Install
$ agentstack add skill-spencerpauly-skills-repo-triage-bug ✓ 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
Triage Bug
Convert a noisy bug report into a ticket someone can act on: one-line title, repro steps, severity, area.
When to use
- Support escalates a bug.
- A teammate dumps a Slack thread or screenshot.
- The user says "triage this" or "what's this bug".
Steps
- Re-read the report once, in full. Don't start writing yet.
- Restate the symptom in one sentence as a user would say it. No internal jargon.
- Pull out repro steps even if the original report doesn't separate them. Number them 1, 2, 3.
- Note the gap between expected and actual.
- Decide severity with this rubric:
- S1 — production down, data loss, or security issue.
- S2 — common path broken, no workaround.
- S3 — broken with workaround.
- S4 — cosmetic / rare path.
- Identify the area (one of: editor, billing, auth, api, infra, marketing).
Output format
## Title
## Severity
S2
## Area
billing
## Repro
1. ...
2. ...
3. ...
## Expected vs actual
- Expected: ...
- Actual: ...
## Notes
- URLs, screenshots, affected user IDs.
Don't
- Don't open with "I think the issue is..." — the title goes first.
- Don't skip severity. Every ticket gets one, even if it's a guess.
- Don't paste raw stack traces into the title. Summarize.
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.