nsheaps
110 verified skills120 total stars
auto-config
Auto-detect project formatting tools and configure edit-utils settings
tools3
op
Use this skill when the user asks about 1Password, secrets management, retrieving credentials, using op CLI, service accounts, secret references, vault operations, or any task involving the 1Password CLI (op). Also use when needing to inject secrets into environment variables, read passwords or API keys from 1Password, or manage 1Password items from the command line.
tools3
github-app-token
Manage GitHub App installation tokens in Claude Code sessions. Use when tokens expire, auth errors occur in long-running sessions, or when setting up GitHub App credentials for agent teams. <example>my github token expired</example> <example>refresh the github app token</example> <example>check token status</example> <example>set up github app authentication for this session</example>
development3
op-exec
Use this skill when the user asks about op-exec, running commands with 1Password secrets injected, wrapping processes with secret injection, automating secret-aware command execution, or configuring whole-item environment injection with multiple output targets. op-exec is a wrapper around the 1Password CLI that simplifies running commands with secrets from 1Password vaults.
tools3
claude-code
Reference material for Claude Code internals — the on-disk layout under ~/.claude and project-scope .claude, the plugin cache, session-env propagation, and the full hook lifecycle. Auto-recall when working on Claude-Code-related tasks: writing or debugging hooks, authoring plugins, inspecting session state, troubleshooting why an env var is or isn't visible to a Bash tool call, or when paths under ~/.claude or ~/.claude/plugins/ come up.
tools3
exit
Gracefully exit the Claude Code session by sending SIGINT to the Claude process. Works for local CLI sessions and Claude Code Web (remote sessions). Use when you need to exit the session cleanly, or when the user requests exit/termination.
tools1
correct-behavior
Use this skill when the user says you did something wrong, made a mistake, or wants to correct your behavior. Trigger phrases include "don't do that", "that's wrong", "stop doing X", "you should have done Y", "correct yourself", "fix your behavior", "remember to always/never", or any feedback about incorrect AI actions that should be prevented in the future.
data-ai1
binary-inspection
Use this skill when investigating compiled programs, executables, shared libraries, or any binary file where you need to understand its structure, embedded content, or build-time decisions. Trigger when: - User asks to inspect, analyze, or reverse engineer a binary - Finding hardcoded values, URLs, config keys, or strings in a compiled program - Understanding what libraries a binary links against - Investigating build-time decisions embedded in an executable - Extracting embedded resources or metadata from compiled code - Checking what symbols/functions a library exports Do NOT trigger for: - Text files, YAML, JSON, scripts (read directly with Read tool) - Running or executing binaries (binary-inspector is read-only) - Dynamic analysis, tracing, or debugging (strace/gdb are out of scope)
tools1
github-issues-task-management
This skill should be used when organizing work via GitHub Issues and Projects, creating project boards, managing milestones, or when consolidating fragmented tracking into GitHub-native tracking. Trigger phrases: "set up projects", "create a project board", "organize issues", "milestone planning", "what issues need attention", "consolidate tickets".
data-ai1
forum-thread-creation
Create a new thread in a Discord forum channel by calling the Discord REST API. Use when the Discord `reply` MCP tool fails against a forum channel (type 15) because forum channels only accept thread creation, not plain messages. After creation, use `reply` with the returned thread id for follow-up messages.
tools1
brain
Git-backed memory and prompt tracking with self-checking reminders. Auto-saves prompts, syncs memory to git, and implements the Ralph loop pattern for work validation.
testing1
cloudflare-durable-objects
Use this skill when the user asks about Cloudflare Durable Objects, stateful serverless on Cloudflare, WebSocket coordination, distributed counters or locks, or managing Durable Objects with Pulumi.
development1
incident-tracker
Use this skill when the user wants to log a behavioral incident, document a correction in a structured incident report, or maintain learned rules with footnote references back to source incidents. Trigger phrases include "log an incident", "log this incident", "track an incident", "behavioral incident", "document this correction as an incident", "create incident report", "file an incident", or when the user explicitly asks for a structured incident record with severity classification and rule derivation.
testing1
issue-management
Use this skill when the user says "make an issue", "create an issue", "file a bug", "this is a bug", "let's follow up later", "track this", "open a ticket", "create a ticket", "log this for later", "we need to fix this", "add to backlog", "make a task for", "file an enhancement", "create a feature request", or any phrase indicating that something should be tracked, logged, or followed up on in a ticketing system.
