CtrlK
BlogDocsLog inGet started
Tessl Logo

triage

Bulk-triage unresolved Jira bugs with AI-driven recommendations and an interactive HTML report. Scan also loads recently resolved bugs for regression matching in analyze. Use when triaging a project backlog, prioritizing bug fixes, identifying candidates for automated fixing, or reviewing stale issues. For one bug in depth (no artifacts), use /assess. Activated by commands: /run, /start, /scan, /analyze, /report, and /assess.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is triage in flightctl/ai-workflows

SKILL.md
Quality
Evals
Security

Triage Workflow Orchestrator

Quick Start

  1. If the user invoked /run, read skills/run.md and follow it — this drives all phases end-to-end without pausing
  2. If the user invoked /assess, read skills/assess.md and follow it — full single-issue triage in chat (does not write analyzed.json / report.html)
  3. If the user invoked a specific bulk phase command (/start, /scan, /analyze, /report), read the corresponding skill file from skills/{phase}.md and execute it
  4. If the user provided a Jira project key but no specific command, start with skills/start.md to validate access and create the workspace, then proceed to skills/scan.md
  5. If no project key was provided, start with skills/start.md to gather it

If a step fails or produces unexpected output, stop and report the error to the user. Do not advance to the next phase. Offer to retry the failed step or escalate.

For principles, hard limits, safety, quality, and escalation rules, see guidelines.md.

Repository
amir-yogev-gh/ai-workflows
Last updated
First committed

Canonical home

flightctl/ai-workflows
In sync

since Sep 17, 2026

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.