Skip to content
Agentmart
Submit a tool

triage-report

Produce a structured, evidence-graded support triage report.

Skill by c-mongan

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/c-mongan-triage-report

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Produce a structured, evidence-graded support triage report.

Use cases: documents

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/triage-report

What's inside

Skill name
triage-report
Description
Produce a structured, evidence-graded support triage report.
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • triage-report-template.md · references/

SKILL.md (first lines)

# Triage Report

Use [`references/triage-report-template.md`](references/triage-report-template.md) (in this skill's directory) as the canonical report structure. Keep its section headings unchanged: the CI structure check and downstream tooling rely on them.

## Rules

- Every important claim must map to a source.
- Separate customer-provided facts from facts independently verified by tools.
- Include rejected hypotheses when they prevent repeated work.
- Include unknowns instead of hiding uncertainty.
- Keep the customer response free of internal-only detail.
- Escalate when support cannot verify or resolve the issue with available evidence.

## Confidence

- **Confirmed by data:** direct evidence from the customer's own system (logs, events, traces, account state or a reproduction) proves the cause. Docs, release notes or a matching known issue alone are not enough; use Likely.
- **Likely based on pattern match:** the evidence points strongly to one cause, but one or more facts remain unverified.
- **Suspected, needs human verification:** plausible, but not enough evidence to act as if true.

## Pre-Send Check

Before considering the report done:

1. Verify that the root-cause confidence matches the evidence.
2. Check that all sensitive data is redacted.
3. Confirm that known-issue search includes at least two symptom-specific queries for bug-shaped tickets.
4. Confirm that the recommended next action is specific and minimal.

From c-mongan/support-triage-agent-template, MIT.

More from c-mongan/support-triage-agent-template

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 7, 2026 (22 days ago)
Last release
Oct 7, 2026 (22 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from c-mongan

Cite this page

triage-report skill. Agent Mart. https://agentmart.dev/skills/c-mongan-triage-report (last updated 2026-10-24)