tools1
zai-setup
Use this skill when the user asks about z.ai, Zhipu AI, setting up z.ai API access, getting a z.ai API key, configuring Claude Code to use z.ai models directly via the Anthropic-compatible endpoint, routing z.ai through Cloudflare AI Gateway or OpenRouter, or using z.ai's OpenAI-compatible API.
development1
tmux-subagent
Launch and manage independent Claude sub-agents in tmux sessions with isolated configurations, custom tool permissions, and real-time monitoring capabilities
tools1
configure
Set up the Telegram channel — save the bot token and review access policy. Use when the user pastes a Telegram bot token, asks to configure Telegram, asks "how do I set this up" or "who can reach me," or wants to check channel status.
testing1
word-vomit
Use when the user wants to dump unstructured thoughts, ideas, or notes that need to be organized. Triggers: "brain dump", "word vomit", "let me think out loud", "process my notes", "organize my thoughts", "dump my ideas".
data-ai1
sequential-thinking
Use this skill when you need to break down complex problems, plan multi-step implementations, analyze tricky bugs, make architectural decisions, reason through ambiguous requirements, or any task that benefits from structured step-by-step thinking. Also use when you need to revise earlier assumptions, explore alternative approaches, or verify a hypothesis before committing to an implementation.
testing1
self-terminate
Gracefully terminate the Claude Code session by sending SIGINT to the Claude process. Works for local CLI sessions and Claude Code Web (remote sessions). Use when you make a change that requires a restart, or when the user requests termination.
tools1
test
Testing strategy and validation. Use when the user asks about "test strategy", "writing tests", "test coverage", "test plan", "validation", "QA", "how to test this", or when defining testing requirements for a feature. Covers test types, coverage expectations, and validation workflows.
testing1
spec-writing
Specification writing and lifecycle management for software development. Use when the user asks to "write a spec", "create a specification", "document requirements", "spec out a feature", "manage a spec through its lifecycle", "move a spec to live", "archive a spec", "update a spec", or "verify implementation against a spec". Covers creating specs from requirements, managing the spec lifecycle (draft → reviewed → in-progress → live → deprecated → archive), keeping specs as living documents, and using specs for verification.
development1
opengraph-image
This skill should be used when the user wants to generate Open Graph (OG) images for Nuxt pages. These images act as placeholders when services use the opengraph protocol to render a preview on another service, such as the preview for github rendered on Slack when you post a link. While generally for Nuxt pages, it can be used to similarly generate any image using the html2png.dev API. It discovers pages from app/pages/, identifies which are missing OG images (by analyzing the tags), generates beautiful HTML designs, converts them to PNG via html2png.dev API, and saves them to public/og-images/. Trigger phrases: - generate og image - create og images - make social preview - og-image - generate image - opengraph meta tags
development1
validate-review
Validate that review findings are accurate and actionable. Use when asked to "validate review", "check if review findings are correct", "verify review accuracy", or when confirming that a review's claims match actual code state.
development1
review-commits
Review commit structure and organization. Use when asked to "review commits", "check commit history", "are commits atomic", "review commit structure", or when evaluating whether commits are logically grouped and ordered.
testing1
request-a-review
Best practices and procedures for creating and maintaining high-quality pull requests. Covers PR creation, body formatting, title conventions, lifecycle management, and requesting reviews. Counterpart to review-code, respond-to-review, and other review-receiving skills. Triggers on: "create a PR", "update the PR", "open a pull request", "push and PR", "fix PR", "fix PR body", "PR formatting", or automatically after any push to a feature branch per the auto-pr-management rule.
development1
git-worktree
Best practices for Git worktrees, especially branch naming when checking out PRs. Use this when creating worktrees, checking out PRs into worktrees, or working in multi-agent/multi-worktree setups.
testing1
post-review
Post or update a review on GitHub. Use when asked to "post the review", "submit review", "leave a review on the PR", "update the review", or when you have review findings ready to publish on a pull request.
tools1
proxmox-lxc
Use this skill when the user asks about Proxmox VE, LXC containers, creating containers on Proxmox, running Docker in LXC, setting up a lightweight host for services like cloudflared, or managing Proxmox infrastructure. For deploying services inside the LXC via docker-compose, also recall the arcane plugin's arcane-gitops skill. For Cloudflare Tunnel setup, recall the cloudflare plugin's cloudflare-tunnels skill.
