Maintainer Persona
Write an issue or PR for a repository you do not own so its maintainers can triage it. Measures the target's own history (reviewers, gates, body length, headings, language, how first-time PRs fare) into an editable persona file, branches by context (OSS first-time / OSS returning / another team inside your org), drafts in Japanese and translates only after approval when the target writes English, checks with a fresh reader and a slop lint baselined on the maintainers' own PRs, and gates the send. Use when filing upstream issues, sending a fix or failing-test PR to another project or team, or r
Install
npx skills add mizchi/skills --skill maintainer-personagit clone --depth 1 https://github.com/mizchi/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/maintainer-persona ~/.claude/skills/maintainer-personaPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Maintainer Persona The shape of a submission is a property of the target repository, not of the finding. Body length, title convention, whether a test is expected, who reviews and how outsiders are treated all differ between repositories, and all of them are measurable from the target's own history. In one large OSS project, of 44 PRs whose authors had never had a PR merged there, 13 were merged, 9 were closed by a maintainer and 22 were closed by an automated check. What decided the outcome was the automation, not being new. Measure the target, keep the numbers in a file, and write to them. ## When to use - Filing an issue or PR in a repository whose maintainers are not you. - Sending a failing test or a fix to another team inside your organisation. - A submission was ignored, split, or asked to be rewritten, and you want to know why before the next one. Not for: your own repositories, or deciding whether a finding is true. Verify the finding first (§3); a readable wrong mechanism does more harm than an unreadable one, because the reader believes it. ## Paths Set `SK` to the directory containing this `SKILL.md`, and run every command from your working repository (where `personas/` lives): ```bash SK=<directory of this SKILL.md> # e.g. ~/.claude/skills/maintainer-persona S=$SK/scripts A=$SK/../ai-index/scripts/slopscore.py ``` `ai-index`, `natural-writing-ja` and `natural-writing-en` are sibling skills
Details
- Skill name
maintainer-persona- Repository
- mizchi/skills
- Path
maintainer-persona/SKILL.md- Repo updated
- 18 November 2026
FAQ
What does the Maintainer Persona skill do?
Write an issue or PR for a repository you do not own so its maintainers can triage it. Measures the target's own history (reviewers, gates, body length, headings, language, how first-time PRs fare) into an editable persona file, branches by context (OSS first-time / OSS returning / another team inside your org), drafts in Japanese and translates only after approval when the target writes English, checks with a fresh reader and a slop lint baselined on the maintainers' own PRs, and gates the send. Use when filing upstream issues, sending a fix or failing-test PR to another project or team, or r
How do I install the Maintainer Persona skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add mizchi/skills --skill maintainer-persona. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Maintainer Persona popular?
It lives in mizchi/skills, which has 423 GitHub stars and 6 forks.
Related skills
Actions CI Tuning
423mizchi/skills
Use when auditing or improving GitHub Actions workflows for a project. Covers cache setup (npm/pnpm/yarn), job parallelism, shard-based test splitting, artifact handling pitfalls, and Playwright-specific patterns. Trigger on: slow CI, cache miss, flaky shard jobs, merge-reports failures, or an explicit 'tune CI' request.
AI Index
423mizchi/skills
Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English. Two layers — a deterministic lint for removable surface tells (scripts/slopscore.py, no API) and a judgment layer of typed probabilistic questions (Jev noul/score) for the tells that survive editing. Includes measured human/AI baselines, a gap-first calibration procedure, and labeled fixtures. Use when building or calibrating an AI-likeness score, or when a draft needs a defensible number rather than a vibe. For writing guidance use natural-writing-ja / natural-writing-en instead.
Apm Usage
423mizchi/skills
Reference for APM manifests, installation, targeted updates, deployment paths and lockfiles. Invoke when the user explicitly asks about APM or apm.yml, or an unfamiliar APM command/error needs exact CLI details. Do not automatically invoke for every project that happens to have installed skills.
Mcloud Local
237medusajs/medusa-agent-skills
Execute mcloud local build to reproduce a Cloud build on the local machine. Use when debugging a build-failed deployment without pushing to the tracked branch, iterating on a build fix, or testing build-variable changes locally. Requires Docker and must run inside the project's Git repo.
Gh Fix CI
423mizchi/skills
Use when GitHub Actions PR checks are failing on a pull request and need to be diagnosed or fixed. Inspects checks / logs via `gh`, drafts a fix plan, and implements only after explicit approval. Trigger on red checks, failing workflow runs, `pr is failing CI` reports — even if the user does not name a specific check. Out of scope: external CI (e.g. Buildkite) — report only the details URL.
Upstream Fix and Pin
423mizchi/skills
自分の依存ライブラリにバグや欠けている機能があり、上流に PR を出して取り込まれるまで下流プロジェクトを動かしたいときの運用。git ref pin(branch HEAD SHA → merge SHA)、`link:` への退避判断、SHA 取り扱い、pnpm v10 の build script gating まで含む。
Browse the most popular Claude skills, all git & code review skills, or write your own with the skills generator.