Grill With Docs
Planning interview skill that asks sharp questions before execution and turns decisions into durable project docs, domain language, PRDs, or ADR notes. Use when the user has an idea, feature, plan, product change, or unclear request that needs alignment before implementation.
Install
$ agentstack add skill-ntaffzii-skill-agents-grill-with-docs ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-ntaffzii-skill-agents-grill-with-docs) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Grill With Docs
Use this skill before implementation when alignment matters.
Workflow
- Establish intent
- Ask what outcome the user wants, who it is for, and what must not change.
- Identify success criteria and failure modes.
- Challenge scope
- Find the smallest useful version.
- Ask what can be deferred.
- Surface hidden dependencies, permissions, data needs, and integration points.
- Separate must-have, should-have, nice-to-have, and out-of-scope items when the request is large.
- Build shared language
- Name the domain concepts in the user's words.
- Define ambiguous terms.
- Prefer one precise term over repeated explanatory phrases.
- Convert decisions into docs
- Create or update lightweight docs only when they will help future sessions.
- Use PRD for product behavior.
- Use ADR for architectural decisions.
- Use glossary/context docs for domain language.
- End with an execution-ready brief
- Goals
- Non-goals
- Decisions
- Open questions
- First implementation slice
- Validation plan
Question Rules
- Ask the fewest questions that unblock execution.
- Group related questions.
- Do not interview forever; once enough context exists, recommend a path.
- If the user is absent, make conservative assumptions and label them.
Verification
- The brief has a clear goal and non-goals.
- Decisions are separated from open questions.
- The first implementation slice is small enough to execute.
- Any assumptions are labeled.
Output Format
End with:
- Goals
- Non-goals
- Scope
- Decisions
- Open questions
- First implementation slice
- Validation plan
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ntaffzii
- Source: ntaffzii/Skill-Agents
- License: MIT
- Homepage: https://github.com/ntaffzii/ai-desk-tools
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.