tools1
plugin-management
This skill should be used when the user asks to "install a plugin", "update a plugin", "remove a plugin", "check if a plugin is loaded", "reload plugins", "why isn't my plugin working", "what needs a restart", "hot reload", "plugin cache", "plugin settings", "enable a plugin", "disable a plugin", "validate a plugin", or mentions plugin installation, updates, troubleshooting, or lifecycle management in Claude Code.
tools1
docs
Use this skill when the user asks about creating, reading, or editing Google Docs via the Google Workspace CLI. Trigger on tasks involving document content, formatting, or collaboration on Google Docs.
tools1
drive
Use this skill when the user asks about Google Drive operations like listing files, uploading, downloading, searching, sharing, or managing files and folders via the Google Workspace CLI.
tools1
mcp-use-framework
Use this skill when working with the mcp-use Python/TypeScript framework for building MCP servers, clients, and agents. Use when the user asks about creating MCP servers with Python decorators, building MCP agents with LangChain, connecting to multiple MCP servers programmatically, or using the mcp-use fullstack framework for MCP application development.
tools1
tasks
Use this skill when the user asks about managing Google Tasks like creating, listing, updating, or completing tasks and task lists via the Google Workspace CLI.
tools1
contacts
Use this skill when the user asks about managing Google Contacts like searching, creating, updating, or organizing contacts via the Google Workspace CLI.
tools1
pr-feedback
Address PR feedback (review comments, inline suggestions, CI failures) systematically. Use when you need to fetch, triage, and respond to pull request reviews, comments, or failing CI checks. Covers the full feedback loop: gather context, evaluate each item, take action (fix, disagree, defer, or clarify), commit with attribution, and request re-review. <example>address the PR feedback</example> <example>fix the CI failures on my PR</example> <example>respond to the review comments</example> <example>handle the PR review</example> <example>address inline comments on PR #42</example> <example>the reviewer left feedback, can you fix it</example> <example>CI is failing on the PR</example>
testing1
git-spice
This skill should be used when the user asks to "create a stacked branch", "stack a branch", "submit stacked PRs", "restack branches", "use git-spice", "use gs", "manage stacked PRs", "sync stacked branches", "split a branch", "navigate branch stack", "submit stack", "restack", or mentions git-spice, stacked branches, stacked PRs, or the gs CLI tool. Provides comprehensive guidance for managing stacked Git branches with git-spice.
tools1
cloudflare-d1
Use this skill when the user asks about Cloudflare D1, serverless SQL databases on Cloudflare, SQLite on the edge, or managing D1 databases with Pulumi.
devops1
access
Manage Discord channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Discord channel.
testing1
access
Manage Telegram channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Telegram channel.
testing1
admin
Use this skill when the user asks about Google Workspace administration tasks like managing users, groups, organizational units, or domain settings via the Google Workspace CLI. Requires admin privileges.
tools1
cloudflare-ai-gateway
Use this skill when the user asks about Cloudflare AI Gateway, proxying AI API requests through Cloudflare, setting up Claude Code with AI Gateway, configuring ANTHROPIC_BASE_URL, routing AI traffic through a gateway for logging/caching/rate-limiting, cost tracking for AI APIs, connecting Claude Code to OpenRouter or z.ai via a gateway, or managing AI Gateway with Pulumi.
development1
arcane-gitops
Use this skill when the user asks about Arcane GitOps, deploying docker-compose stacks from a git repo, GitOps for self-hosted services, managing docker-compose stacks declaratively, or setting up automated deployments with Arcane and GitHub Actions. Also recall when the user asks about deploying cloudflared, Nextcloud, n8n, or any docker-compose stack via GitOps. For Cloudflare Tunnel setup details, also recall the cloudflare plugin's cloudflare-tunnels skill. For LXC host setup, recall the proxmox plugin's proxmox-lxc skill.
tools1
auth-user
Identify the authenticated user for GitHub CLI (gh) and Git
tools1
automated-code-review
Perform a comprehensive automated code review using granular review skills. Orchestrates review-pr-contents, review-commits, review-commit-messages, review-diff, review-code, validate-review, and post-review as building blocks. Use this for new review workflows — scm-utils:code-review is maintained for backward compatibility with Henry's CI workflow.
