Skills Reference
Skills Reference
Section titled “Skills Reference”PopKit provides 51 reusable skills across 4 plugins. Skills provide specialized automation for common development tasks.
Invocation Modes
Section titled “Invocation Modes”PopKit intentionally exposes skills in both direct and orchestrated forms:
| Mode | Typical syntax | Use case |
|---|---|---|
| Workflow command | /popkit-<plugin>:<command> | Daily/default usage |
| Direct skill invocation | /pop-... or /skill invoke pop-... | Advanced/targeted usage |
Examples:
/popkit-dev:nextwrapspop-next-actionwith command-level parsing and formatted output./popkit-ops:assess securityroutes into thepop-assessment-securityskill.
Note: depending on client/version, you may see direct-skill entries as bare /pop-* aliases.
popkit-core (15 skills)
Section titled “popkit-core (15 skills)”Foundation skills for project management, embedding, and plugin operations.
pop-analyze-project
Section titled “pop-analyze-project”Description: Comprehensive codebase analysis discovering architecture, patterns, dependencies, testing coverage, and improvement opportunities.
Use when: Starting work on an unfamiliar project or needing to understand a codebase.
/popkit-core:pop-analyze-projectpop-auto-docs
Section titled “pop-auto-docs”Description: Generate comprehensive documentation from codebase analysis - creates README sections, API docs, migration guides, and examples.
/popkit-core:pop-auto-docspop-bug-reporter
Section titled “pop-bug-reporter”Description: Capture bug context, generate reports, and optionally create GitHub issues or share patterns.
/popkit-core:pop-bug-reporterpop-cloud-signup
Section titled “pop-cloud-signup”Description: Create PopKit Cloud account, generate API key, and configure local connection.
/popkit-core:pop-cloud-signuppop-dashboard
Section titled “pop-dashboard”Description: Multi-project dashboard showing health scores, recent activity, and quick actions across all registered projects.
Use when: Switching between projects, checking overall status, or managing project registry.
/popkit-core:pop-dashboardpop-doc-sync
Section titled “pop-doc-sync”Description: Synchronize documentation with codebase - updates AUTO-GEN sections in CLAUDE.md, validates cross-references, and reports stale documentation.
/popkit-core:pop-doc-syncpop-embed-content
Section titled “pop-embed-content”Description: Manage project embeddings - embed skills, agents, commands, and MCP tools for semantic discovery. Handles rate limiting, incremental updates, and status reporting.
/popkit-core:pop-embed-contentpop-embed-project
Section titled “pop-embed-project”Description: Embed project-local skills, agents, and commands for semantic search. Use after creating items manually or to update embeddings.
/popkit-core:pop-embed-projectpop-mcp-generator
Section titled “pop-mcp-generator”Description: Generate custom MCP server with semantic search, project-aware tools, and health monitoring capabilities.
Use when: Setting up project-specific development tools or after analyzing a codebase.
/popkit-core:pop-mcp-generatorpop-plugin-test
Section titled “pop-plugin-test”Description: Run comprehensive tests on plugin components. Validates hooks, agents, skills, and plugin structure across all PopKit packages.
/popkit-core:pop-plugin-testpop-power-mode
Section titled “pop-power-mode”Description: Multi-agent orchestration system using Claude Code’s native background agents for true parallel collaboration. Enables shared context, sync barriers between phases, and coordinator oversight.
Use when: Complex tasks benefiting from parallel execution (epics, large refactors, multi-phase features).
/popkit-core:pop-power-modepop-project-init
Section titled “pop-project-init”Description: Initialize .claude/ structure and add PopKit section to CLAUDE.md without overwriting. Detects conflicts, creates config, prompts for Power Mode.
/popkit-core:pop-project-initpop-sandbox
Section titled “pop-sandbox”Description: E2B Sandbox Manager — provides safe, isolated environments for code execution and testing. Essential for multi-agent swarms to avoid local file conflicts.
/popkit-core:pop-sandboxpop-project-reference
Section titled “pop-project-reference”Description: Load cross-project context in monorepos. Lists available workspace projects or loads specific project context. Supports pnpm, npm/yarn, Lerna workspaces.
/popkit-core:pop-project-referencepop-project-templates
Section titled “pop-project-templates”Description: Curated project templates that guide feature-dev Phase 3 questions with research-backed technology choices. Provides standardized options for common project types (SaaS API, ML Service, CLI Tool, Full-Stack).
/popkit-core:pop-project-templatespop-skill-generator
Section titled “pop-skill-generator”Description: Generate custom skills based on codebase patterns, common workflows, and team conventions discovered during analysis.
Use when: You want to capture project-specific patterns as reusable skills.
/popkit-core:pop-skill-generatorpop-validation-engine
Section titled “pop-validation-engine”Description: Validate plugin integrity and offer safe auto-fixes for common issues - checks agents, skills, hooks, routing config, and plugin structure.
