Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Dev tools
16,902 results · page 305 of 564
- View details
code-dedupSkillDev tools
Searches for duplicate code, duplicate tests, and dead code, then safely merges or removes them. Use when the user says "deduplicate", "find duplicates", "remove dead code", "DRY up", or "code dedup". Requires test coverage — refuses to touch untested code.
Ready to connect★ 113
- View details
deviateSkillDev tools
Stop an in-flight assign-to-workforce run the moment execution must diverge from the confirmed plan, get explicit human approval for the divergence, and record it as a first-class, append-only deviation record via `devague deviate` before resuming — never fold a deviation silently into drift after t
Ready to connect★ 113
- View details
gf-cocotbSkillDev tools
Python-based testbench generation using Cocotb. Alternative to SystemVerilog testbenches for Python-native hardware engineers. Example: "create a cocotb test for the FIFO", "write Python testbench"
Ready to connect★ 113
- View details
gf-errorsSkillDev tools
Error translation layer for hardware tool outputs. Converts cryptic Verilator, Yosys, GHDL, and simulation errors into 3-layer explanations. Used internally by gf orchestrator — not user-invocable directly.
Ready to connect★ 113
- View details
gf-formalSkillDev tools
Formal verification from natural language. Generates SVA properties, configures SymbiYosys, runs proofs, and explains results. Example: "formally verify the FIFO never overflows"
Ready to connect★ 113
- View details
gf-learn-ctxSkillDev tools
Contextual learning — micro-lessons embedded in workflow output. Explains hardware concepts on first encounter, tracks what has been taught, generates practice exercises on demand. Used internally by orchestrator — not typically invoked directly.
Ready to connect★ 113
- View details
gf-lintSkillDev tools
SystemVerilog lint checker with structured output for orchestration. Runs Verilator lint, categorizes errors/warnings, explains issues, and returns a parseable result block for /gf orchestration.
Ready to connect★ 113
- View details
gf-pnrSkillDev tools
Place and route with nextpnr for open-source FPGA targets. Supports iCE40, ECP5, and Gowin devices. Example: "place and route for iCEBreaker", "run P&R targeting ice40"
Ready to connect★ 113
- View details
gf-protocolsSkillDev tools
Protocol scaffolding library. Generates correct, readable protocol interface scaffolds (AXI4-Lite, SPI, UART, I2C, AXI4-Full, AXI-Stream, Wishbone) with testbench templates and integration examples. Example: "create an I2C master interface", "scaffold AXI-Stream source"
Ready to connect★ 113
- View details
gf-simSkillDev tools
SystemVerilog simulator with structured output for orchestration. Auto-detects DUT vs testbench, compiles with Verilator, runs simulation, and returns a parseable result block for /gf orchestration.
Ready to connect★ 113
- View details
gf-summarySkillDev tools
Summarize Verilator, lint, or simulation output into a readable, actionable format. Use when the user wants to understand build output, lint errors, or simulation results from a Verilator or EDA tool run.
Ready to connect★ 113
- View details
gf-tuiSkillDev tools
GateFlow terminal console inspired by OpenClaw local TUI workflows. Shows workspace status, component inventory, tool health, map readiness, release readiness, and command shortcuts from one terminal surface.
