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
2,684 results · page 43 of 90
- View details
executive-assistantSkillProductivity
A skilled executive assistant that helps with calendar management, travel coordination, and comprehensive executive support. Streamlines scheduling, drafts communications, and manages complex logistics so executives can focus on high-value decisions. Use when: working with executive-assistant.
Ready to connect★ 163
- View details
machine-learning-engineerSkillProductivity
Expert machine learning engineer skill. Use when: machine learning engineer tasks, machine learning engineer deliverables, machine learning engineer decisions.
Ready to connect★ 163
- View details
cas-workerSkillProductivity
Factory worker guide for task execution in CAS multi-agent sessions. Use when acting as a worker to execute assigned tasks, report progress, handle blockers, and communicate with the supervisor.
Ready to connect★ 162
- View details
abort-safe-handlerSkillProductivity
Orchestrator-level Stage 4 entry gate for /gaai:bootstrap. Presents a pre-loop 'Skip Q&A entirely' option, delegates to qa-loop-ui when the user proceeds, and returns a unified abort_safe_result with telemetry on every path. Guarantees no partial state on skip or abort.
Ready to connect★ 161
- View details
differed-task-executionSkillProductivity
Delays execution of a task until a specified time or after a duration. Use when the user asks to run something later, in X minutes/hours, at a specific time, schedule a command, or defer work to a future point.
Ready to connect★ 160
- View details
raySkillProductivity
Main entry point and router for the rayskills toolbox. Use this skill when the user is unsure which ray-* skill to use, simply drops in a real task or situation, or explicitly asks to take a piece of content from idea through research and writing all the way to the WeChat Official Account drafts box
Ready to connect★ 160
- View details
ray-multimodelSkillProductivity
Performs minimal-sufficient division of labor across Grok, Claude, and Codex based on task value, with the current session acting as the lead to complete acceptance. Use when the user explicitly asks to "let Grok go first", "multi-model collaboration", "two independent proposals", "model competition
Ready to connect★ 160
- View details
reframe-voiceSkillProductivity
Write, rewrite, or review content in the evidence-led reframe voice style. Use when the user explicitly asks to write in "reframe voice" or "reframe style". Do NOT use for general writing tasks.
Ready to connect★ 160
- View details
cash-flow-forecasterSkillProductivity
Projects 30-90 days of daily cash flow per cash account by combining current balance, scheduled recurring inflows and outflows from recurring.json, and a 6-month rolling average of discretionary spend, then flags days where projected balance falls below a configurable safety floor. Use for forward p
Ready to connect★ 159
- View details
focus-timeboxing-8020SkillProductivity
Combines Pareto prioritization (80/20), timeboxing, and deep work techniques to manage attention, eliminate context-switching, and maximize high-impact output. Use when managing time and attention, combating procrastination, prioritizing high-impact work, planning daily/weekly schedules, or when use
Ready to connect★ 159
- View details
meta-prompt-engineeringSkillProductivity
Transforms vague or unreliable prompts into structured, constraint-aware prompts with explicit roles, task decomposition, output formats, and quality checks. Use when prompts produce inconsistent outputs, need explicit structure and constraints, require safety guardrails, involve multi-step reasonin
Ready to connect★ 159
- View details
ml-primitive-decoderSkillProductivity
Decomposes any ML construct (attention, layer norm, softmax, convolution, dropout, contrastive loss, diffusion step, gradient descent update, cross-entropy) into the small set of linear-algebra primitives it's built from, then explains why those primitives produce the observed behavior. Includes an
Ready to connect★ 159
- View details
mlb-category-state-analyzerSkillProductivity
Computes the weekly category state for a Yahoo H2H Categories matchup across all 10 scoring categories (R, HR, RBI, SB, OBP, K, ERA, WHIP, QS, SV). Pulls current totals from Yahoo, builds rest-of-week per-cat projections from roster + schedule, then DELEGATES matchup/per-cat win-probability math to
Ready to connect★ 159
- View details
mlb-playoff-schedulerSkillProductivity
Counts MLB games per team during the Yahoo fantasy playoff window (weeks 21, 22, 23 -- Aug 17 through Sep 6, 2026) and grades the quality of each team's opponents. Emits three signals per rostered player -- playoff_games (int, max ~21), playoff_matchup_quality (0-100), holding_value (0-100) -- that
Ready to connect★ 159
- View details
mlb-two-start-scoutSkillProductivity
For a given fantasy week (Monday-Sunday), identifies every starting pitcher scheduled to start twice, validates both probable starts, grades each matchup against the league's Quality Starts (QS) scoring rules, and ranks the list by streamability_score. Flags bullpen-game and opener risks that nearly
Ready to connect★ 159
- View details
codex-model-routing-teamSkillProductivity
In the Codex App, automatically creates multiple background tasks with assignable models and reasoning effort for complex, parallelizable knowledge work or coding tasks; the main Agent handles planning, task division, integration, and acceptance. Use for multi-source research, multi-section content,
Ready to connect★ 157
- View details
agent-teamSkillProductivity
Launch Agent Team mode, where multiple workers process tasks in parallel and share findings. Suitable for large refactors, codebase migrations, and comprehensive reviews.
