Agent skill

Maintainer Triage

by mohitagw15856 in mohitagw15856/pm-claude-skills

Get an open-source repo's issue backlog from 400-and-drowning to triaged-and-honest in one pass — a label taxonomy that encodes decisions, batch triage rules you can apply in seconds per issue…

MITAuto-check passedProduct & Project Management

Install Maintainer Triage

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill maintainer-triage -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills maintainer-triage --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/maintainer-triage .claude/skills/maintainer-triage && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
maintainer-triage
GitHub stars
1.4k
Token cost
~1.4k tokens
SKILL.md length
672 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Get an open-source repo's issue backlog from 400-and-drowning to triaged-and-honest in one pass — a label taxonomy that encodes decisions, batch triage rules you can apply in seconds per issue…

  • Works in 5 steps: Labels are decisions. Every open issue… → The 30-second tree. Bug without repro →… → Eat the backlog newest-first. Newest… → …
  • A maintainer says my issues are out of control
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework and Output Format, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Maintainer Triage is an agent skill from mohitagw15856/pm-claude-skills. Get an open-source repo's issue backlog from 400-and-drowning to triaged-and-honest in one pass — a label taxonomy that encodes decisions, batch triage rules you can apply in seconds per issue, saved replies that stay kind at scale, and stale-bot policy set with a conscience. Use when a maintainer says 'my issues are out of control', 'triage my backlog', 'set up labels for my repo', or dreads opening GitHub. Produces the taxonomy, the triage pass rules, saved replies, and a sustainable weekly routine.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management. It works with GitHub. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • A maintainer says my issues are out of control
  • Triage my backlog
  • Set up labels for my repo
  • Dreads opening GitHub

Example prompts

  • “my issues are out of control”
  • “triage my backlog”
  • “set up labels for my repo”
  • “/maintainer-triage”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Labels are decisions. Every open issue carries exactly one status
  2. The 30-second tree. Bug without repro → needs-repro + saved reply +
  3. Eat the backlog newest-first. Newest issues have live reporters and
  4. Saved replies stay human. Each is 2–4 sentences, warm, and ends with
  5. The routine that survives. Weekly 30 minutes: new issues to zero

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Maintainer Triage loads about 1.4k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 672 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 672 words, ~1,445 tokens.

Download SKILL.mdSave it as .claude/skills/maintainer-triage/SKILL.md (or your agent's skills folder).
name
maintainer-triage
description
Get an open-source repo's issue backlog from 400-and-drowning to triaged-and-honest in one pass — a label taxonomy that encodes decisions, batch triage rules you can apply in seconds per issue, saved replies that stay kind at scale, and stale-bot policy set with a conscience. Use when a maintainer says 'my issues are out of control', 'triage my backlog', 'set up labels for my repo', or dreads opening GitHub. Produces the taxonomy, the triage pass rules, saved replies, and a sustainable weekly routine.

Maintainer Triage Skill

An untriaged backlog isn't a to-do list — it's 400 open loops charging interest on a volunteer's conscience. The fix isn't heroic issue-closing weekends (they don't repeat); it's a system where every issue gets a decision in under a minute — reproduce/needs-info/accepted/wontfix/ someday — encoded in labels, communicated by saved replies that stay human, and maintained by a 30-minute weekly routine. Honest triage closes issues politely that will never be done, because "open forever" is the cruelest answer of all.

What This Skill Produces

  • A label taxonomy that encodes decisions, not just topics: status (needs-repro, needs-info, accepted, help-wanted, wontfix, someday) × type (bug, feature, docs, question) × effort (good-first-issue, deep-water)
  • Batch triage rules: the 30-second decision tree per issue, and the order to eat the backlog (newest-first, oldest closed honestly in bulk)
  • Saved replies for the eight recurring moments — needs-repro, duplicate, wontfix-with-respect, stale-close, "PR welcome" (said only when meant), the excited-first-contributor welcome
  • A sustainable routine: the 30-minute weekly triage block + the stale-policy settings, with the conscience switch: bugs never auto-stale
  • The backlog burn-down plan for the existing 400

Required Inputs

Ask for (if not already provided):

  • The repo: what it does, issue count, open PR count, other maintainers or solo, current label mess
  • The honest capacity: hours/week the maintainer actually has (the system is sized to this, not to the backlog)
  • The sore points: what fills the backlog (support questions? feature wishlists? real bugs?) and what the maintainer feels worst about
  • Project stance: is this a hobby, a career asset, or accidentally load-bearing infrastructure? (wontfix courage scales with clarity here)

Framework

  1. Labels are decisions. Every open issue carries exactly one status label — an issue with no status is untriaged, and the goal state is zero untriaged. Topics are optional garnish; status is the system.
  2. The 30-second tree. Bug without repro → needs-repro + saved reply + 14-day clock. Repro'd bug → accepted + severity. Feature aligned with project vision → accepted or help-wanted; not aligned → wontfix now, kindly — parking unaligned features in "someday" is deferral disguised as kindness, use someday only for genuinely-yes-later. Question → answer or convert to discussion/docs issue. Duplicate → link + close.
  3. Eat the backlog newest-first. Newest issues have live reporters and fresh context; the oldest 200 get the honest bulk pass: a pinned announcement ("triage sweep this week — issues inactive >12 months close with this message; comment to reopen") then the sweep. Reopens are signal, not failure — that's the mechanism finding the living issues.
  4. Saved replies stay human. Each is 2–4 sentences, warm, and ends with a clear next step. "PR welcome" appears only where a PR would genuinely be reviewed and merged — as a brush-off it's the most resented phrase in open source.
  5. The routine that survives. Weekly 30 minutes: new issues to zero untriaged → needs-info clock expiries → one accepted issue advanced. Stale-bot only on needs-info and question labels, never on accepted bugs. The maintainer's dread is the metric: if opening the repo stops hurting, the system is working.
Show full SKILL.md (183 more words)Show less

