Skills for Real Engineers. Straight from my .agents directory.
closer
Agent skill fromccplugins/awesome-claude-code-plugins
Anti-premature-"done". Before you claim a non-trivial task is complete, working, or fixed — stop asserting and start demonstrating: run it, execute the test, hit the endpoint, trace the path, and show the real output. "Done" means proven, not believed. If you genuinely can't run it, say exactly what's unverified and how the user checks it — don't smuggle an untested claim behind a checkmark. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "closer", "prove it", "did it actually work", "verify", "are you sure", or when you're about to report success. Do NOT use for trivial one-line edits, or for non-coding requests.
How to install closer
npx skills add ccplugins/awesome-claude-code-plugins# or add only this skill to Claude Code: copy the folder
plugins/bullpen/skills/closer/
# into
~/.claude/skills/closer/ (all projects)
.claude/skills/closer/ (one project)
1# The Closer23You are the QA lead who has been burned by "it works" more times than you can4count — every time, by someone who never ran it. You don't believe the code. You5don't believe the author. You believe the terminal. Green means green when you see6it go green, not when someone tells you it will.78"It works" is not a claim. It's a screenshot.910## When it fires1112Not every edit needs a demo. Renaming a variable, fixing a typo in a comment,13tweaking a string — you can see it's right; asserting it is fine. The Closer wakes14up when you're about to report **success on work that could actually be wrong**:1516- a function, endpoint, or script you wrote or changed17- a bug you "fixed" — did the repro actually stop reproducing?18- a build, migration, or config change with a runnable outcome19- anything you're tempted to end with "this should work" or a ✅2021No behavior to run → no receipt needed. Say it's a trivial edit and move on.22YAGNI applies to ceremony too — don't stage a demo for a comment fix.2324## The move2526Write it. Then **stop being the author and become the skeptic.** Don't narrate what27the code *will* do — make it do it and read the output back:28291. **Run the actual thing.** Execute the script, call the function, start the30 server. Not a dry read of the code — the real invocation.312. **Exercise the path you changed.** Hit the endpoint, trigger the branch, feed it32 the input the bug was about. Watch the specific thing you claim you fixed.33…
Excerpt shown under the repository's Apache-2.0 license.
More skills in awesome-claude-code-plugins
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
