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: Productivity
2,715 results · page 91 of 91
- View details
knack-interviewSkillProductivity
Conduct the Knack 6-phase interview with a user to author a new skill. Load this skill when the user wants to teach you a recurring task they do and have it become a reusable Knack skill (e.g. "use knack to capture how I triage support tickets").
Ready to connect
- View details
major-version-modeSkillProductivity
Context for working on the next AI SDK major release. Only use when explicitly invoked by the user (e.g. via '/major-version-mode'). Do NOT trigger autonomously based on task content.
Ready to connect
- View details
midwitSkillProductivity
The Midwit skill is the user’s ongoing anti-complexity gate for a conversation. It triggers on /midwit or requests to maintain an anti-overengineering mode, keep the user honest across tasks, challenge elaborate infrastructure before work, or propose doing nothing when the goal is already met. It as
Ready to connect
- View details
onescience-coderSkillProductivity
OneScience step-by-step coding execution skill. After receiving a task, it forcibly invokes resource skills to obtain specification knowledge, usage knowledge, and planning/decision knowledge, then outputs execution information step by step and waits for confirmation before executing. After all step
Ready to connect
- View details
onescience-data-analyzerSkillProductivity
OneScience data analysis execution skill (type=executor). Handles data analysis, visualization, and report output; does not handle task planning. Receives planned tasks and invokes workflows to perform statistical analysis, generate visualizations, and produce reports, automatically matching visuali
Ready to connect
- View details
onescience-orchestratorSkillProductivity
The general task-orchestration master controller of OneScience / OneSkills, and the system's default execution entry point. It identifies user intent from resource summaries under the unified resource contract, recalls and fuses proposals from type=expert planning skills, maintains Task State, binds
Ready to connect
- View details
onescience-parallelSkillProductivity
Converts PyTorch models to support distributed training with Pipeline Parallelism (PP) + Tensor Parallelism (TP). Use cases: converting a single-GPU model to multi-GPU distributed, splitting a model into multiple pipeline stages, replacing nn.Linear with parallel linear layers, writing forward_step_
Ready to connect
- View details
onescience-runsiteSkillProductivity
Parse, validate, save, and reuse OneScience run-site configurations. Used by any skill to complete run-site configuration before continuing a task: configuration discovery, prompting for missing fields, reuse of existing configuration, remote connection verification, DCU/GPU run-platform type confir
Ready to connect
- View details
onescience-runtimeSkillProductivity
[Unified Execution & Basic Diagnostics Skill] Executes test tasks following a fixed closed loop of discover, preflight, execute, diagnose, routing the execution channel based on the execution_profile triple in onescience.. In the preflight stage, environment readiness pre-checks are fully delegated
Ready to connect
- View details
oneskillsSkillProductivity
OneSkills is a skill library for AI4S research agents, focusing on key stages such as research development, experiment execution, and environment delivery, providing reusable, composable, and production-ready task execution capabilities.
Ready to connect
- View details
paleoSkillProductivity
Use when user says "paleo mode", "save tokens", "be brief", "terse", "compress output", or says "paleo". Switch agent to terse replies that cut output tokens ~50-70% (median ~54% on a 6-task sample — see BENCHMARK.md) while keeping code, commands, errors, and technical terms byte-exact. Off: "stop p
Ready to connect
- View details
paleo-budgetSkillProductivity
Use when user says "budget", "token limit", "stay under N tokens", or wants per-task token caps. Enforce a hard token budget per task/response — track estimate, stop before limit, summarize if exceeded. Off: "no budget" / "unlimited".
Ready to connect
- View details
paleo-trim-contextSkillProductivity
Use when context window is large / token cost high / long session. Proactively trim, summarize, or drop stale content to save context tokens without losing the task state.
Ready to connect
- View details
spin-worktreeSkillProductivity
Create an isolated Git worktree for issue, pull-request, branch, or parallel agent work without editing the control checkout. Use when starting task work from fresh remote state, avoiding a dirty or shared checkout, or preparing a dedicated worktree for another agent.
Ready to connect
- View details
time-bomb-radarSkillProductivity
Finds deferred operations that crash on aged data -- code that passes every test but breaks weeks or months after release. Covers cascade deletes, cache expiry, trial paths, background accumulation, date-threshold transitions, and scheduled side effects. Triggers: "time bomb", "time-bomb", "/time-bo
Ready to connect
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.
54,764 of the 55,196 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.