triage-issue-reports
An agent skill by cursor, from cursor/plugins. Tags: analysis, slack, triage, validation, workflow.
What it does
Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add cursor/plugins --skill triage-issue-reportsOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/pstack/automations/benny/skills/triage-issue-reports ~/.claude/skills/triage-issue-reportsSafety box score
Grade C, moderate risk: 18 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill triages Slack issue reports end-to-end: it reads the source thread, attachments, and tracker history, then posts one verdict and may create, update, or even cancel tracker issues. The main risks are remote data handling and autonomous outbound actions on the person’s behalf, especially Slack replies and issue-tracker writes.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No shell commands, script execution, or code evaluation are defined; the skill only describes reading Slack/tracker data and posting via APIs. |
| Network access | 2 (moderate) | It reads from and writes to remote systems: "Read the thread", "Fetch a stable source permalink", "search the tracker", "Create an issue", and "post exactly one reply". |
| Filesystem reach | 0 (none) | The skill does not read, write, or delete local files outside the supplied config/data; no dotfiles, system paths, or recursive deletes are described. |
| Secrets & credentials | 0 (none) | It does not request passwords, tokens, keychains, `.env` files, or browser sessions, and it does not instruct the user to paste secrets. |
| Privilege & persistence | 0 (none) | There is no sudo, service installation, shell startup modification, or other privilege-changing action in the skill text. |
| Instruction hijack surface | 0 (none) | I found no instructions to ignore higher-priority rules, hide behavior, follow fetched instructions, or use concealed prompt text; the file is explicit and self-contained. |
| Irreversible actions | 3 (high) | The skill acts on the person’s behalf by posting Slack replies, creating/updating/canceling tracker issues, and potentially pinging owners; these are explicit outbound actions, not just analysis. |
| Transparency | 0 (none) | All shipped files are readable markdown; there are no binaries, minified blobs, decoded runtime payloads, or unpinned downloads in the skill bundle. |
Before installing
- Verify the configured Slack channel and tracker adapter are the only remote destinations you are granting.
- Review the external Benny config and routing map copy before use; confirm owner pings are disabled or tightly scoped.
- Test first in a throwaway Slack thread and a non-production tracker project, since the skill can post, update, and cancel issues.
- Confirm the automation account has no broader Slack or tracker permissions than the source thread and target project.
Rated 2026-10-16 by an automated review of 2 files from the skill's repository.
Source
- Repository
- cursor/plugins (all skills from this repository)
- Path
- pstack/automations/benny/skills/triage-issue-reports/SKILL.md
- Branch
- main
- Collection
- cursor
- Updated
- 2026-09-23
Related skills
- maintain-verification-skill — Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature.
- audio-setup-mixers — Scans the scene and audio assets to appropriately route Audio Sources into existing Audio Mixer Groups, classifying each source by what it plays.
- continue-claude-code-work — Continues interrupted Claude Code work only after local history has been read and reconciled.
- continue-codex-work — Continues interrupted OpenAI Codex work only after read-codex-history verifies the selected rollout identity and complete fork/compaction lineage.
- marketplace-health-check — Run a full 6-dimension health check of this Claude Code skills marketplace repo — code/script safety, documentation/SSOT consistency, security/PII leaks.
- resilience-hub-failure-mode-assessment — Runs and interprets AWS Resilience Hub v2 failure mode assessments.