Development Claude Skills
8 676 development skills from 759 authors. They write and change code. Half of them fit into 1 830 tokens or less — that is what one costs your context window when the agent loads it. 1 213 ship runnable scripts rather than instructions alone. 42 of them cannot work without an MCP server, most often rube. We also found 1 172 copies of these same skills sitting in other people's repositories — counted once here, not 1 172 times.
8 676 unique 759 authors 5 252 updated this month 1 369 from vendors
Set up and maintain the Parallel CLI (install, auth, balance, skills install)
> repo quality/adoption/trust, discoverability, contribution readiness, topics, homepage URL, description, issues/wiki/license/CI settings, owner/org-wide repo audits, repo popularity/adoption signals, README/package/GitHub metadata drift, URL/license/topics gaps, and Agent Skill repo packaging/evals. Use when the user asks for repo-level readiness, repo metadata/configuration, or visitor/contributor trust. Do not trigger for README-only writing, one PR descriptions/reviews, function-level code tests, or general implementation/architecture work; defer those to narrower specialists unless the user explicitly asks for repo-level readiness/proof/metadata judgment.
Create, improve, or audit README.md documents for GitHub projects. Use only when the user explicitly asks for a README, README quality/readability, README accuracy, or README examples. Do not use for full docs sites, API-reference-only work, general repo launch/readiness audits, topics/homepage metadata, or broad repository review.
Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to build, inspect, run, debug, or revise COMSOL Multiphysics / COMSOL Desktop models. Choose the simplest real COMSOL control path for the task: saved `.mph` inspection, local COMSOL documentation, direct COMSOL executables (`comsolbatch`, `comsolcompile`, `comsolmphserver`, `comsol.exe mphclient`), or the sim COMSOL runtime when structured live introspection, shared Desktop collaboration, checkpointing, or plugin diagnostics are useful. Do not use for generic COMSOL theory.
Expert guidance on writing GitHub Actions workflows. Use when: (1) writing or editing any file under .github/workflows/, (2) choosing between an existing action and a shell script in CI, (3) picking action versions, (4) configuring workflow permissions or cloud authentication from CI, (5) reviewing a workflow in a PR.
Expert guidance on Swift library and framework design. Use when developers mention: (1) designing a Swift library or framework, (2) public API design patterns, (3) protocol-oriented architecture or associated types, (4) result builders or DSL design, (5) performance optimization for libraries, (6) @inlinable or @usableFromInline, (7) noncopyable types for APIs, (8) progressive disclosure in API design, (9) ResponseGenerator or builder patterns.
Expert guidance on Swift best practices, patterns, and implementation. Use when developers mention: (1) Swift configuration or environment variables, (2) swift-log or logging patterns, (3) OpenTelemetry or swift-otel, (4) Swift Testing framework or @Test macro, (5) Foundation avoidance or cross-platform Swift, (6) platform-specific code organization, (7) Span or memory safety patterns, (8) non-copyable types (~Copyable), (9) API design patterns or access modifiers.
General-purpose iterate-fix-and-ship loop for any codebase. Use when: (1) running a continuous bug-fixing loop, (2) iterating on a feature until all tests pass, (3) driving worktree-per-fix PR workflows autonomously. Pair with a project-specific testing skill (e.g. /wendy-cloud-testing) that supplies test commands and failure-mode knowledge.
Expert guidance on building WASM apps for Wendy Lite MCU firmware on ESP32-C6. Use when developers mention: (1) Wendy Lite or wendy-lite, (2) WASM apps on ESP32 or microcontrollers, (3) WendyLite Swift package or import WendyLite, (4) building C/Rust/Swift/Zig apps for ESP32, (5) WAMR runtime on embedded devices, (6) GPIO/I2C/SPI/UART/NeoPixel from WASM, (7) Embedded Swift on WASM or wasm32-none-none-wasm, (8) BLE provisioning on ESP32-C6, (9) uploading WASM binaries to MCU, (10) TLS/networking on ESP32 from Swift.
Guidelines and workflow for working on Laravel 11 or Laravel 12 applications across common stacks (API-only or full-stack), including optional Docker Compose/Sail, Inertia + React, Livewire, Vue, Blade, Tailwind v4, Fortify, Wayfinder, PHPUnit, Pint, and Laravel Boost MCP tools. Use when implementing features, fixing bugs, or making UI/backend changes while following project-specific instructions (AGENTS.md, docs/).