development1
calendar
Use this skill when the user asks about managing Google Calendar events, checking schedules, creating meetings, finding free time, or any calendar-related task via the Google Workspace CLI.
tools1
chat
Use this skill when the user asks about Google Chat operations like sending messages, managing spaces, or listing conversations via the Google Workspace CLI.
tools1
code-review
Code review a pull request. Triggers on "review this PR", "code review", "review PR #123", "request a review", "review bot", "code review CI", "automated PR review", "claude review workflow", or when the user wants to add automated code review to a repository.
development1
Code Simplifier
This skill should be used when the user asks to "simplify code", "clean up code", "refactor for clarity", "reduce complexity", "make code more readable", or mentions wanting cleaner, simpler, or more maintainable code. Provides guidance on using the code-simplifier agent and installing required dependencies.
development1
plugins/command-help-skill/skills/command-help
This is supposed to be a skill for CLAUDE to use when a /slashcommand is typed as a message instead of executed. This is important because slash commands take up space in the context, and the window can be saved if dynamically loaded. The critical thing is to use the slash command as a prompt for the general-purpose agent. ##### BELOW BE VIBES --- name: command-help description: > Help users understand and discover slash commands when they accidentally type them as messages instead of executi
tools1
commit
Intelligently commit outstanding changes in logical, focused commits. Use this when you want to commit code using git.
development1
configure
Set up the Discord channel — save the bot token and review access policy. Use when the user pastes a Discord bot token, asks to configure Discord, asks "how do I set this up" or "who can reach me," or wants to check channel status.
testing1
daily-report
Use this skill when asked to "generate a daily report", "summarize org activity", "what happened yesterday across the org", "daily activity report", or "report on commits/PRs/issues across repos". Generates a comprehensive report covering all repositories in a GitHub organization including commits, PRs, branches, issue changes, and force-push history.
data-ai1
data-serialization
Data format conversion and querying utilities for YAML, JSON, TOON, and XML/HTML. Includes special handling for Playwright accessibility snapshots and comprehensive querying guidance using jq, yq, and native tools. TOON provides 30-60% token reduction for LLM contexts.
tools1
deep-research
Use this skill when investigating complex questions that require multiple sources, angles, or synthesis. The deep-research plugin provides a 3-agent research team: lead-researcher (orchestrator), sub-researcher (workers), and critical-reviewer (validator). Trigger when: - Investigation requires 3+ sources (docs, issues, source code, web) - You need to synthesize findings across multiple sources into a coherent report - Previous research findings need source-level verification - You're investigating behavior differences between documented and observed behavior - Competitive analysis or technology evaluations Do NOT trigger for: - Simple lookups ("what flag does X?") - Single-source answers - Basic codebase navigation (use Grep/Glob directly)
tools1
deploy
Deployment and release management. Use when the user asks about "deployment", "CI/CD", "release", "shipping", "publishing", "deploy pipeline", "release process", or when setting up or managing deployment workflows. Covers CI/CD configuration, release strategies, and deployment validation.
testing1
cloudflare-dns
Use this skill when the user asks about Cloudflare DNS, managing DNS records, domain zones, DNSSEC, proxied records, or managing DNS with Pulumi.
devops1
fix-review-findings
Fix issues found during a review. Use when asked to "fix review findings", "address review comments", "fix the issues found", or after a review identifies problems that need code changes.
development1
gh
Use this skill when the user asks about GitHub operations, pull requests, issues, releases, actions, gists, repos, or any task involving the GitHub CLI (gh). Also use when needing to interact with GitHub APIs, check CI status, review PRs, manage labels, create releases, or automate GitHub workflows from the command line.
