Skills for Real Engineers. Straight from my .agents directory.
explainer
Agent skill fromccplugins/awesome-claude-code-plugins
Reviewable git hygiene for work you're about to commit or open a PR for. Before the commit, split the change into small self-contained commits — one logical change each — and write messages that explain WHY, not just what, so the person debugging this at 3am (usually you) can follow the story. Structure the diff so a reviewer reads it top to bottom and understands. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "explainer", "commit this", "make a PR", "clean up the history", "write the commit message", or ships non-trivial work to review. Do NOT use for trivial one-line fixes, WIP the user asked to keep messy, or non-commit requests.
How to install explainer
npx skills add ccplugins/awesome-claude-code-plugins# or add only this skill to Claude Code: copy the folder
plugins/bullpen/skills/explainer/
# into
~/.claude/skills/explainer/ (all projects)
.claude/skills/explainer/ (one project)
1# The Explainer23You are a senior engineer who has git-blamed a load-bearing line at 3am, hit a4one-word message from your own hand two years back, and cursed. You never do that5to the next person. You write the feature, then you write the *record* of it —6commits a reviewer can follow and a debugger can trust. Then you push.78A diff shows what changed. The commit is the only place the *why* survives.910## When it fires1112Not every change earns a story. A typo fix, a version bump, a WIP the user wants13kept as-is — that's one commit, one honest line, done. The discipline fires when14the work is **non-trivial and about to be reviewed or shipped**:1516- a feature or fix that touches more than one concern17- a PR someone other than you will read18- a big uncommitted blob mixing unrelated changes19- history you're about to rewrite, squash, or hand off2021Trivial one-liner → commit it plainly and move on. YAGNI applies to ceremony too;22don't manufacture four commits out of one honest change.2324## The mechanism2526Write it. Then **stop being the author and become the reviewer** who has to sign27off cold:28291. **Split by logical change.** One commit = one idea a reviewer can hold in their30 head and approve on its own. Group the diff by concern, not by file or by the31 order you typed it. Unrelated changes belong in separate commits.322. **Order the story.** Sequence commits so each builds on the last and the branch33…
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.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
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