Universal project development workflow for safe, maintainable, proportionate software changes. Use when creating or modifying code, documentation, UI/UX, tests, architecture, design systems, debugging workflows, performance work, deployment preparation, or multi-repository features. Enforces source-of-truth-first discovery, reuse before creation, smallest-reliable-solution decisions, dependency judgment, scoped verification, and visual QA for UI tasks.
Search the internet with Google or DuckDuckGo, inspect results, and extract selected pages as readable Markdown. Use when answers require current web sources, JavaScript-rendered pages, or browser access that can handle bot protection. Prefer dedicated tools such as GitHub CLI for GitHub data and curl for direct files or simple URLs.
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the index', 'ccc', 'cocoindex-code'.
Administer the backlog tooling ecosystem when a capability gap is discovered. Invoke when backlog.py, backlog skills, or backlog agents lack a needed operation and a workaround was used or is about to be used. Classifies gaps as script (delegates to @python-cli-architect), process (loads improve-processes), or documentation (delegates to @contextual-ai-documentation-optimizer). Scope — backlog.py, create/work/groom-backlog-item skills, backlog-item-groomer agent, hooks, templates, references, rules, and tests.
Generates and commits conventional-commits messages by analyzing staged git diffs — fast and fork-context safe. Use when the user asks to commit staged changes, needs a type-scope-description message generated from the current diff, or wants scope selection guidance and pre-commit hook handling.
Creates a GitHub milestone on the current repository and returns its number for downstream use. Use when starting a new sprint, release, or theme grouping of backlog items. No args triggers guided intake (title, due date, description); 'quick {title}' skips to description only. Checks for duplicates before creating. Returns milestone number for /group-items-to-milestone.
Install and configure the GitHub CLI (gh) for AI agent environments where gh may not be pre-installed and git remotes use local proxies instead of github.com. Use when gh command not found, shutil.which returns None, need GitHub API access for issues or PRs or releases or workflow runs, or repository operations fail with 'failed to determine base repo' error. Provides auto-install script with SHA256 verification, GITHUB_TOKEN auth with anonymous fallback, and the required -R flag pattern for proxy environments. Covers project management via GitHub Projects V2, milestones via REST API, issue lifecycle templates, and label taxonomy management.
Analyze git repository history to produce a codebase risk profile before code review. Probes repo size, runs 7 parallel git analysis pipelines (hotspots, bug magnets, bus factor, contributor momentum, firefighting frequency, newly added files), cross-references hotspots with bug magnets to identify high-risk files with primary owner annotation, and writes walkthrough/recon-report.md. Use before code review to prioritize reviewer attention, at the start of linear-walkthrough Phase 1 Discovery to weight file coverage, or when onboarding to an unfamiliar codebase.
Modern Git workflows, best practices, and commands. Use when the user asks about Git branch management (git switch vs checkout), file restoration (git restore), fixup commits, autosquash rebasing, git worktrees, rerere, force-with-lease, repository cleanup (git clean, stale branches, bloat analysis), history navigation (revision syntax, range notation, pickaxe search), recommended global git config, or GitButler and the but CLI.
Transforms validated /linear-walkthrough artifacts into one presentation-ready deck outline per major codebase component. Use when the user asks to create a presentation, prepare a walkthrough deck, build an onboarding deck, produce an architecture review deck, or summarize a codebase for a technical audience. Requires walkthrough directory output -- reads unified walkthrough, per-section files, validation reports, coverage maps, entry points, and open questions -- then orchestrates four parallel agent phases to produce slide outlines with speaker notes, evidence references, and suggested visuals.
Badge design and selection knowledge base for shields.io badges in README files. Use when writing or updating READMEs, choosing badge layouts, selecting badge styles, adding project health indicators, or picking Simple Icons logo slugs. Covers shields.io URL encoding rules, static vs dynamic badge selection, style variants (flat/flat-square/for-the-badge/social/plastic), layout patterns (two-tier/inline/centered), project-type badge sets for Python/JS/Rust/Claude plugins, color reference, non-obvious logo slugs, and common anti-patterns to avoid.
