Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
npx claudepluginhub bjornjee/skills --plugin skillsStrict Go code reviewer that enforces evidence-based principles and project-specific rules from CLAUDE.md/AGENTS.md/LEARNINGS.md. Use for any Go change. Reports only findings backed by a cited rule and a concrete fix — never taste calls.
Performance analysis and optimization specialist. Use PROACTIVELY for identifying bottlenecks, optimizing slow code, reducing bundle sizes, and improving runtime performance. Profiling, memory leaks, render optimization, and algorithmic improvements.
Strict Python code reviewer that enforces evidence-based principles and project-specific rules from CLAUDE.md/AGENTS.md/LEARNINGS.md. Use for any Python change. Reports only findings backed by a cited rule and a concrete fix — never taste calls.
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
Test-Driven Development guide enforcing strict RED → GREEN → REFACTOR. Use PROACTIVELY for new features, bug fixes, and refactors. Walks the discipline explicitly and refuses to write implementation before a failing test exists. Stack-aware: speaks `make test`, Go (`-race`, mockery), and Python (pytest).
Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Evidence-first repo execution workflow for ECC. Use when the user wants a command run, a repo checked, a CI failure debugged, or a narrow fix pushed with exact proof of what was executed and verified.
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Harness-native ECC plugin for engineering teams - 63 agents, 251 skills, 79 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
v9.42.3 — Patch release for cursor-agent smoke checks in untrusted workspaces. Run /octo:setup.
AI-powered development tools for code review, research, design, and workflow automation.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Multi-agent tmux dashboard with skills, hooks, and workflow automation
Personal skills, agents, and rules for Claude Code.
This plugin is a pure configuration plugin — rules, skills, and agents only. It ships no hooks, no scripts, and no runtime code.
Dashboard/runtime hooks and the generic workflow skills (/feature, /fix, /pr, /chore, /investigate, /refactor) and the generic review agents (code-reviewer, planner, security-reviewer, tdd-guide, build-error-resolver) are provided by the separate bjornjee/agent-dashboard plugin. Install both side-by-side for the full experience.
/plugin marketplace add bjornjee/skills
/plugin install bjornjee-skills@bjornjee-skills
skills/ Canonical workflow and specialty skills (slash commands)
agents/ Specialized subagents
.claude/rules/ Rules and guidelines (symlinked into ~/.claude/rules/)
.claude-plugin/ Claude plugin manifest + marketplace
plugins/skills/ Codex plugin package; plugins/skills/skills is a symlink → ../../skills
.agents/plugins/ Codex marketplace pointer (marketplace.json)
scripts/ Helper scripts (rules symlink installer, codex plugin link verifier)
Both plugins read from the same skills/ directory: the Claude plugin loads it directly, and the Codex plugin sees it through plugins/skills/skills → ../../skills. There is no second copy to keep in sync.
| Skill | Description |
|---|---|
/agent-harness-construction | Design and optimize AI agent action spaces, tool definitions, and observation formatting |
/agent-introspection-debugging | Structured self-debugging workflow for AI agent failures |
/agentic-engineering | Eval-first execution, decomposition, and cost-aware model routing |
/claude-api | Anthropic Claude API patterns for Python and TypeScript |
/context-budget | Audit Claude Code context window consumption across agents, skills, MCP servers, and rules |
/git-workflow | Git branching, commits, merge vs rebase, conflict resolution |
/github-ops | GitHub repository operations and automation via gh CLI |
/golang-patterns | Idiomatic Go patterns and conventions |
/golang-testing | Go testing patterns (table-driven, subtests, benchmarks, fuzzing) |
/hookify-rules | Create hookify rules and configure hook syntax |
/mcp-server-patterns | Build MCP servers with Node/TypeScript SDK |
/regex-vs-llm-structured-text | Decision framework for choosing between regex and LLM for parsing |
/safety-guard | Prevent destructive operations when working on production systems |
/search-first | Research-before-coding workflow |
/strategic-compact | Suggests manual context compaction at logical intervals |
/terminal-ops | Evidence-first repo execution workflow |
| Agent | Description |
|---|---|
go-reviewer-strict | Strict Go code reviewer enforcing evidence-based principles from CLAUDE.md/AGENTS.md |
performance-optimizer | Performance analysis and optimization specialist |
python-reviewer-strict | Strict Python code reviewer enforcing evidence-based principles |
refactor-cleaner | Dead code cleanup and consolidation specialist |
| File | Scope | Description |
|---|---|---|
core.md | All | KISS, DRY, workflow phases, agent dispatch, model selection |
python.md | **/*.py | PEP 8, Pydantic, pytest, tooling |
golang.md | **/*.go | Idiomatic Go conventions |
fastapi.md | **/*.py | Service layer, DI, async SQLAlchemy, soft delete |
react-native.md | **/*.ts{,x} | Expo, worktree isolation, Metro ports |
ai-ml.md | **/evals/** | Eval pipelines, prompt testing, experiments |
Run scripts/install-rules-symlinks.sh to symlink these into ~/.claude/rules/ so Claude Code loads them at user scope.
This repo includes configuration for OpenAI Codex CLI so you can install the same workflow skills in Codex or delegate isolated coding tasks from Claude Code.
Add this repo as a Codex marketplace and install the skills plugin. The marketplace pointer at .agents/plugins/marketplace.json directs Codex at the packaged plugin in plugins/skills/.
codex plugin marketplace add github.com/bjornjee/skills
codex plugin add skills@bjornjee-skills
Restart Codex after adding the marketplace if the plugin list is already open.
The Codex package follows the official plugin layout:
plugins/skills/
.codex-plugin/plugin.json
skills/ # symlink → ../../skills (canonical)