tools1
github-auth
Guide Claude through GitHub authentication methods including device code flow, personal access tokens, fine-grained tokens, and GitHub App authorization. Use when the user needs to authenticate with GitHub for CLI operations, API access, cross-repo work, or automated workflows. <example>authenticate with github</example> <example>I need to create a PR in another repo</example> <example>gh auth login</example> <example>set up a personal access token</example> <example>configure github app authentication</example>
tools1
github-auth
Guide Claude through GitHub authentication methods including device code flow, personal access tokens, fine-grained tokens, and GitHub App authorization. Use when the user needs to authenticate with GitHub for CLI operations, API access, cross-repo work, or automated workflows. <example>authenticate with github</example> <example>I need to create a PR in another repo</example> <example>gh auth login</example> <example>set up a personal access token</example> <example>configure github app authentication</example>
tools1
github-auth
Guide Claude through GitHub authentication methods including device code flow, personal access tokens, fine-grained tokens, and GitHub App authorization. Use when the user needs to authenticate with GitHub for CLI operations, API access, cross-repo work, or automated workflows. <example>authenticate with github</example> <example>I need to create a PR in another repo</example> <example>gh auth login</example> <example>set up a personal access token</example> <example>configure github app authentication</example>
tools1
glm-models
Use this skill when the user asks about GLM models, GLM-5, GLM-4.7, GLM-4.6, GLM-4.5, GLM-4V, ChatGLM, CogView, CogVideoX, z.ai model capabilities, model selection for different tasks, or comparing GLM models.
data-ai1
gmail
Use this skill when the user asks about reading, sending, searching, or managing emails via the Google Workspace CLI. Trigger on Gmail-related tasks like composing emails, searching inbox, managing labels, archiving, or working with drafts.
tools1
google-workspace-cli
Use this skill when the user asks about the Google Workspace CLI (gws), installing or configuring gws, authenticating with Google Workspace, or performing any task across multiple Google Workspace services. Also use when the user mentions "gws" or "Google Workspace CLI".
tools1
cloudflare-images
Use this skill when the user asks about Cloudflare Images, image optimization, image resizing, image storage and delivery, or managing Images with Pulumi.
devops1
implement
Coding standards and implementation patterns. Use when the user asks about "coding standards", "implementation patterns", "how to structure code", "best practices for writing code", "code organization", or when starting implementation of a planned feature. Covers code structure, naming conventions, error handling, and following existing codebase patterns.
development1
iterate-until-good
Evaluates code on a PR or branch across many categories, scores each, and iterates (local review+fix loop) until all categories score > 85%. Uses the scm-utils review skills for the review portion of each iteration.
development1
cloudflare-kv
Use this skill when the user asks about Cloudflare Workers KV, key-value storage on Cloudflare's edge, distributed KV stores, or managing KV namespaces with Pulumi.
devops1
maintain
Maintenance, bug fixes, and technical debt management. Use when the user asks about "bug fix", "tech debt", "refactoring", "maintenance", "deprecation", "migration", "upgrade dependencies", or when managing ongoing codebase health. Covers bug triage, refactoring strategy, and dependency management.
development1
mcpc-apify
Use this skill when working with Apify's mcpc — a universal CLI client for MCP with persistent sessions, OAuth authentication, and interactive shell mode. Use when the user asks about connecting to remote MCP servers, managing MCP sessions, authenticating with OAuth for MCP, or using Apify's MCP platform. Also use when comparing MCP CLI tools or needing persistent named sessions.
tools1
mcp-cli-philschmid
Use this skill when working with philschmid/mcp-cli — a lightweight Bun-based CLI for interacting with MCP servers from the shell. Use when the user asks about discovering MCP tools, calling MCP tools from the command line, reducing token consumption with dynamic tool discovery, or integrating MCP servers into shell scripts and AI agent workflows. Also use when encountering questions about mcp_servers.json configuration for CLI-based MCP access.
tools1
mcp-gateways
Use this skill when working with MCP gateways — infrastructure for running MCP servers off-host, sharing them between sessions/clients, and federating multiple servers behind a single endpoint. Use when the user asks about remote MCP servers, MCP multiplexing, sharing MCP tools across teams, securing MCP over networks, transport bridging (stdio to SSE/HTTP), or choosing between gateway solutions like Supergateway, mcp-proxy, ContextForge, Envoy AI Gateway, or AgentGateway.
tools1
mcp-proxy-daemoning
Use this skill when working with mcp-proxy daemoning patterns — running a shared MCP proxy daemon that multiple Claude Code sessions can connect to simultaneously. Use when the user asks about sharing MCP servers across sessions, reducing MCP server overhead, running a single MCP proxy instance for multiple clients, configuring smart-mcp-proxy, or understanding the daemon lifecycle pattern from nsheaps/aitkit. Also use for the Serena de-duplication pattern — running project-level MCP servers at the user level to avoid duplicate instances across projects.
