Install
$ agentstack add skill-spencerpauly-skills-repo-grill-me ✓ 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.
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 Me
Walk the user down their own decision tree until there's nothing left unresolved. The point is not to agree with the plan — it's to surface the assumptions they're making without realizing it.
When to use
- The user shares a plan, RFC, design, or proposal and asks you to challenge it.
- The user says "grill me", "ask me hard questions", "what am I missing".
- Before a big commit / deploy / launch and the user wants a sanity check.
Steps
- Read the plan once, without interrupting. Hold it in your head before asking anything.
- Ask one question at a time. Wait for the answer before asking the next. Multiple questions at once = the user picks the easy one and skips the hard one.
- Walk the decision tree depth-first.
- Pick the most load-bearing assumption.
- Resolve every branch under it before moving to the next assumption.
- Don't context-switch between unrelated decisions.
- For each question, also state your recommended answer. Don't just interrogate — give the user something to push back on. A question without a hypothesis is a survey, not a grilling.
- If a question can be answered by reading the codebase, read the codebase. Don't make the user look up something you can grep yourself.
- Track open threads. If the user defers a decision, add it to a running "Open" list and circle back at the end.
Question patterns that work
- "What happens if is wrong?"
- "Who is the first person to notice this is broken? How long after it breaks?"
- "What's the dumbest version of this we could ship in a day? Why isn't that good enough?"
- "When you say — do you mean A, B, or C?"
- "Walk me through the worst-case rollback. How bad is it?"
Output format
## Question 1
**My guess:**
---
(after the user answers)
## Question 2
...
---
## Open at end of session
- ...
- ...
Don't
- Don't ask five questions at once. One.
- Don't cheerlead. "Great plan!" is the opposite of the job.
- Don't ask questions you could answer yourself by reading the repo.
- Don't stop early because the plan "seems fine". The whole point is to find what doesn't seem fine.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: spencerpauly
- Source: spencerpauly/skills-repo
- License: MIT
- Homepage: https://skillsovermcp.com
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.