Install
$ agentstack add skill-shivaedev-pardes-pr-description ✓ 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
pr-description
A good PR description answers three things fast: why does this exist, what did it do, and what should I look at? Use this exact structure, and keep every section short — a reviewer should grasp the change in under a minute.
Title
Meaningful, and about impact — what the change does for the product or system, not how it's implemented. Never a branch name, a file path, or "fix stuff".
Body
Why?
1–3 sentences: the actual problem or motivation. Pull it from the real context; don't invent one. If you genuinely don't know why, find out before opening the PR.
How?
1–2 sentences: a short technical summary for a technical reader — the approach, not a file-by-file walkthrough.
Decisions
One bullet per meaningful tradeoff, abandoned alternative, or scope choice — each with the reason. N/A if there were none.
Callouts
One bullet per spot a reviewer should look harder at — risky surfaces, things that look innocuous but have knock-on effects, one-way doors. Callouts — N/A if everything is straightforward.
Never include
- Files-changed lists — the diff already shows them.
- Test plans or "how I tested" narration.
- Risk speculation and hedging.
- Diff narration — restating the code change in prose.
That's it: an honest title, four short sections, and nothing the diff already says.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ShivaeDev
- Source: ShivaeDev/pardes
- License: MIT
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.