Strategic rebase with mandatory pre-analysis. Use when asked to rebase a branch onto main (or any target). Runs a file-level diff of both sides before touching git, produces a per-file disposition plan (KEEP/MERGE/DROP/REWRITE), and only then executes the rebase. Prevents surprise conflicts and silent data loss from rebasing without knowing what changed on both sides. Triggers: 'rebase', 'rebase onto main', 'rebase this branch', 'rebase and merge', 'update branch from main'.
API reference for Claude Code multi-agent swarm tools -- TeamCreate, SendMessage, TeamDelete, TaskCreate/Update/List/Get, and Agent tool parameters. Use when looking up tool signatures, message schemas, shutdown sequences, error handling patterns, or debugging swarm operations. Covers direct messages, broadcasts, plan approval flows, graceful shutdown sequences, crashed teammate recovery, and common error causes.
Conceptual foundation for Claude Code multi-agent orchestration -- defines teams, teammates, leaders, tasks, inboxes, messages, and backends and shows how they connect. Use when starting to build a swarm workflow, understanding the swarm lifecycle and file layout, reading team config structure, or learning the task dependency system before writing TeamCreate or Agent tool calls.
Dasel v3 query patterns for Hibernate .hbm.xml mapping files — entity-table binding, Java property-to-column extraction, one-to-many set/list/bag relationship tracing, many-to-one foreign key discovery, batch scanning across 60+ HBM files. Use when querying Hibernate ORM class mappings, extracting schema metadata from Java persistence layer, or auditing entity-column relationships in enterprise legacy codebases.
Dasel v3 selector patterns for Maven POM XML files — use when querying dependency versions, filtering by groupId or scope, extracting module hierarchy from parent POMs, or detecting version conflicts across enterprise multi-module Java projects. Load this skill when working with pom.xml files using dasel.
Dasel v3 selectors for Spring bean factory XML — use when querying any Spring ApplicationContext XML for bean discovery, dependency wiring, JMS destination mapping, property injection extraction, or cross-bean reference tracing. Load this skill before writing dasel selectors against Spring bean XML files (applicationContext.xml, *_beans.xml, spring-*.xml).
SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feature, or convert an idea into executable task files.
Fetch and report current API syntax, changelog entries, and breaking changes for a specific library or protocol version. One research angle within a parallel technical-research set — runs independently and returns a structured cited report. Invoke when a specific library name and version are the target.
Administer the backlog tooling ecosystem when a capability gap is discovered. Invoke when backlog.py, backlog skills, or backlog agents lack a needed operation and a workaround was used or is about to be used. Classifies gaps as script (delegates to @python-cli-architect), process (loads improve-processes), or documentation (delegates to @ai-doc-optimizer). Domain: backlog.py, create/work/groom-backlog-item skills, backlog-item-groomer agent, hooks, templates, references, rules, and tests.
Use when a task asks for architecture review, dependency graph visualization, module coupling analysis, or circular dependency detection. Auto-detects scope (git diff → PR diff → full project). Reads project config (pyproject.toml, tsconfig.json, go.mod, Cargo.toml) to establish the intra-project module namespace before parsing imports. Builds a module-dependency graph across Python, TypeScript, JavaScript, Go, Rust, and Java. Detects cycles via graphify output or an executable Python script. Checks Conway's Law alignment against CODEOWNERS and directory structure. For Claude plugin repos, also traces cross-language chains: hook configs → hook scripts, SKILL.md/agent docs → node/uv-run scripts, PEP 723 inline deps, and MCP tool calls. Emits Mermaid flowcharts with severity color-coding (red = circular dep, yellow = high-coupling, green = clean, blue = Conway violation). Applies recursive semantic partitioning for graphs > 40 nodes. Registers each diagram as a codebase-analysis artifact.
Reviews CLI application code for correctness and quality. Use when reviewing tools that use argparse, click, typer, commander.js, or similar argument parsers — covers exit codes, help flags, stdin/stdout/stderr separation, non-interactive operation, signal handling, argument validation, ANSI color safety, and dry-run support for destructive operations.
Applies Node.js-specific code review patterns for async I/O, streams, security, process management, and dependency hygiene. Use when reviewing Node.js server code, route handlers, middleware, or any JavaScript file alongside package.json without TypeScript. Triggers on sync I/O in request paths, missing stream backpressure, process.exit misuse, eval/exec injection risks, wildcard version ranges, missing lockfiles, EventEmitter cleanup gaps, and unvalidated environment variables at startup.