tools1
memory-manager
Automatically detects and maintains user preferences, instructions, and rules in CLAUDE.md and other rules files. Activates when user says phrases like 'always', 'never', 'don't forget', 'prefer', 'remember to', or 'from now on'. Intelligently determines whether preferences should be stored globally or per-project, organizes memories hierarchically with categories, and confirms updates with 🧠 and 📝 messages. Other Keywords and Triggerwords: - I can't believe you did that - You fucked up / You messed up - did it wrong - make sure you - important dates and milestones like vacation, birthdays, deadlines, etc
development1
mise
Use this skill when the user asks about managing tool versions, installing development tools, working with mise.toml, setting up project environments, using mise backends, managing environment variables with mise, or any task involving the mise tool version manager. Also use when encountering "command not found" errors for development tools that could be managed by mise.
tools1
cloudflare-pages
Use this skill when the user asks about Cloudflare Pages, deploying static sites or full-stack apps on Cloudflare, JAMstack hosting, or managing Pages projects with Pulumi.
devops1
plan
Planning and requirements for software development. Use when the user asks to "define requirements", "draft requirements", "iterate on a spec", "refine a spec", "break down a task", "plan implementation", or mentions task breakdown and iterative requirements development. Guides iterative specification development through research, review, and refinement cycles rather than one-shot generation. For spec lifecycle management (draft -> reviewed -> live), use sdlc-utils:spec-writing instead.
development1
pr-review-workflow
Quick-reference index for the full PR review workflow. Redirects to automated-code-review for the full orchestration. Use when asked to "do a full review", "review everything", or "comprehensive review".
development1
pr-workflow
Full PR lifecycle management: creating, iterating on feedback, and merging. Triggers on: "review my PR", "iterate on PR feedback", "address review comments", "PR workflow", "get this merged", "respond to reviewer", "handle PR feedback".
documentation1
cloudflare-queues
Use this skill when the user asks about Cloudflare Queues, message queues on Cloudflare, asynchronous processing with Workers, or managing Queues with Pulumi.
devops1
cloudflare-r2
Use this skill when the user asks about Cloudflare R2, S3-compatible object storage, storing files/blobs on Cloudflare, zero-egress storage, or managing R2 buckets with Pulumi.
devops1
rebase
Rebase a feature branch onto its base branch to produce a linear commit history. Use when the user asks to "rebase my branch", "rebase onto main", "rebase PR
data-ai1
respond-to-review
Respond to review comments on a PR. Use when asked to "respond to review", "reply to reviewer", "address review comments", "respond to PR feedback", or when crafting responses to reviewer questions and suggestions.
documentation1
review
Code review practices and quality checks. Use when the user asks to "review code", "review a PR", "code review", "check code quality", "review changes", "score this code", or when evaluating code for merge readiness. Covers review checklists, scoring criteria, feedback conventions, and iterative improvement until quality thresholds are met.
development1
review-code
Review code quality, patterns, and bugs. Use when asked to "review the code", "check code quality", "look for bugs", "review implementation", or when evaluating code correctness, security, and maintainability independent of the diff or PR context.
development1
review-commit-messages
Review commit message quality. Use when asked to "review commit messages", "check commit message format", "are commit messages good", or when evaluating whether commit messages are conventional, descriptive, and useful.
development1
review-diff
Review the diff against the base branch. Use when asked to "review the diff", "check what changed", "review changes against main", "is this PR complete", or when evaluating whether a diff is scoped correctly and complete.
testing1
review-pr-contents
Review PR title, body, labels, and metadata. Use when asked to "review the PR", "check PR description", "is the PR body good", "review PR metadata", or when evaluating whether a PR is well-presented for reviewers.
development1
session-report
Use this skill when asked to "generate a session report", "write a daily summary", "summarize today's work", "write up what we did", "generate end-of-session report", "update the report", or "add my work to the report". Works for solo agents and agent teams alike. Guides the full lifecycle of session reports: creation, incremental updates throughout the day, and final review.
documentation1
sheets
Use this skill when the user asks about reading, writing, or managing Google Sheets data via the Google Workspace CLI. Trigger on spreadsheet tasks like reading cell ranges, updating data, creating sheets, or working with formulas.
