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.
npx claudepluginhub nvk/stepbystep --plugin stepbystepLLM-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.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
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.
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).
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
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.