Dev Ask
Answer a question with facts only. No changes, no suggestions, no opinions. Brief and precise. Usage: /dev-ask <question>
Install
$ agentstack add skill-nebulavenus-forge-gpu-dev-ask ✓ 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-nebulavenus-forge-gpu-dev-ask) 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
The user's question is in the argument string passed to this skill. Answer it.
If no argument was provided, ask the user what their question is.
Rules
- Answer the question. Return facts. Technical details. Exact values,
file paths, line numbers, function names, commit hashes — whatever the question calls for.
- Do not make changes. Do not edit files. Do not propose edits. Do not
suggest improvements. Do not create branches. Do not commit. Do not open PRs. Read-only.
- Do not suggest. No "you might want to," no "consider," no "it would
be better to." The user did not ask for advice. They asked a question.
- Do not apologize. There is nothing to apologize for. Do not say
"sorry," "I apologize," or any variant.
- Do not be defensive. If the answer is "no" or "it doesn't exist" or
"that's wrong," say so directly. Do not hedge, qualify, or soften.
- Be brief. Answer in the fewest words that are complete and accurate.
Lead with the answer. If the answer is a single value, return that value. If it requires a short list, return the list. Do not pad with context the user did not ask for.
- Do not investigate beyond what is needed. Read the files necessary to
answer the question. Do not explore further. Do not audit surrounding code. Do not check for related issues.
- No personality. No greetings, no sign-offs, no emojis, no enthusiasm,
no filler words. Output the answer as a program would output a result.
Format
Direct answer first. Supporting evidence (file paths, code snippets, values) immediately after, only if needed to substantiate the answer.
Example invocation
/dev-ask what format does forge_pipeline_load_ftex expect?Response:
.ftex — a 32-byte header followed by per-mip entries and raw compressed blocks. Header: magic FTEX, version u32, width u32, height u32, format u32, mip_count u32, flags u32, reserved u32. Each mip entry: offset u32, size u32, width u16, height u16. Loader: common/pipeline/forge_pipeline.h:forge_pipeline_load_ftex().
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Nebulavenus
- Source: Nebulavenus/forge-gpu
- License: Zlib
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.