/popkit-core:pop-validation-enginepopkit-dev (17 skills)
Section titled “popkit-dev (17 skills)”Development workflow skills for git operations, routines, and feature development.
pop-brainstorming
Section titled “pop-brainstorming”Description: Collaborative design refinement that transforms rough ideas into fully-formed specifications through Socratic questioning. Explores alternatives, validates incrementally, and presents designs in digestible chunks.
Use when: Before writing code when requirements are unclear or multiple approaches exist.
/popkit-dev:pop-brainstormingpop-changelog-automation
Section titled “pop-changelog-automation”Description: Enhanced changelog generation with semantic versioning, auto-categorization, and release notes. Parses conventional commits, determines version bump, categorizes changes by type.
Use when: Before releases or on PR merge to automate version management.
/popkit-dev:pop-changelog-automationpop-complexity-analyzer
Section titled “pop-complexity-analyzer”Description: Analyzes task/feature complexity (1-10) and recommends subtask breakdown for planning and prioritization. Provides actionable recommendations for agent selection and risk assessment.
/popkit-dev:pop-complexity-analyzerpop-context-restore
Section titled “pop-context-restore”Description: Fully restore working context from a previous session - loads STATUS.json, reads key files, rebuilds mental model of current work state.
/popkit-dev:pop-context-restorepop-executing-plans
Section titled “pop-executing-plans”Description: Controlled batch execution of implementation plans with review checkpoints between phases. Loads plan, critically reviews for issues, executes tasks in batches, then pauses for feedback.
Use when: You have a complete implementation plan and want structured execution with quality gates.
/popkit-dev:pop-executing-planspop-finish-branch
Section titled “pop-finish-branch”Description: Guide completion of development work by presenting structured options: merge locally, create PR, keep as-is, or discard.
Use when: Implementation is complete, all tests pass, and you need to decide how to integrate the work.
/popkit-dev:pop-finish-branchpop-morning
Section titled “pop-morning”Description: Start-of-day setup routine. Calculates Ready to Code Score (0-100) based on session restoration, service health, dependency updates, branch sync, PR reviews, and issue triage.
/popkit-dev:pop-morningpop-next-action
Section titled “pop-next-action”Description: Context-aware recommendation engine that analyzes git status, TypeScript errors, GitHub issues, and technical debt to suggest prioritized next actions.
Use when: Unsure what to work on next, starting a session, or feeling stuck.
/popkit-dev:pop-next-actionpop-nightly
Section titled “pop-nightly”Description: End-of-day cleanup routine. Calculates Sleep Score (0-100) based on uncommitted work, branch cleanup, issue updates, CI status, and service shutdown.
/popkit-dev:pop-nightlypop-routine-measure
Section titled “pop-routine-measure”Description: Display routine measurement dashboard with metrics, costs, trends, and visualization.
/popkit-dev:pop-routine-measurepop-routine-optimized
Section titled “pop-routine-optimized”Description: Token-optimized morning/nightly routine using caching and selective execution.
/popkit-dev:pop-routine-optimizedpop-session-capture
Section titled “pop-session-capture”Description: Save complete session state to STATUS.json for seamless continuation across conversations. Captures git context, in-progress tasks, service status, focus area, and next actions.
Use when: End of work sessions, before context limits, or when switching tasks.
/popkit-dev:pop-session-capturepop-session-resume
Section titled “pop-session-resume”Description: Restore context from STATUS.json at session start. Loads previous state, displays session type, shows what to continue working on.
/popkit-dev:pop-session-resumepop-worktree-manager
Section titled “pop-worktree-manager”Description: Python-based git worktree manager with 8 operations: list, create, remove, switch, update-all, prune, init, analyze. Handles cross-platform paths and STATUS.json integration.
/popkit-dev:pop-worktree-managerpop-worktrees
Section titled “pop-worktrees”Description: Create isolated git worktrees with smart directory selection and safety verification. Verifies .gitignore, runs project setup, confirms clean test baseline.
Use when: Starting feature work that needs isolation from current workspace.
/popkit-dev:pop-worktreespop-writing-plans
Section titled “pop-writing-plans”Description: Create comprehensive implementation plans with exact file paths, complete code examples, and verification steps for engineers with zero codebase context.
Use when: After brainstorming/design is complete when handing off to another developer or planning complex multi-step work.
/popkit-dev:pop-writing-planspop-session-branch
Section titled “pop-session-branch”Description: Create, switch, and merge session branches for side investigations. Branch off to explore bugs, research APIs, or debug issues without polluting main context. DAG-based session architecture inspired by Pi.
Use when: You need to temporarily investigate something unrelated to your main task.
/popkit-dev:pop-session-branchpopkit-ops (14 skills)
Section titled “popkit-ops (14 skills)”Operations and quality skills for assessments, testing, debugging, and benchmarking.
pop-assessment-anthropic
Section titled “pop-assessment-anthropic”Description: Validates PopKit compliance with Claude Code patterns using concrete standards and automated checks.
/popkit-ops:pop-assessment-anthropicpop-assessment-architecture
Section titled “pop-assessment-architecture”Description: Validates code quality using concrete metrics for DRY, coupling, cohesion, and architectural patterns.
