⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

bug-from-user

@rockscy⭐ 10 stars

Convert a vague user complaint into a reproducible bug report a solo dev can act on. Use when the user pastes a confusing customer message, says "user says it's broken but I can't repro", "this email makes no sense", or wants to triage a bug report.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐ 10 on GitHubGitHub ↗

Growing

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

solo-skills

Claude Code skills for people who ship alone.

License: MIT Skills

English | 简体中文

curl -fsSL https://raw.githubusercontent.com/rockscy/solo-skills/main/install.sh | bash

What is this?

A small, opinionated set of Claude Code skills for the tasks solo founders and indie devs actually do every day: writing launch tweets, replying to awkward customer emails, running a 5-minute personal standup, turning a vague bug report into something actionable, deciding what to ship next when you're alone with the call.

Most skill packs assume you have a team. This one assumes you don't.


Why?

Most skill packssolo-skills
Audience"Real engineers" (broad)Solo founders, indie devs
Boundaries"Use when…" only"Use when…" AND "Do NOT use when…"
ExamplesOften abstractWorked input → output for every skill
InstallManual copyOne-line curl | bash

The "Do NOT use when…" section is the core differentiator. Force-applying a framework when it doesn't fit is the #1 way solo devs waste a Saturday. Every skill in this pack tells you when it should not fire.


Skills

SkillWhat it does
ship-decisionForce a fast, regret-minimizing call between 2–3 product options.
launch-tweetDraft a launch tweet or 3–4 tweet thread, no hype words.
changelog-from-commitsConvert raw git log into user-facing release notes.
bug-from-userConvert a confusing customer message into a reproducible bug report.
standup-solo5-minute personal standup: shipped / blocked / today's #1.
email-customerPolite-but-firm reply to refunds, scope creep, complaints.
postmortem-solo≤350-word blame-free postmortem after a missed deadline or outage.

Install

Option 1: One-liner (recommended)

curl -fsSL https://raw.githubusercontent.com/rockscy/solo-skills/main/install.sh | bash

This drops the seven skill directories into ~/.claude/skills/. Existing files of the same name are never overwritten — the installer skips them and tells you which.

Option 2: Manual

git clone https://github.com/rockscy/solo-skills.git
cp -r solo-skills/skills/* ~/.claude/skills/

Verify

Open Claude Code and type /. You should see ship-decision, launch-tweet, etc. in the skill list.


How to use

Inside any Claude Code session, the skills auto-trigger when you describe a matching situation. You can also invoke explicitly:

/ship-decision

I'm stuck choosing between rebuilding my landing page in Framer or sticking with my hand-coded Next.js page. I have ~6 hours of focused time this weekend.

Claude reads SKILL.md, applies the framework, and responds in the prescribed format.


Design principles

  1. Boundaries first. Every skill leads with when not to use. Wrong skill > no skill.
  2. One sentence beats one paragraph. Output formats enforce brevity.
  3. Show input → output. Every skill includes a worked example, not just guidelines.
  4. No corporate voice. No "I'm excited", no "per our policy", no emoji decoration.

Contributing

PRs welcome. Read CONTRIBUTING.md. The bar:

  • Skill solves a real problem a solo dev hits monthly or more often.
  • Has a "When NOT to use" section. (Hard requirement.)
  • Has at least one worked input → output example.
  • Output format is concrete (table, structured text, fixed sections) — no "be helpful" vibes.

License

MIT — copy, modify, ship, sell. No attribution required, but it's appreciated.

// HOW IT'S BUILT

KEY FILES

skills/bug-from-user/SKILL.mdREADME.md

// REPO STATS

10 stars