Skip to content
Agentmart
Submit a tool

github-issue-triage

Read, analyze, and draft high-signal GitHub issue responses from bounded provider evidence without silently mutating the repository.

Skill by runxhq

IndexedApache-2.0★ 104
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/runxhq-github-issue-triage

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

Read, analyze, and draft high-signal GitHub issue responses from bounded provider evidence without silently mutating the repository.

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
Runs as
Node.js package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/github-issue-triage

What's inside

Skill name
github-issue-triage
Description
Read, analyze, and draft high-signal GitHub issue responses from bounded provider evidence without silently mutating the repository.
License
Apache-2.0
Instructions
95 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (12)

  • SKILL.md
  • gh · fixtures/bin/
  • composes-in-graph.yaml · fixtures/
  • default-reads-and-drafts-response.yaml · fixtures/
  • default-requires-github-binding.yaml · fixtures/
  • discover-bounded-snapshots.yaml · fixtures/
  • invented-issue-ref-rejected.yaml · fixtures/
  • respond-from-snapshot.yaml · fixtures/
  • composed.graph · fixtures/support/
  • github-issue-triage.mjs
  • catalog.md · references/
  • run.yaml

SKILL.md (first lines)

# GitHub Issue Triage

Turn a noisy issue queue into one evidence-backed next action. The skill helps a
maintainer decide which thread deserves attention and how to respond without
silently mutating a repository or inventing state that is not present in the
thread snapshot.

Discovery and response are separate jobs. The default `provider-respond` runner
reads one issue through the GitHub instance selected here, the signed-in `gh`
session or a stored token, binds the returned snapshot and readback into the
receipt, and turns it into a concise profile,
recommended posture, draft reply, and follow-up plan. `discover` and `respond`
remain explicit supplied-evidence lanes for offline queues and replay. Every
analysis lane stops at a draft. Select `post` explicitly to consume that exact
packet under a scoped comment grant and require provider readback without
repeating triage.

## When to use it

Use the default runner when the operator has a repository and issue number and
wants current provider-grounded evidence. Use `discover` for a supplied issue
queue and `respond` when an exact snapshot is already available or a receipt is
being replayed. Use `code-intake` when the material must first become an
engineering change request, and `github-issue-to-pr` only after explicit promotion to
implementation.

Do not use the analysis runners to close, label, assign, comment on, or promise
work in a repository. They prepare the maintainer decision and draft only; the
explicit `post` runner performs only the exact accepted comment.

## Evidence and provider boundary

Every candidate and response is bound through Runx's native data digest to the
exact issue snapshot or bounded snapshot set. `provider-respond` obtains that
snapshot through `github/issue.read` with `repo.read`, and the provider
operation remains in the sealed run alongside the draft. `post` comments
through `github/comments.create`, which completes only when the read-back
comment matches the exact accepted body. Supplied snapshots are labelled as
such rather than promoted to provider readback.

Ground the assessment in the thread, repository facts, receipts, and supplied
maintainer context. Do not infer contributor intent, reproduce hostile language
unnecessarily, or claim a fix, release, or investigation exists unless the
snapshot proves it.

## Inputs and result

`discover` accepts a bounded `issue_snapshots` set, a selection `query`, and
optional maintainer constraints. It returns a ranked triage queue whose ids and
rationales bind to the admitted snapshot index.

`provider-respond` accepts `owner/name`, an issue number, and optional objective
and maintainer context. `respond` accepts the same analysis context with one
already obtained `issue_snapshot`. Both return the issue profile, response
strategy, unsent response draft, and concrete follow-up actions with
`delivery_status: not_sent`; the provider status distinguishes live readback
from supplied evidence.

## Stop conditions

- Return `needs_more_evidence` or `needs_human` when a thread is ambiguous,
  hostile, unsafe, underspecified, or outside declared maintainer posture.
- Reject issue ids, repository state, labels, commitments, or completed work not
  present in the admitted snapshot.
- Do not turn maintainer context into provider evidence.
- Refuse when no GitHub instance is selected, or the selected one cannot read
  the issue; the skill never handles a raw token.
- Keep mutation out of the analysis lanes. An accepted draft moves explicitly
  to `post`, which requires scoped GitHub comment authority and provider
  readback.

## Example

A queue contains a reproducible regression, a broad feature request, and a stale
question. Discovery can prioritize the regression and explain why. Response can
draft a concise request for the missing version detail or describe a verified
workaround. It cannot say “fixed in the next release” unless the snapshot or
other admitted evidence establishes that fact. Posting requires the separate
`post` invocation and its comment-scoped grant.

## Agent task contracts

### `github-issue-triage-discover`

Rank only issues in the supplied index. Return bounded candidates and the
selection rationale an operator needs to review the ranking. Never invent issue
ids, provider state, promises, or completed work.

### `github-issue-triage-respond`

Draft one helpful maintainer response grounded only in the admitted issue
evidence. Preserve repository, issue number, title, and state exactly. Do not
claim work is complete unless the snapshot proves it. The draft is not sent.

From runxhq/runx, Apache-2.0.

More from runxhq/runx

Signals

Stars
104
Forks
109
Open issues
16
Contributors
16
Last commit (this folder)
Oct 21, 2026 (8 days ago)
Last release
Oct 18, 2026 (11 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Website
runx.ai
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from runxhq

Cite this page

github-issue-triage skill. Agent Mart. https://agentmart.dev/skills/runxhq-github-issue-triage (last updated 2026-10-24)