By xxKeefer
Opinionated engineering workflows -- investigation, planning, implementation, closure. Requires primitives.
Deep-dive investigation of a feature, bug, or technical problem. Accepts tracker tickets, wiki pages, or a plain description — delegates to /grill-it for clarification until the problem is fully understood, then creates a ticket in the project's tracker capturing the spike. Use when the user says "spike it", "spike this", "investigate this", "flesh this out", "hydrate ticket", "improve ticket", "research this", "feasibility study", or wants to fully understand a problem before committing to implementation.
Turn a /spike-it output into tracker tickets ready for /plan-it or /do-it. Decomposes the spike into demo-able blocks of work, gets user approval, resolves the epic, then creates the tickets in the issue tracker. Use when the user says "task it", "create tickets", "break into tickets", "make the tickets", or wants to turn a spike or feature breakdown into tracked issues.
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
Resolve git merge/rebase conflicts in a file using its history and the in-progress operation as context. Simple conflicts resolve automatically; complex ones (both sides added, or a migration/refactor collided with edits) pause for the user with evidence and a justified recommendation. Then follows links to conflicted test siblings and refactor parents/children. Usage: resolve-conflicts <filepath>. Use when the user says "resolve conflicts", "fix the merge", "resolve this conflict", or hands you a conflicted file.
Critically assess code review feedback before applying fixes. Accepts feedback from AI reviewers (e.g. GitHub Copilot, CodeRabbit), human reviewers, or directly as arguments. Use when user says "resolve it", "address feedback", "resolve feedback", pastes review comments, or wants to evaluate PR suggestions. Do NOT blindly trust the reviewer — analyze validity, trade-offs, and alternatives first.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code skills for idiomatic, agnostic workflows. Organized into domains.
| Path | Holds |
|---|---|
skills/ | The domain plugins -- one directory per domain (see table below). |
hooks/ | Claude Code hook holders (e.g. tool-policy) -- installable guardrails. |
scripts/ | Supporting tooling skills depend on (e.g. obsidian/ -- journal Templater scripts). |
statusline/ | The self-contained Claude Code status line script, installed by /setup-statusline. |
output-styles/ | Claude Code output styles (e.g. Terse.md). |
.claude-plugin/ | Marketplace registry (marketplace.json). |
| Domain | Skills | Purpose |
|---|---|---|
| primitives | grill-it, explain, look-up, write-to-file, caveman, handoff, update-handoff, do-next, tabular-analysis | Foundational building blocks |
| developer | research-it, spike-it, task-it, plan-it, do-it, tdd, tweak-it, hunt-it, fix-it, happy-path, resolve-it, resolve-conflicts, document-it, explain-it | Engineering lifecycle |
| journal | yearly, monthly, weekly, daily, reflect, update-occasions-config | Life admin + personal growth |
| projects | new-project, capture-goals, refine-task, schedule-goals, project-status, summarize-sprint, close-project | Long-running goal management |
| meta | audit-workflow, write-a-skill, migrate-a-skill, retire-a-skill | Skills about skills |
| omen | scaffold-setting, doctor-setting, plan-session, log-session, log-cannon, log-npcs, log-place, log-progression, make-lore, make-blurb, make-summary | Creative -- TTRPG, worldbuilding |
| scribe | add-procedure, edit-article, define-concept, define-term, define-language, take-a-note, triage-notes, teach | Capture vault procedures + edit notes |
| nix-manager | add-it, remove-it, rice-it, refine-it, debug, explain | NixOS config management |
| utility | setup-pre-commit, setup-git-guardrails, setup-skill-tally, setup-statusline, configure-obsidian-kanban | Dev-environment setup |
| experimental | lobotomize, patch-doctor | Skills on probation |
| deprecated | debrief | Holding pen for skills awaiting a keep/kill decision |
Add to ~/.claude/settings.json:
{
"extraKnownMarketplaces": {
"xxkeefer-skills": {
"source": {
"source": "directory",
"path": "/path/to/this/repo"
}
}
},
"enabledPlugins": {
"primitives@xxkeefer-skills": true,
"developer@xxkeefer-skills": true,
"journal@xxkeefer-skills": true,
"projects@xxkeefer-skills": true,
"meta@xxkeefer-skills": true,
"omen@xxkeefer-skills": true,
"scribe@xxkeefer-skills": true,
"nix-manager@xxkeefer-skills": true,
"utility@xxkeefer-skills": true,
"experimental@xxkeefer-skills": true,
"deprecated@xxkeefer-skills": true
}
}
primitives is required by all other domains. Enable whichever domains you need.
plugin.json (e.g. 1.0.0 -> 1.0.1)mainSeveral skills were inspired by or adapted directly from Matt Pocock's skills repo:
Thanks Matt for sharing these publicly.
NixOS config management -- add, remove, rice, refine, debug, and explain. Requires primitives.
Personal skills on probation. Promote to a real domain once usage justifies it; demote to `deprecated` if it doesn't.
Long-running, goal-oriented project management for Obsidian. Stateful per-project workspaces, Kanban boards, and a bridge into the journal. Requires primitives; interfaces with journal.
Personal skills awaiting a keep/kill decision. Disable freely; delete once confirmed unused.
Dev-environment setup skills -- pre-commit hooks, git guardrails, skill-usage tallying, statusline install, and obsidian-kanban configuration. Isolated so they're easy to maintain or retire.
npx claudepluginhub xxkeefer/skills --plugin developerCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,642 supported skills.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.