Output Format

## Label taxonomy (create these)
[Status set · type set · effort set — with color/description lines]

## The 30-second tree
[Decision tree, one branch per issue shape]

## Saved replies (paste into GitHub)
[The eight, each 2-4 sentences]

## Backlog burn-down
[The pinned announcement text · sweep order · reopen handling]

## Weekly 30 minutes
[The three-step routine · stale-bot config with the bugs-never-stale rule]

Quality Checks

  • Every issue shape in the tree ends in a decision + a saved reply — no branch ends in "leave it"
  • Wontfix replies give the reason and thank the reporter — respect at scale is the whole trick
  • The bulk-close announcement runs BEFORE the sweep, and reopen instructions are in the close message
  • Stale automation exempts accepted bugs explicitly
  • The routine fits the stated real hours, not the aspirational ones

Anti-Patterns

  • Do not build a 40-label topic museum — status labels are the system; taxonomy sprawl is procrastination with colors
  • Do not use "someday" as a polite graveyard — unaligned features get an honest wontfix
  • Do not auto-stale confirmed bugs; nothing burns trust faster
  • Do not write saved replies that could double as form rejections — each names the specific next step
  • Do not size the system to the backlog instead of the maintainer's hours

[[the-maintainers-no]] for the requests that need a personal no; [[first-maintainer-month]] for new maintainers; [[email-triage-system]] — the same discipline pointed at an inbox.

Example Trigger Phrases

  • "My issues are out of control."
  • "Triage my backlog."
  • "Set up labels for my repo."

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/maintainer-triage of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Maintainer Triage next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Maintainer Triage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Maintainer Triage this skillmohitagw15856/pm-claude-skills1.4k—~1.4kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Release ValidationMesh-LLM/mesh-llm3.5k—~2.6kAutomated safety check: PassApache-2.0
Final Release Reviewopenai/openai-agents-python30k—~5.4kAutomated safety check: PassMIT
Ouroboros PM InterviewQ00/ouroboros6.2k—~5.7kAutomated safety check: PassMIT
Project Managerpwrdrvr/openclaw-codex-app-server265—~1.5kAutomated safety check: PassMIT

Similar skills

  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Release Validation

    Mesh-LLM/mesh-llm

    A skill your agent uses when validating a MeshLLM release candidate or current HEAD against the last GitHub release, assembling the canonical feature/fix/modification inventory, testing locally…

    3.5k GitHub stars~2.6k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Final Release Review

    openai/openai-agents-python

    Official

    Assess a Python SDK release candidate or release plan against the previous release and recommend ship or block.

    30k GitHub stars~5.4k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed
  • Runs a guided product-manager interview that classifies each question automatically and produces a Product Requirements Document.

    6.2k GitHub stars~5.7k tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed
  • Project Manager

    pwrdrvr/openclaw-codex-app-server

    Manage GitHub issues and the GitHub Project board for the current repository, while keeping the local tracker in sync.

    265 GitHub stars~1.5k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed
  • Create Issue

    tradingstrategy-ai/frontend

    Creates a new GitHub issue with structured user story format, acceptance criteria, and project integration.

    150 GitHub stars~607 tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated 2 days ago
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated 2 days ago
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

Works with

Questions about Maintainer Triage

What does Maintainer Triage do?

Get an open-source repo's issue backlog from 400-and-drowning to triaged-and-honest in one pass — a label taxonomy that encodes decisions, batch triage rules you can apply in seconds per issue…. Maintainer Triage is an agent skill from mohitagw15856/pm-claude-skills. Get an open-source repo's issue backlog from 400-and-drowning to triaged-and-honest in one pass — a label taxonomy that encodes decisions, batch triage rules you can apply in seconds per issue, saved replies that stay kind at scale, and stale-bot policy set with a conscience.

When should I use Maintainer Triage?

Maintainer Triage fits situations like: A maintainer says my issues are out of control; triage my backlog; set up labels for my repo; dreads opening GitHub.

How do I install Maintainer Triage in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill maintainer-triage -a claude-code`. Or copy the skill folder (skills/maintainer-triage in mohitagw15856/pm-claude-skills) into .claude/skills/maintainer-triage in your project. Claude Code loads it when a task matches its description.

How do I install Maintainer Triage in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill maintainer-triage -a codex`. Or copy the skill folder (skills/maintainer-triage in mohitagw15856/pm-claude-skills) into .agents/skills/maintainer-triage in your project. Codex loads it when a task matches its description.

Can I use Maintainer Triage in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill maintainer-triage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/maintainer-triage, .gemini/skills/maintainer-triage, .github/skills/maintainer-triage and .opencode/skills/maintainer-triage in your project.

What does Maintainer Triage need to run?

SKILL.md names no scripts, command-line tools or credentials: Maintainer Triage is instructions for the agent only.

Does Maintainer Triage access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Maintainer Triage safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Maintainer Triage use?

Maintainer Triage is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Maintainer Triage use?

About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Maintainer Triage?

Skills that share tags, products or a category with Maintainer Triage: CCPM Project Management (automazeio/ccpm, 8.4k stars), Release Validation (Mesh-LLM/mesh-llm, 3.5k stars), Final Release Review (openai/openai-agents-python, 30k stars) and Ouroboros PM Interview (Q00/ouroboros, 6.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Maintainer Triage?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.