Ready to connect★ 156
- View details
context-reportSkillProductivity
Analyzes the current project's Claude Code session data and produces a context efficiency report (model usage, tool efficiency, delegation ratio, TodoWrite usage rate). Use together with context-management.md.
Ready to connect★ 156
- View details
debugging-protocolSkillProductivity
Comprehensive protocol for validating root causes of software issues. Use when you need to systematically debug a complex bug, flaky test, or unknown system behavior by forming hypotheses and validating them with specific tasks.
Ready to connect★ 156
- View details
load-planSkillProductivity
Shows the load plan for the current workspace: auto-loaded rules (size/line count), all available skills (grouped by domain), and trigger keywords. Useful at the start of a session, when taking over a new task, or when evaluating workspace configuration.
Ready to connect★ 156
- View details
pmSkillProductivity
Project management workflows: Sprint planning, Issue prioritization (MoSCoW/RICE), status reports, risk assessment, Sprint retrospectives. Best used when starting a new project, in Sprint planning meetings, writing progress reports, or prioritizing tasks.
Ready to connect★ 156
- View details
researchSkillProductivity
General research workflow: define research questions, gather diverse sources, competitive analysis, literature review, synthesize insights, and produce structured reports. Suitable for market research, competitive analysis, technology evaluation, or any task requiring systematic information organiza
Ready to connect★ 156
- View details
contextual-commitSkillProductivity
Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT
Ready to connect★ 154
- View details
laravel:task-schedulingSkillProductivity
Schedule tasks with safety; use withoutOverlapping, onOneServer, and visibility settings for reliable cron execution
Ready to connect★ 154
- View details
laravel:writing-plansSkillProductivity
Create an actionable Laravel implementation plan—bite-sized tasks with TDD-first steps, migrations, services, jobs, and validation points
Ready to connect★ 154
- View details
lina-reviewSkillProductivity
Used to review code changes and spec compliance in the LinaPro OpenSpec workflow. Must be used after completing /opsx:apply tasks, after fixing lina-feedback feedback, and before running /opsx:archive; must also be used when the user requests a code review or a spec compliance check, or explicitly i
Ready to connect★ 153
- View details
catalyst-calendarSkillProductivity
Build and maintain a calendar of upcoming catalysts across a coverage universe — earnings dates, conferences, product launches, regulatory decisions, and macro events. Helps prioritize attention and position ahead of events. Triggers on "catalyst calendar", "upcoming events", "what's coming up", "ea
Ready to connect★ 152
- View details
close-managementSkillProductivity
Plan and control month-end, quarter-end, and year-end close activities. Use for close calendars, dependency management, status tracking, bottleneck escalation, readiness checks, and post-close improvement.
Ready to connect★ 152
- View details
lunar-calendarSkillProductivity
Professional lookup tool for the Chinese lunar calendar. Core capabilities: - Gregorian to lunar conversion (sexagenary year, zodiac sign, leap month flag) - Lunar to Gregorian conversion (precise leap month support) - Almanac auspicious/inauspicious activities lookup (marriage, construction, busine
Ready to connect★ 152
- View details
pull-requestSkillProductivity
Create, update, or validate a NiceEval pull request body. Use when a task includes drafting, applying, checking, or creating a PR; do not invoke remote mutations without the user's authorization.
Ready to connect★ 152
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.
53,585 of the 54,017 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.