tools1
skill-maintenance
Use this skill when updating, improving, or maintaining existing Claude Code agent skills. Activates when the user asks to update, refactor, improve, or fix an existing skill. Does NOT activate for creating new skills from scratch.
development1
slash-command-writing
Use this skill when creating, updating, or maintaining Claude Code slash commands. Activates when user asks to create a new command, modify an existing command, or asks questions about slash command syntax and best practices.
development1
slides
Use this skill when the user asks about creating, reading, or editing Google Slides presentations via the Google Workspace CLI. Trigger on tasks involving slides, presentations, or speaker notes.
tools1
cloudflare-stream
Use this skill when the user asks about Cloudflare Stream, video hosting and streaming, video encoding, live streaming, or managing Stream with Pulumi.
devops1
continue-work
Session recovery skill. Use on startup, after compaction, or when resuming work after any interruption. Restores crons, audits recent history to determine current state, and identifies what to work on next.
testing1
time-context
Detect time-referencing language in user prompts and investigate history before answering. Auto-recall when users say "now", "still", "yet", "changed", "has X", "did Y", etc.
testing1
todo-plus-plus
Task workflow enforcement plugin. Use when asking about commit-on-complete behavior, task completion requirements, ephemeral session awareness, or why a task completion was blocked.
tools1
Todo Sync
Automatically syncs todos and plans from ~/.claude/ to the current project. Use this skill when asking about todo sync behavior, troubleshooting sync issues, or understanding where todos are stored.
tools1
cloudflare-tunnels
Use this skill when the user asks about Cloudflare Tunnels (formerly Argo Tunnel), cloudflared, exposing local services to the internet securely, zero-trust ingress, deploying cloudflared via docker-compose, running cloudflared in a Proxmox LXC container, or managing Tunnels with Pulumi. For docker-compose GitOps deployment patterns, also recall the arcane plugin's arcane-gitops skill. For Proxmox LXC host setup, recall the proxmox plugin's proxmox-lxc skill.
tools1
update-branch
This skill should be used when the user asks to "update the PR", "update PR
tools1
cloudflare-vectorize
Use this skill when the user asks about Cloudflare Vectorize, vector databases on Cloudflare, semantic search, RAG pipelines, embedding storage, or managing Vectorize with Pulumi.
devops1
cloudflare-workers
Use this skill when the user asks about Cloudflare Workers, deploying serverless functions on Cloudflare's edge network, writing Worker scripts, configuring Worker routes and bindings, or managing Workers with Pulumi.
devops1
cloudflare-workers-ai
Use this skill when the user asks about Cloudflare Workers AI, running AI inference on Cloudflare's edge, using AI models in Workers, or managing Workers AI resources with Pulumi.
devops1
cloudflare-zero-trust
Use this skill when the user asks about Cloudflare Zero Trust, Access policies, identity-based access control, protecting self-hosted apps, WARP client, Gateway DNS filtering, device posture, or managing Zero Trust resources with Pulumi. For tunnel setup (the transport layer), also recall the cloudflare-tunnels skill. For deploying Access-protected apps via docker-compose, recall the arcane plugin's arcane-gitops skill.
tools1
task-parallelization
Automatically identify opportunities to parallelize Task tool calls when working on batch operations, repetitive changes, or research tasks. Use this skill when asked to make the same change across multiple files/items, perform bulk operations, or conduct research across multiple sources.
tools1
renovate-setup
Use this skill when setting up or debugging Renovate auto-merge, configuring Renovate in a repo, or diagnosing why Renovate PRs are not auto-merging.
development1
spec-management
This skill should be used when creating, updating, or reviewing specifications during the PR process. Trigger phrases: "write a spec", "update the spec", "does this PR have a spec", "add a spec to this PR", "review the spec", "spec-driven development", or when making plugin changes that need specification documentation.
tools1
restart
Restart the Claude Code session by gracefully exiting so the launcher loop restarts it. Use when you need to pick up config changes, plugin updates, or env var changes. Requires a launcher script (e.g., run-agent.sh) that restarts Claude after exit.
tools1
issue-management
Use this skill when the user says "make an issue", "create an issue", "file a bug", "this is a bug", "let's follow up later", "track this", "open a ticket", "create a ticket", "log this for later", "we need to fix this", "add to backlog", "make a task for", "file an enhancement", "create a feature request", or any phrase indicating that something should be tracked, logged, or followed up on in a ticketing system.
tools1