief when the idea is raw. /constitution should read the Product Brief when present and run the governing-principles interview; if the user explicitly skips it, downstream PRD work may continue with framework-default/skipped principles.

Analysis never creates task records. /spec-design also does not create task records or feature-local implementation design; it only updates backbone SDD specs and spec-index, while /spec-improve FT- remains the feature-level gate. /clarify-feature FT- is optional and only for a specific feature that is explicitly pending/blocked or has decomposition-affecting unresolved markers.

Artifacts

  • .memory-bank/analysis/index.md
  • .memory-bank/analysis/product-brief.md
  • .memory-bank/analysis/brainstorming/BR-.md

Templates in assets/ are reference shapes for those artifacts. They are intentionally compact and can be adapted during interactive sessions.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.