Is the Maintainer Decline skill free?

Yes. The skill itself is free from posit-dev/skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Maintainer Decline SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Maintainer Decline?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Maintainer Decline with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Maintainer Decline

Drafts issue-closure and won't-fix replies that decline while keeping contributors respected

by posit-dev · posit-dev/skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · d41b37e

Fetched SKILL.md via raw GitHub; the maintainer-decline dir contains only SKILL.md (no scripts to break), frontmatter parses with name+description, no hardcoded paths or security smells. Trigger phrasings tested — SHOULD fire: "help me write a reply closing this GitHub issue as won't-fix", "draft a polite decline for a feature I don't want to add", "tell this contributor their PR is out of scope"; should NOT: "write a cover letter declining a job offer", "draft a reply approving and merging this PR" — all 5 judged correctly. Output test: drafted a real decline reply to a mock CSV-import feature request both without and with the skill; the skill version led with the "Yeah, this is a reasonable ask" validation opener, reframed from stating the decision to stating the "we believe... net negative" principle, and tightened 3 paragraphs to one 4-sentence reply — a concrete structural shift, not just a restatement of rules.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What Maintainer Decline does

A writing-guidance skill for open-source maintainers composing replies that close, decline, or redirect issues — feature requests marked won't-fix, deprecations, design-intent explanations, or redirects to another package. It supplies eight named response patterns (duplicate, superseded, design philosophy, workaround, clarification, effort assessment, scope, redirect) with a structure for each, plus a heuristic table for picking one. Triggers when asked to draft a reply that says "no" to, or closes, a community issue or contribution.

How to install Maintainer Decline

git clone --depth 1 https://github.com/posit-dev/skills.git /tmp/maintainer-decline-src
mkdir -p ~/.claude/skills
cp -R /tmp/maintainer-decline-src/open-source/maintainer-decline ~/.claude/skills/maintainer-decline
# Pure prompt-guidance skill: single SKILL.md, no scripts, no deps, no API keys.
# Verify: cat ~/.claude/skills/maintainer-decline/SKILL.md

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Maintainer Decline

/maintainer-decline Drafts issue-closure and won't-fix replies that decline while keeping contributors respected

It also activates on plain-language prompts like these:

Write a reply declining this feature request
Close this issue as won't-fix politely
Explain why this design choice is intentional

Frequently asked questions

Is the Maintainer Decline skill free?: Yes. The skill itself is free from posit-dev/skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Maintainer Decline work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md via raw GitHub; the maintainer-decline dir contains only SKILL.md (no scripts to break), frontmatter parses with name+description, no hardcoded paths or security smells. Trigger phrasings tested — SHOULD fire: "help me write a reply closing this GitHub issue as won't-fix", "draft a polite decline for a feature I don't want to add", "tell this contributor their PR is out of scope"; should NOT: "write a cover letter declining a job offer", "draft a reply approving and merging this PR" — all 5 judged correctly. Output test: drafted a real decline reply to a mock CSV-import feature request both without and with the skill; the skill version led with the "Yeah, this is a reasonable ask" validation opener, reframed from stating the decision to stating the "we believe... net negative" principle, and tightened 3 paragraphs to one 4-sentence reply — a concrete structural shift, not just a restatement of rules.
What is the Maintainer Decline SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Maintainer Decline?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Maintainer Decline with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.