Debug
Debug your application to find and fix a bug or errors
Planning
Generate an implementation plan for new features or refactoring existing code.
vd-create
Create or refine a VibeDev Studio UnifiedWorkflow graph via tool calls. Use when the user says `$vd-create`, asks the model to “build the workflow graph”, “set up Research/Planning/Execution/Review steps”, or wants the model to collaboratively design prompts/conditions/breakpoints and write them into `unified_workflows` so the UI canvas shows the plan before running `$vd-next`.
vd-next
Advance a VibeDev workflow from chat. Use when the user types `$vd-next` / says “vd next” and wants the agent to fetch the next compiled step prompt from the VibeDev MCP HTTP server (`vibedev-mcp serve`) and handle breakpoint/new-thread/diagnose states.
vibedev-flow-designer
Use when translating a program/app idea into a VibeDev MCP Job (deliverables, definition of done, invariants, and a small step plan) and preparing it to transition to READY without implementing features yet
duckdb-alb-log-analyzer
Analyze AWS Application Load Balancer (ALB) logs stored in S3 using DuckDB. Use when users request ALB log analysis, error investigation, performance analysis, traffic analysis, or need to query ALB access logs. Supports analyzing response times, status codes, error patterns, and traffic trends from S3-stored logs.
dealer-proposal
|
deep-research
|
skill-creator
|
context7-cli
Use the local Context7 CLI in this repo to search libraries and fetch Context7 context for skills or documentation tasks. Trigger when you need to run `c7 search`/`c7 context`, resolve library IDs, or retrieve text/json outputs from Context7 via the CLI.
crypto-expert
Crypto best-practices guidance and review across languages and domains. Use whenever cryptography, encryption, hashing, signatures, key/nonce/IV handling, randomness, password storage, TLS/PKI, secure channels, token formats, or "roll your own crypto" is mentioned, including high-level questions or code/design reviews. Trigger broadly to prevent subtle security mistakes.
debug-mode
Run an iterative, hypothesis-driven “debug mode” loop to diagnose and fix a bug using targeted instrumentation and log capture. Use when the user wants an interactive debug loop, when you need to quickly narrow a failure via added debug statements, or when you need a lightweight way to centralize logs from a repro run (via `agent-skills debug` server + SSE UI).
gh-cli
Standardize all GitHub interactions via the GitHub CLI (`gh`) instead of ad-hoc URLs, UI clicks, or direct REST API calls. Use when you need to read or change GitHub state (repos, issues, pull requests, reviews, check status, Actions workflows/runs, releases, labels, milestones, discussions, gists) and want deterministic output (prefer `--json` + `--jq`). Also use when the user provides a GitHub URL, including deep links like `https://github.com/OWNER/REPO/pull/123`, `.../issues/123`, `.../pull/123/files`, or comment permalinks like `#issuecomment-...`, and you need to fetch the underlying PR/issue/thread and reply. Fall back to `gh api` only when there is no first-class `gh NOUN VERB` command.
astro-forms
Form infrastructure for Astro projects. Contact forms, booking forms, quote requests. Zod validation, email delivery (Resend/Brevo), rate limiting, Google Sheets, postcode lookup, spam protection.
astro-images
Width-based responsive image patterns for Astro. Local build-time processing, per-format quality (AVIF/WebP/JPG/PNG), alpha-aware fallback, art direction, face-focus, OG generation, image SEO. Picture, ArtPicture, FixedImage components.
astro-performance
Core Web Vitals and performance optimization for Astro sites. LCP preloading, font strategy, image patterns, critical path, third-party scripts, Cloudflare Tag Gateway. Use for performance tuning.
deployment
Deployment workflow for Astro v6 sites on Cloudflare Workers + GitHub. Use before first deploy, when debugging 500 errors, build failures, wrangler config issues, or dependency compatibility problems. Triggers on deploy, deployment, Cloudflare Workers, wrangler, staging, production, 500 error on CF, build output, dist folder problems, worker errors, resend cloudflare, vite version conflict. Also use when pushing to GitHub, checking deploy status, managing Cloudflare Workers via MCP, setting up Workers Builds, or configuring preview deployments.
design-tokens
Design system foundation. Generates full color scales, typography, and spacing from siteConfig.brand and siteConfig.fonts. No raw values in components.
astro-audit
Full code audit for Astro lead generation projects. Build, deps, performance, security, a11y, SEO, browser compat, form testing. Run before every deploy.
