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 64 of 91
- View details
codex-ccSkillProductivity
Delegates coding tasks from Codex to local Claude Code in print mode while preserving Claude's normal runtime customizations by default. Use when: (1) You want Codex to call Claude Code locally, (2) You need Claude-side skills, plugins, MCP servers, custom commands, CLAUDE.md rules, or workspace set
Ready to connect★ 64
- View details
effect-tsSkillProductivity
Effect-TS expert — write, debug, refactor, and explain code using the Effect ecosystem (effect, @effect/platform, @effect/rpc, @effect/cli, @effect/schema, @effect/cluster). Use this skill whenever the user works with Effect-TS code, mentions Effect services/layers/fibers/streams/schedules, asks abo
Ready to connect★ 64
- View details
r3f-best-practicesSkillProductivity
Gives your agent best-practice guidance for writing and reviewing React Three Fiber 3D code.
Ready to connect★ 64
- View details
research-taskSkillProductivity
Execute a research task using compositional workflow planning. Characterizes the task, selects an approach from a library of research strategies, executes it, and self-evaluates output quality.
Ready to connect★ 64
- View details
shareholder-meetingSkillProductivity
Query shareholder meeting information for A-share listed companies (market.ft.tech). Use when the user asks about shareholder meetings, record dates, voting dates, or meeting proposals.
Ready to connect★ 64
- View details
subagent-coordinatorSkillProductivity
Launches multiple subagents in parallel and automatically assembles their results into a single report. Use for independent tasks that can be executed simultaneously. Triggers: 'параллельно', 'несколько субагентов', 'запусти агентов', 'исследуй рынок', 'проанализируй конкурентов'.
Ready to connect★ 64
- View details
subagent-runnerSkillProductivity
Automatically launches and manages subagents for parallel task processing. Breaks large tasks into subtasks, runs subagents in parallel, and collects results.
Ready to connect★ 64
- View details
timeSkillProductivity
Time and timezone utilities for getting current time and converting between timezones. Use when: (1) Getting current time in any timezone, (2) Converting time between different timezones, (3) Working with IANA timezone names, (4) Scheduling across timezones, (5) Time-sensitive operations. Triggers:
Ready to connect★ 64
- View details
workflows-planSkillProductivity
Transform spec (with frontmatter claims) into an implementation plan with task decomposition and sub-agent assignment. Stage 3 of the development workflow.
Ready to connect★ 64
- View details
workflows-workSkillProductivity
Execute the implementation plan by dispatching sub-agents for each task. Stage 4 of the development workflow.
Ready to connect★ 64
- View details
zephyr-indexSkillProductivity
Static human-browsable catalog of the Zephyr RTOS skill set. Skill selection is handled by the zephyr-agent-skills entry point and by zephyr-cli skills suggest; this index is a reference listing only, not a task skill.
Ready to connect★ 63
- View details
1c-config-routerSkillProductivity
Router for 1C configuration tasks. Determines the appropriate workflow or individual skill for the user's task.
Ready to connect★ 63
- View details
1c-ssl-patternsSkillProductivity
Applied scenarios of the Standard Subsystems Library (SSL/BSP): HOW a developer's task is solved, with which library mechanism, in what order, and with what limitations. Use when you need to DO something via SSL/BSP - run a scheduled job, perform a long operation in the background, print a form, etc
Ready to connect★ 63
- View details
axiom-alarmkit-refSkillProductivity
Use when implementing alarm functionality, scheduling wake alarms, or integrating AlarmKit with Live Activities. Covers AlarmKit authorization, alarm configuration, SwiftUI views, and Live Activity integration.
Ready to connect★ 63
- View details
axiom-assume-isolatedSkillProductivity
Use when needing synchronous actor access in tests, legacy delegate callbacks, or performance-critical code. Covers MainActor.assumeIsolated, @preconcurrency protocol conformances, crash behavior, Task vs assumeIsolated.
Ready to connect★ 63
- View details
axiom-background-processingSkillProductivity
Use when implementing BGTaskScheduler, debugging background tasks that never run, understanding why tasks terminate early, or testing background execution - systematic task lifecycle management with proper registration, expiration handling, and Swift 6 cancellation patterns
Ready to connect★ 63
- View details
axiom-background-processing-diagSkillProductivity
Symptom-based background task troubleshooting - decision trees for 'task never runs', 'task terminates early', 'works in dev not prod', 'handler not called', with time-cost analysis for each diagnosis path
Ready to connect★ 63
- View details
axiom-background-processing-refSkillProductivity
Complete background task API reference - BGTaskScheduler, BGAppRefreshTask, BGProcessingTask, BGContinuedProcessingTask (iOS 26), beginBackgroundTask, background URLSession, with all WWDC code examples
Ready to connect★ 63
- View details
axiom-concurrency-profilingSkillProductivity
Use when profiling async/await performance, diagnosing actor contention, or investigating thread pool exhaustion. Covers Swift Concurrency Instruments template, task visualization, actor contention analysis, thread pool debugging.
Ready to connect★ 63
- View details
claude-code-usageSkillProductivity
[AUTO-INVOKE] MUST be invoked at the START of each new coding session. Covers context management, task strategies, and Foundry-specific workflows. Trigger: beginning of any new conversation or coding session in a Solidity/Foundry project.
Ready to connect★ 63
- View details
iceboxSkillProductivity
Icebox a raised-but-undecided concern instead of forcing a plan-or-dismiss call: record it with no verdict so the context survives. Use when a review, PR, audit, or eval surfaces something real-maybe that should not be scheduled or closed yet, or when the user says to icebox or park an item.
Ready to connect★ 63
- View details
kata-execute-phaseSkillProductivity
Use when the user wants Kata to execute planned phase work or advance tasks in the active milestone.
Ready to connect★ 63
- View details
kata-plan-phaseSkillProductivity
Use when the user asks to plan a phase, slice upcoming work, or turn a milestone goal into executable Kata tasks.
Ready to connect★ 63
- View details
kata-progressSkillProductivity
Use when the user asks for Kata project status, milestone progress, task progress, or execution state.
Ready to connect★ 63
- View details
meeting-to-tasksSkillProductivity
Full pipeline from meeting recording to development plans: local transcription with screen analysis and screenshots, task list extraction, and a separate SDD development plan for each task that requires code. ALWAYS use when the user provides a path to a meeting or call recording and wants to get ta
Ready to connect★ 63
- View details
prompt-enhancerSkillProductivity
Improves and structures short unstructured prompts and task statements, turning them into detailed imperative specifications with numbered analysis steps, explicit edge cases, and a description of the expected output format. Preserves all terms and conditions of the original and adds no new requirem
Ready to connect★ 63
- View details
- View details
solidity-debugSkillProductivity
[AUTO-INVOKE] MUST be invoked when debugging failed on-chain transactions. Covers transaction receipt analysis, gas diagnosis, calldata decoding, revert reason extraction, and state verification. Trigger: any task involving failed tx analysis, revert debugging, or on-chain transaction troubleshootin
Ready to connect★ 63
- View details
battle-planSkillProductivity
Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the batt
Ready to connect★ 62
- View details
cash-applySkillProductivity
Implement Cash tasks with a sub-agent quality gate after completion
Ready to connect★ 62
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.