Provides Python-specific code review rules for the dh code-reviewer agent. Activates on pyproject.toml or *.py file detection — enforces uv, ruff, ty, pytest, type annotation, error handling, and Python 3.11+ idioms including pathlib, match statements, and modern union syntax.
Provides TypeScript-specific code review patterns covering strict mode, ESM, type safety, branded types, discriminated unions, async patterns, runtime safety, and common anti-patterns. Activates on detection of tsconfig.json, *.ts, or *.tsx files during code review — loaded automatically by dh:code-reviewer.
Local codebase analysis research angle — derives behavioral contracts, coding conventions, SKILL.md flow insertion points, and agent data availability maps from actual source files. Use when the blocking question is answered by reading the repository: what does this function actually do, what pattern does the codebase use for X, where in this workflow does a new step go, or what data does this agent already have.
Execute large-scale automated code transformations safely and idempotently. Use when renaming symbols across a codebase, migrating API call-sites, enforcing new patterns at scale, or applying structural edits to many files at once. Triggers on: 'codemod', 'mass rename', 'migrate all usages', 'transform codebase', 'apply pattern at scale', AST-based refactoring, or any task requiring consistent edits across 10 or more files.
Use when the PLAN artifact from SAM Stage 2 needs contextualization against actual codebase state — grounds the design plan in reality by performing scope analysis (NEW/MODIFY/COMPLETE classification), conflict detection between plan assumptions and codebase patterns, and resource mapping to concrete file paths and integration points. Produces an updated ARTIFACT:PLAN registered via MCP with a Contextualization section appended.
Register a plan artifact via the MCP backlog server. Use when you produce a document or report that downstream agents or worktree-isolated environments need to retrieve — feature-context, codebase-analysis, architect, task-plan, T0-baseline, TN-verification, or research artifacts. Triggers include "store an artifact", "register a plan artifact", "write a report to the backlog", "upload artifact content".
Spawn and manage persistent interactive Claude Code CLI sessions with bidirectional communication via tmux. Provides spawn, send, read, status, list, and kill subcommands for orchestrating parallel peer sessions. Uses built-in --worktree and --tmux flags. Sessions stay alive for multi-turn steering. Triggers on "spawn claude session", "launch separate claude", "peer session", "inter-session communication", "shadow clone", "kage bunshin".
Synthesis step in the multi-angle technical research pipeline. Receives structured outputs from all four research angles (api-state, ecosystem-research, impact-measurement, codebase-auditor), applies cross-angle signal weighting and conflict resolution, and produces a single synthesized Research section. Invoked by the technical-researcher orchestrator after all angle skills complete. Returns content to the orchestrator — does not write to the backlog.
Decomposes a contextualized plan into atomic, independently executable task files with complete embedded context. Use after SAM Stage 3 Context Integration produces the contextualized plan artifact — when the plan is ready for TASK file generation with CLEAR ordering, CoVe checks, and dependency graphs for parallel execution.
Executes a groomed milestone with parallel kage-bunshin sessions in isolated worktrees. Use when a milestone has been groomed and /groom-milestone has produced a dispatch plan. Reads the dispatch plan, creates an integration branch, spawns one kage-bunshin (independent claude -p process) per wave item in its own worktree — each session is a full orchestrator with Agent tool and TeamCreate. Sequentially merges worktree branches, relays wave discoveries to subsequent waves, then lands the integration branch to main. Takes a milestone number as argument.
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.
Complete reference for Claude Code plugins system (April 2026). Use when creating plugins, understanding plugin.json schema, marketplace configuration, bundling skills/commands/agents/hooks/MCP/LSP/monitor servers, plugin caching, validation, or distribution. Covers plugin components, directory structure, installation scopes, environment variables, CLI commands, debugging, and enterprise features.
Cross-platform hooks reference for AI coding assistants — Claude Code, GitHub Copilot, Cursor, Windsurf, Amp. Covers hook authoring in Node.js (ESM and CJS) and Python, per-platform event schemas, inline-agent hooks and MCP in agent frontmatter, common JSON I/O, exit codes, best practices, and a fetch script to refresh docs from official sources. Use when writing, reviewing, or debugging hooks for any AI assistant.
Hook JSON input/output API reference — what data hooks receive via stdin and what JSON they can return to control Claude Code behavior. Use when writing hook scripts, checking exit code behavior, building JSON output for PreToolUse permissions, or understanding event-specific input schemas.