Skillsaw Issue Triage logo

Skillsaw Issue Triage

Community
stbenjam
skillsaw-issue-triage

Triage a GitHub issue filed against skillsaw — classify it (bug, feature, docs, question, other), verify its claims against the codebase, enrich it with missing details, and post one structured triage comment. Use when triaging and labeling incoming issues, not to fix them.

Overview

Publisherstbenjam
Repositoryskillsaw
Skill nameskillsaw-issue-triage
Stars
69
Forks
15
Bundled files
4
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by stbenjam on GitHub. Read the source before you install it.

Installation

Install the Skillsaw Issue Triage AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/stbenjam/skillsaw/tree/main/.agents/skills/skillsaw-issue-triage
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/stbenjam/skillsaw.git /tmp/skillsaw
mkdir -p .claude/skills
cp -r /tmp/skillsaw/.agents/skills/skillsaw-issue-triage .claude/skills/skillsaw-issue-triage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skillsaw Issue Triage in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Skillsaw Issue Triage on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Skillsaw Issue Triage is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

skillsaw Issue Triage

Triage a single open issue on the skillsaw linter. Check what kind of issue it is, check whether its claims hold up against the actual code, fill in the details it is missing, review the evidence, and leave one triage comment. This skill triages issues — never fix them here (that job belongs to skillsaw-issue-solver).

Read the detailed evaluation checklist for each classification in references/, and read only the checklist for the class the issue falls into (progressive disclosure). Keep this file lean and pull the checklist in on demand.

Step 1 — Read the Issue

Run this for the issue number you were given:

bash
gh issue view <number> --json number,title,body,labels,author,comments,createdAt

Read the title, body, and every comment before judging anything. Note the skillsaw version the reporter names (or none), and check any config, command, or file content they pasted.

Step 2 — Classify

Set exactly one primary class. When an issue spans two, pick the one that determines the next action and note the secondary in the comment.

ClassThe issue is…Evaluation checklist
bugA claim that skillsaw behaves incorrectly — wrong violation, crash, false positive/negative, bad autofixreferences/bug-evaluation.md
featureA request for new behavior — a new rule, flag, config option, output format, or tool/format supportreferences/feature-evaluation.md
documentationDocs are missing, wrong, or unclear (README, skillsaw.org, rule docs) — code behavior is not disputedreferences/other-evaluation.md
questionA usage/support question, not a defect or requestreferences/other-evaluation.md
otherDuplicate, invalid, spam, out-of-scope, or needs-more-inforeferences/other-evaluation.md

Write the class and a one-sentence rationale.

Step 3 — Verify Accuracy

Read the checklist for the chosen class now (references/*.md) and work it. Check whether the issue is accurate — do its claims match how skillsaw actually behaves?

  • For a bug: run the repro against the current code. Trace the cited behavior to the responsible rule or src/ module, then verify it. A bug you cannot reproduce, or that describes intended behavior, is not confirmed — always say so.
  • For a feature: check whether it already exists, whether it fits skillsaw's scope (core vs a rule plugin), and verify it would not break existing users.
  • For documentation / question / other: verify the underlying facts before agreeing or redirecting.

Cite what you checked with file:line references and command output — never assert a conclusion you did not verify.

Step 4 — Enrich

Add the details the issue is missing so it is actionable without a round-trip:

  • Reproduction: write a minimal repro (config + input file + command + observed vs expected) when the reporter left one out and you can construct one.
  • Locus: include the rule ID, file, and line most relevant to the issue.
  • Version / environment: include the version the behavior was verified against, and whether it still reproduces on main.
  • Related work: review duplicate or related issues and any open PR that already touches this (gh issue list / gh pr list --search).
  • Suggested labels: include labels (e.g. bug, enhancement, documentation, question, duplicate, needs-info, good-first-issue), but never apply them unless asked.

Step 5 — Decide the Recommendation

Set exactly one recommendation — this is the headline of the triage comment:

RecommendationWhen
🛠️ FIX — REPRODUCEDA real defect you reproduced or confirmed against the code (a genuinely wrong or missing doc counts here too).
✨ IMPLEMENT — GOOD IDEAAn in-scope feature worth building into skillsaw core.
🔌 PLUGINIn skillsaw's domain but niche / single-vendor — belongs in a rule plugin, not core. Link skillsaw.org/plugins/.
⛔ REJECTOut of scope, not reproduced, works-as-intended, invalid, duplicate, or answered.

Follow the class checklist to decide: a bug that reproduces → FIX, one that doesn't → REJECT; for a feature, follow the domain gate in references/feature-evaluation.md (out of domain → REJECT, niche → PLUGIN, broadly useful → IMPLEMENT).

Step 6 — Post One Triage Comment

Read references/triage-template.md, then post it as exactly ONE comment:

bash
gh issue comment <number> --body "$(cat <<'TRIAGE'
<rendered triage>
TRIAGE
)"

This skill is advisory: keep its output a recommendation for a maintainer. Post the triage comment on your own initiative, but never close, reassign, or label the issue yourself — always leave that to a human. Follow one exception only: a label action the invoking context directs — for instance, keep clearing an automation's own trigger label once you post the comment. Always carry that out.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Skillsaw Issue Triage AI skill do?

Triage a GitHub issue filed against skillsaw — classify it (bug, feature, docs, question, other), verify its claims against the codebase, enrich it with missing details, and post one structured triage comment. Use when triaging and labeling incoming issues, not to fix them.

Why use Skillsaw Issue Triage on TypingMind?

Because you install it once and use it with any model. Skillsaw Issue Triage is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Skillsaw Issue Triage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/stbenjam/skillsaw/tree/main/.agents/skills/skillsaw-issue-triage. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Skillsaw Issue Triage?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Skillsaw Issue Triage?

As many as you like. As long as a model supports skills, you can use Skillsaw Issue Triage with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Skillsaw Issue Triage AI skill free?

Yes. It is published on GitHub by stbenjam under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