Ready to connect★ 113
- View details
gf-vizSkillDev tools
Terminal visualization for GateFlow codebase maps. Renders module hierarchies, FSM state diagrams, and module detail cards as interactive ASCII/Unicode art. Example requests: "visualize the codebase", "show hierarchy", "show FSM", "show module detail"
Ready to connect★ 113
- View details
graphql-operationsSkillDev tools
Guide for writing GraphQL operations (queries, mutations, fragments) following best practices. Use this skill when: (1) writing GraphQL queries or mutations, (2) organizing operations with fragments, (3) optimizing data fetching patterns, (4) setting up type generation or linting, (5) reviewing oper
Ready to connect★ 113
- View details
novel-cocreateSkillDev tools
Co-creation planning: clarify requirements through multi-turn dialogue with the AI, gradually accumulating a creation directive for an entire book; once finalized, you can go straight into writing. Triggers: "I haven't figured out what to write yet", "help me sort out my ideas", "let's plan a book t
Ready to connect★ 113
- View details
novel-diagSkillDev tools
Diagnose the current project's output artifacts, providing actionable findings across four dimensions (workflow/quality/planning/context), and write a redacted report. Triggers: "诊断这本书" (diagnose this book), "为什么卡住了" (why is it stuck), "检查创作有没有问题" (check the writing for problems), "生成 diag 报告贴 issue
Ready to connect★ 113
- View details
novel-pipelineSkillDev tools
Chains all features into a resumable pipeline: (co-creation →) writing → review → rewrite → delivery, executed stage by stage with checkpoint resume. Triggers: "一条龙写完整本书" (write a whole book end to end), "从头跑完整个流程" (run the entire flow from scratch), "中断后接着跑" (resume after interruption). Use when yo
Ready to connect★ 113
- View details
novel-reviewSkillDev tools
Runs the Editor review stage of the novel-studio pipeline over an existing project chapter by chapter, producing review feedback only, without changing the original text. Triggers: "review my novel", "go through it chapter by chapter", "find issues in the chapters" — use when you need a quality diag
Ready to connect★ 113
- View details
novel-rewriteSkillDev tools
Rewrites chapters one by one with Writer based on review feedback via the rewrite stage of the novel-studio pipeline, modifying the original chapter text. Triggers: "按评审改写", "重写这几章", "根据意见润色正文". Use after novel-review when applying revisions based on feedback.
Ready to connect★ 113
- View details
novel-writeSkillDev tools
Drives novel-studio with a single creative requirement through a resumable pipeline for complete creation (writing → review → rewrite → export). Triggers: 'help me write a novel', 'write based on this setting', 'run a creation pass'. Use when there are clear creative requirements and an unattended e
Ready to connect★ 113
- View details
novel-writing-assetsSkillDev tools
View, enable, disable, combine, bind, trial-write, and recompile novel-studio's long-term writing style assets. Triggers: 「列出写法特征」「启用/停用某个写法」「组合写法」「绑定写法」「试写写法」「重编译写法规则」「维护写法资产」.
Ready to connect★ 113
- View details
- View details
run-testsSkillDev tools
Lets your agent build and run the correct dotnet test command for a repo, with the right filters and options.
Ready to connect★ 113
- View details
rust-best-practicesSkillDev tools
Guide for writing idiomatic Rust code based on Apollo GraphQL's best practices handbook. Use this skill when: (1) writing new Rust code or functions, (2) reviewing or refactoring existing Rust code, (3) deciding between borrowing vs cloning or ownership patterns, (4) implementing error handling with
Ready to connect★ 113
- View details
scopeSkillDev tools
Explore the scope of a vague idea BEFORE framing it into a spec (the idea→scope leg; the optional opening move ahead of /think). Survey the surfaces the idea touches — code, docs, skills, CI, sibling repos — and seed the coming Announcement Frame with boundary, non-goal, and assumption claims that c
Ready to connect★ 113
- View details
story-deslopSkillDev tools
Lets your agent detect and remove AI-sounding writing patterns from text so it reads more natural.
Ready to connect★ 113
- View details
story-douban-long-writeSkillDev tools
Methodology for Douban Read original long-form novels and adapter for the novel-studio pipeline. Use it to organize the theme, genre, opening, prose, tags, synopsis, and submission self-check requirements of a 150K-300K character original long-form novel into pipeline inputs; direct generation of th
Ready to connect★ 113
- View details
story-long-writeSkillDev tools
Helps your agent write long web novels, managing worldbuilding, characters, and plot lines from outline to chapters.
Ready to connect★ 113
- View details
story-short-writeSkillDev tools
Helps your agent write short fiction, guiding the story from initial idea to finished draft with focus on emotion and pacing.
Ready to connect★ 113
- View details
submit-prSkillDev tools
Creates a pull request with a well-structured description after verifying CI passes. Use when the user asks to submit, create, or open a pull request.
Ready to connect★ 113
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,789 of the 54,221 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.