StepByStep turns the current session's research, summary, plan, or partially completed work into an interactive one-step-at-a-time instruction mode.
Invoke it with:
/stepbystep/sbsstepbystepsbs@stepbystepThe plugin asks for one concrete action at a time, defines a checkpoint test,
then waits for feedback such as pass, next, back, regress, revise,
skip, or done.
Codex uses the repo-local marketplace:
.agents/plugins/marketplace.json
plugins/stepbystep/.codex-plugin/plugin.json
plugins/stepbystep/skills/stepbystep/SKILL.md
Install or add this repository as a Codex marketplace, then enable
stepbystep@stepbystep.
Claude Code uses the Claude plugin package:
.claude-plugin/marketplace.json
claude-plugin/.claude-plugin/plugin.json
claude-plugin/commands/stepbystep.md
claude-plugin/commands/sbs.md
claude-plugin/skills/stepbystep/SKILL.md
During development, load it directly:
claude --plugin-dir ./claude-plugin
OpenCode discovers project skills and commands from:
.opencode/skills/stepbystep/SKILL.md
.opencode/commands/stepbystep.md
.opencode/commands/sbs.md
.agents/skills/stepbystep/SKILL.md
The package mirror also lives at:
plugins/stepbystep-opencode/
Pi Coding Agent discovers Agent Skills from:
.pi/skills/stepbystep/SKILL.md
.agents/skills/stepbystep/SKILL.md
The package mirror also lives at:
plugins/stepbystep-pi/
Use /skill:stepbystep to force the skill in Pi, or ask naturally with sbs
or stepbystep.
.agents/plugins/marketplace.json - local Codex marketplace manifest.claude-plugin/marketplace.json - Claude Code marketplace manifestclaude-plugin/ - Claude Code plugin package.opencode/ - project-local OpenCode skills and commands.pi/ - project-local Pi skill.agents/skills/ - portable Agent Skills discovery pathplugins/stepbystep/ - Codex plugin packageplugins/stepbystep-opencode/ - OpenCode package mirrorplugins/stepbystep-pi/ - Pi package mirrorscripts/sync-mirrors.sh - refresh all mirrors from the Codex skill sourcetests/test_stepbystep_plugin.sh - structural validationRun validation:
./scripts/sync-mirrors.sh
./tests/test_stepbystep_plugin.sh
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.
LLM-compiled knowledge base. Topic-isolated wikis, parallel multi-agent research (topic + question auto-detect), thesis-driven investigation with verdicts, repo assessment, Obsidian dual-linking, retardmax mode, and --min-time sustained research.
Local-first health intelligence: event-driven de-identified result reviews, diagnostic gap closure, least-harm protocols, medication collateral-damage ledgers, capture-aware research queues, and health-assessment-v2 integration.
npx claudepluginhub nvk/stepbystep --plugin stepbystepTools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
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
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.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.