← Back to Skills Marketplace
Prfaq Beagle
by
Kevin Anderson
· GitHub ↗
· v1.0.0
· MIT-0
92
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install prfaq-beagle
Description
Use when the user wants to pressure-test a product, internal-tool, or OSS concept against Amazon's Working Backwards PRFAQ gauntlet before committing to a sp...
Usage Guidance
This skill is internally consistent with its stated purpose, but before enabling it you should: 1) be aware it will scan your repository (auto-discover docs) and create/modify files under .beagle/concepts/<slug>/ — back up any sensitive content you don't want scanned or committed; 2) expect it to reuse prior analysis/research outputs by default (it won't overwrite without explicit refresh) — review .beagle before re-running; 3) note that web grounding is performed by companion web-research (which may make web requests or require web tools/credentials) — review the companion's permissions/policy if you care about outbound network access; 4) this skill explicitly forbids writing code or scaffolding, so it won't start builds or deployments. If any of those behaviors are unacceptable in your environment (repo scanning, local file writes, or companion web access), run it in a sanitized or disposable workspace or inspect the companion skills first.
Capability Analysis
Type: OpenClaw Skill
Name: prfaq-beagle
Version: 1.0.0
The prfaq-beagle skill bundle implements a structured 'Working Backwards' product discovery process based on Amazon's PRFAQ methodology. It guides an AI agent through five stages (Ignition, Press Release, Customer FAQ, Internal FAQ, and Verdict) to rigorously filter product concepts. The skill utilizes companion skills (artifact-analysis and web-research) to ground its feedback in local documents and market data, following a well-defined 'Companion Invocation Contract' in companion-contract.md. The instructions in SKILL.md and the reference files emphasize a skeptical, 'hardcore' coaching tone but include explicit safety boundaries, such as prohibiting the agent from writing code or scaffolding projects. No indicators of data exfiltration, malicious execution, or unauthorized persistence were found.
Capability Tags
Capability Assessment
Purpose & Capability
Name and description (Working Backwards PRFAQ filter) match the instructions: the skill reads/writes PRFAQ artifacts under .beagle/concepts/<slug>/, auto-discovers repo docs for artifact-analysis, and coordinates web-research. It requests no unrelated binaries, environment variables, or external installs.
Instruction Scope
Runtime instructions explicitly read and write files in the project workspace (prfaq.md, analysis/, research/, brief.md) and call companion skills in serial. This is coherent for a document-based coach, but note it performs repository auto-discovery (scans project folders) and will create/modify files under .beagle — users should expect local file reads/writes and deliberate resume/reuse behavior. No instructions request unrelated system data (shell history, credentials, etc.).
Install Mechanism
Instruction-only skill with no install spec and no code; nothing is downloaded or executed beyond the agent following prose instructions and invoking declared companion skills.
Credentials
No environment variables, credentials, or config paths are required by this skill. Companion skills (artifact-analysis, web-research) may have their own needs, but prfaq-beagle itself does not request secrets.
Persistence & Privilege
Flags: always=false and user-invocable=true. The skill writes/maintains files under its own workspace (.beagle/concepts/<slug>/) and reuses prior runs by default per its resume rules. It does not request system-wide privilege, nor does it alter other skills' configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install prfaq-beagle - After installation, invoke the skill by name or use
/prfaq-beagle - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
prfaq-beagle 1.0.0
- Initial release of the prfaq-beagle skill: a Working Backwards product concept filter inspired by Amazon’s PRFAQ process.
- Guides users through a five-stage gated workflow (Ignition, Press Release, Customer FAQ, Internal FAQ, Verdict) for idea validation.
- Provides a binary pass/fail verdict with direct coaching; only passing concepts generate a handoff brief for brainstorm-beagle.
- Applies pressure-testing to solution-first and technology-first pitches, enforcing customer-first rigor.
- Does not produce specs, implementation plans, or code; strictly focused on concept validation before resource commitment.
- Includes resume support and folder structure for persistent concept tracking and artifact storage.
Metadata
Frequently Asked Questions
What is Prfaq Beagle?
Use when the user wants to pressure-test a product, internal-tool, or OSS concept against Amazon's Working Backwards PRFAQ gauntlet before committing to a sp... It is an AI Agent Skill for Claude Code / OpenClaw, with 92 downloads so far.
How do I install Prfaq Beagle?
Run "/install prfaq-beagle" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Prfaq Beagle free?
Yes, Prfaq Beagle is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Prfaq Beagle support?
Prfaq Beagle is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Prfaq Beagle?
It is built and maintained by Kevin Anderson (@anderskev); the current version is v1.0.0.
More Skills