/popkit-ops:pop-assessment-architecturepop-assessment-performance
Section titled “pop-assessment-performance”Description: Evaluates efficiency using concrete metrics for context usage, token consumption, and lazy loading validation.
/popkit-ops:pop-assessment-performancepop-assessment-security
Section titled “pop-assessment-security”Description: Validates security posture using concrete vulnerability patterns, automated secret scanning, and OWASP-aligned checklists.
/popkit-ops:pop-assessment-securitypop-assessment-ux
Section titled “pop-assessment-ux”Description: Evaluates user experience using concrete heuristics for command naming, error messages, and interaction patterns.
/popkit-ops:pop-assessment-uxpop-benchmark-runner
Section titled “pop-benchmark-runner”Description: Orchestrates benchmark execution comparing PopKit vs baseline Claude Code.
/popkit-ops:pop-benchmark-runnerpop-code-review
Section titled “pop-code-review”Description: Confidence-based code review that filters issues to 80+ threshold, eliminating false positives. Reviews implementation against plan or requirements for bugs, quality issues, and project conventions.
Use when: After completing major features, before merging to main, or after each task in multi-step workflows.
/popkit-ops:pop-code-reviewpop-cross-model-review
Section titled “pop-cross-model-review”Description: Advisory outside-voice review that runs through the opposite model family when possible, normalizes the result into a stored artifact, and can optionally publish/update a PR comment for the current head SHA.
Use when: Before marking a PR ready, during finish-branch flow, or when you want an unbiased second opinion from a different model family.
/popkit-ops:pop-cross-model-reviewpython packages/popkit-ops/skills/pop-cross-model-review/scripts/run_review.py --pr 123 --publish commentpop-systematic-debugging
Section titled “pop-systematic-debugging”Description: Four-phase debugging: root cause, patterns, hypothesis, implement. For complex bugs, test failures, and multi-component issues.
/popkit-ops:pop-systematic-debuggingpop-deploy-init
Section titled “pop-deploy-init”Description: Initialize deployment configuration for a project. Detects project type, target platform, and generates deploy.json configuration.
/popkit-ops:pop-deploy-initpop-deploy-setup
Section titled “pop-deploy-setup”Description: Set up deployment infrastructure — generates Dockerfiles, docker-compose, Kubernetes manifests, and CI/CD pipeline configs based on deploy.json configuration.
/popkit-ops:pop-deploy-setuppop-deploy-validate
Section titled “pop-deploy-validate”Description: Pre-deployment validation with build checks, test suite, security scans, and dependency audits. Generates readiness score (0-100) with go/no-go recommendation.
/popkit-ops:pop-deploy-validatepop-deploy-execute
Section titled “pop-deploy-execute”Description: Execute deployments to target environments with dry-run support. Captures metrics, handles rollback on failure, records deployment history.
/popkit-ops:pop-deploy-executepop-deploy-rollback
Section titled “pop-deploy-rollback”Description: Emergency rollback to previous versions with automatic and manual triggers. Validates rollback success and generates incident reports.
/popkit-ops:pop-deploy-rollbackpopkit-research (3 skills)
Section titled “popkit-research (3 skills)”Knowledge management skills for research capture and retrieval.
pop-knowledge-lookup
Section titled “pop-knowledge-lookup”Description: Query cached external documentation and blog content for authoritative, up-to-date information. Sources include Claude Code docs, engineering blog, and configured knowledge bases with 24-hour TTL caching.
Use when: You need current information about Claude Code features, hooks, or best practices.
/popkit-research:pop-knowledge-lookuppop-research-capture
Section titled “pop-research-capture”Description: Capture research insights, decisions, and learnings during development. Prompts for context and rationale, stores with embeddings for later semantic retrieval.
Use when: After completing spikes, making architectural decisions, or discovering important patterns.
/popkit-research:pop-research-capturepop-research-merge
Section titled “pop-research-merge”Description: Process research branches from Claude Code Web sessions - merges content, moves docs to .claude/research/, and creates GitHub issues.
Use when: /popkit-dev:next detects research branches or when manually processing research from mobile sessions.
/popkit-research:pop-research-mergeSkill Conventions
Section titled “Skill Conventions”Context Modes
Section titled “Context Modes”Skills declare their execution context:
- Default context: Runs in the main conversation (most skills)
- Forked context (
context: fork): Runs in an isolated context to reduce token overhead. Used for expensive operations like embeddings and web research.
The PopKit Way
Section titled “The PopKit Way”Skills should end with a clear next-step handoff through the best interaction
surface the runtime actually supports. In practice, that means PopKit may use
request_user_input, AskUserQuestion, or plain-text fallback while keeping
the workflow contract stable. This ensures:
- Context-aware next action options
- Continuous workflow engagement
- Intentional user decisions at every step
Next Steps
Section titled “Next Steps”- Learn about Agents Reference
- Explore Commands Reference
- Read the Getting Started Guide