eeat-signals
Audit and strengthen visible E-E-A-T signals and AI-search (GEO) readiness on Astro lead-gen sites. Use when a page or site needs Experience/Expertise/Authoritativeness/Trust signals, author credibility, first-hand-experience proof, trust pages (about/contact/privacy/returns), NAP + company registration display, review/trust-mark surfacing, AI-crawler access in robots.txt, or answer-first content for ChatGPT/Gemini/Perplexity/AI Overviews. Also triggers on "EEAT", "E-E-A-T", "GEO", "AEO", "AI search visibility", "get cited by AI", "trust signals", "author bio", "local trust", or making a small/niche business outrank larger competitors. Runs a deterministic auditor with runnable tests. Delegates JSON-LD generation to schema-entity-graph and JSON-LD validation to schema-audit; delegates copy voice to humanise-copy.
error-pipeline
>-
schema-entity-graph
Build and assemble a complete Schema.org entity graph for Astro lead-gen sites, driven from siteConfig. Use whenever a project needs JSON-LD structured data — new site setup, schema implementation, adding schema to existing pages, or when the user mentions entity graph, schema components, JSON-LD setup, structured data system, or knowledge graph. Also triggers when building a new Astro project that needs SEO schema, implementing service/area/blog schemas, or connecting business + person + service entities. Works with the schema-audit skill (audit validates rules; this skill builds the implementation). Always use this skill for schema assembly — never write schema components from scratch without it.
soborbo-tracking
>-
feature-file
Manage features.yml for tracking requirements and progress; use proactively ONLY when features.yml already exists, or invoke manually to create one; complements TodoWrite for persistent project state.
waterfall-development
Enforces strict waterfall development workflow with phase gates. Use when (1) features.yml exists in project root, (2) user asks to implement/develop/build a feature, (3) user explicitly requests waterfall workflow. Creates features.yml if missing when invoked.
commit-message
Format git commit messages combining Conventional Commits summary lines with Linux kernel-style bodies. Use when writing, reviewing, or formatting commit messages.
deep-research
Conduct rigorous, multi-source deep research with workflowz orchestration, iterative retrieval, claim-level evidence tracking, source verification, adversarial review, and cited synthesis. Use for complex questions requiring broad coverage, multiple independent sources, comparison, contradiction handling, or an auditable research report; do not use for a quick factual lookup.
git-commit
Guide for breaking changes into logical, atomic commits using interactive staging. Use when committing changes that span multiple concerns, when needing to stage parts of files (hunks), when asked to create well-organized commit history, or when changes should be split into multiple commits.
software-architecture
Document software architecture using ARCHITECTURE.md and docs/*.md files with Mermaid diagrams. Use proactively when ARCHITECTURE.md exists in project root, or invoke to create initial architecture documentation. Covers system design, data flows, component relationships, and code organization with references to key entry points and abstractions.
structured-logging
Guide for writing effective log messages using wide events / canonical log lines. Use when writing logging code, adding instrumentation, improving observability, or reviewing log statements. Teaches high-cardinality, high-dimensionality structured logging that enables debugging.
alloy-modeling
Model and analyze relational systems with Alloy. Use when: designing object graphs, authorization rules, topology constraints, schemas, ownership relations, or other structure-heavy systems; writing Alloy signatures, relations, facts, predicates, assertions, and scope-bounded checks; debugging counterexample instances; or deciding what should be abstracted into a bounded relational model.
formal-verification
OPT-IN workflow for involved formal-verification planning. Use only when: the user explicitly asks for formal verification, this skill is referenced by workspace instructions, or the task explicitly calls for structuring a full formal-verification effort across models, refinement steps, and implementation-level proof obligations.
tlaplus-modeling
Model and reason about concurrent or distributed systems with TLA+ and PlusCal. Use when: designing multithreaded or distributed behavior before code exists, deriving invariants from an informal design, writing TLA+ specs, creating PlusCal algorithms, model checking with TLC, organizing multi-module specifications, debugging verification failures, or reducing state space. Covers informal concurrency design, MCP tool usage, PlusCal preferred syntax (call/await over goto), TLA+ module organization, and state-space optimization.
ci-gatekeeper-agent
>
pr-author-agent
>
rca-copilot-agent
>
signal-factory-core
>
telemetry-validator-agent
>
eda
>
code-review-loop
>
code-review
>
dataset-inspector
>
do-literature-review
>
lazy-imports
>
obsidian-create-note
>
tutorial-expand
>
uv-deps
>
clear
>
auto-duplicate-fixer
Automate detection and removal of duplicate files/functions in TypeScript, JavaScript, and Python projects. Safely refactor imports, validate with tests, and deploy changes with zero risk of breaking the system.
codebase-locator
Locates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.
Page 1235 of 1665 · 83227 results