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 72 of 91
- View details
support-tool-stackSkillProductivity
Customer support platform selection, setup, and optimization — Intercom, Zendesk, Front, Help Scout, HubSpot Service Hub, Linear, and AI-native tools. Use when choosing a support platform, migrating tools, setting up help desk workflows, designing ticket routing, building macros and saved replies, o
Ready to connect★ 50
- View details
Threading & Multi-ThreadingSkillProductivity
Threading patterns in Delphi — TThread, TTask, TParallel, Synchronize, Queue, thread-safety, Producer-Consumer, pools, cancellation and debugging
Ready to connect★ 51
- View details
using-gtm-skillsSkillProductivity
Route a go-to-market request to the right GTM Skills, install or verify the catalog, and compose multi-skill workflows without loading the entire library. Use when first installing gtm-skills, discovering which skill fits a task, checking available categories, or planning a workflow that spans multi
Ready to connect★ 50
- View details
context-task-classifierSkillProductivity
Use before compacting context to classify the current turn's task.
Ready to connect★ 50
- View details
dag-schedulingSkillProductivity
Usar cuando se orquestan múltiples agentes SDD con dependencias entre ellos.
Ready to connect★ 50
- View details
- View details
- View details
meta-reflectionSkillProductivity
Protocol of the 4 meta-questions for questioning the framing of a task before executing it. SPEC-194. Use when criterion-simulation-judge activates with FRAME_DOUBT or FRAME_REJECT, or when the operator wants manual reflection before a high-impact decision.
Ready to connect★ 50
- View details
org-meeting-captureSkillProductivity
Tacit Knowledge Capture for Meetings: extracts decision-makers, informal agreements, and political signals from transcripts.
Ready to connect★ 50
- View details
overnight-sprintSkillProductivity
Use when you want to run low-risk tasks autonomously overnight.
Ready to connect★ 50
- View details
parallel-dispatchSkillProductivity
Use when parallel subagents with admission-handle are needed — launches N tasks in the background and collects results later, without blocking the parent turn. Triggers: launch subagents in parallel, parallelize this, admission-handle, collect results.
Ready to connect★ 50
- View details
pbi-decompositionSkillProductivity
Use when decomposing a PBI into tasks and estimating hours.
Ready to connect★ 50
- View details
risk-scoringSkillProductivity
Use when calculating the risk of a task to decide the level of review required.
Ready to connect★ 50
- View details
skill-evaluationSkillProductivity
Use when you need to select the most appropriate skill for a given task.
Ready to connect★ 50
- View details
smart-calendarSkillProductivity
Usar cuando se gestiona la agenda inteligente con sincronización Outlook/Teams.
Ready to connect★ 50
- View details
speq-implementSkillProductivity
Orchestrate implementation of a reviewed plan: task breakdown, TDD sub-agents, code review, and verification report. Use when the user asks to implement, build, or execute a plan under specs/_plans/ — after /speq-plan, before /speq-record. Arg: <plan-name>.
Ready to connect★ 50
- View details
superplanSkillProductivity
Use when starting significant features, epics, or complex tasks. Creates multi-phase implementation plans with parallelizable phases, poker estimates, TDD-first acceptance criteria, and quality gates. Detects tech stack from CLAUDE.md/AGENTS.md (bypassing internet research if complete) or via codeba
Ready to connect★ 50
- View details
transcriptor-digestSkillProductivity
Use when new folders are detected in the transcriptor meetings directory or when you want to digest transcripts and screenshots of meetings captured by Savia Sonora (formerly Savia Transcriptor). Triggers: digerir reuniones, transcriptor, reuniones nuevas, digest de la reunion, capturas de la re
Ready to connect★ 50
- View details
vowlineSkillProductivity
Universal operating skill: bind the public task, act from evidence, preserve boundaries, and verify the delivered result.
Ready to connect★ 50
- View details
write-a-skillSkillProductivity
Guide for correctly creating a new skill in pm-workspace. Use when a task is repeated 2+ times or takes more than 15 minutes.
Ready to connect★ 50
- View details
dough-adr-awarenessSkillProductivity
Use and cite this project's current Accepted Architectural Decision Records for architecture-shaped work, follow supersession, surface conflicts instead of silently drifting, and preserve human ownership of decisions and exceptions. Use when a task mentions ADRs or architectural constraints, may rev
Ready to connect
- View details
fable-advisorSkillProductivity
Use when the user wants a task executed by the current session model with a persistent Fable 5.1 advisor overseeing it. A read-only Fable 5.1 subagent writes the plan and answers checkpoint consults; a separate fresh Fable 5.1 reviewer issues a binding pre-commit verdict. Accepts a GitHub issue or a
Ready to connect
- View details
fable-orchestrateSkillProductivity
Use when the user wants a task decomposed and driven by a Fable 5.1 orchestrator delegating implementation to Sonnet 5 workers. Fable decomposes into self-contained specs, dispatches Sonnet workers (Agents for 1–2 pieces, a Workflow for fan-out), reviews each result, merges into one branch, and take
Ready to connect
- View details
fableplanSkillProductivity
Use when the user wants a task planned by a Fable 5.1 planning subagent before building it. Spins up a Plan subagent running on Fable 5.1 to produce an implementation plan, relays the plan back to the main agent, and — if a GitHub issue is referenced — posts the plan as a comment on that issue and a
Ready to connect
- View details
fest-executionSkillProductivity
Execute active festival tasks. Use when finding the next task, marking tasks completed/blocked/reset, committing with festival traceability, advancing workflow steps, and validating sequence progress.
Ready to connect
- View details
fest-methodologySkillProductivity
Use when the user mentions festivals, the fest CLI, phases, sequences, or tasks, or when working inside a `festivals/` directory. Provides the core Festival methodology model so Claude understands the planning system.
Ready to connect
- View details
fest-planningSkillProductivity
Plan and scaffold festivals. Use when creating festival/phase/sequence/task structure, enforcing naming rules, linking festivals to projects, and promoting lifecycle states.
Ready to connect
- View details
issueplanSkillProductivity
Use when the user wants the current large language model to plan and build a task in the same session without a subagent. When an issue is referenced, it posts the plan and asks whether to build. Without an issue, it builds and opens a pull request after presenting the plan. Trigger on "/issueplan",
Ready to connect
- View details
metacognitionSkillProductivity
Checks task understanding, evidence, scope, and stopping conditions at decision-changing moments. Use when starting repository work, changing task type, encountering unexpected evidence, or completing a meaningful phase.
Ready to connect
- View details
context-optimizerSkillProductivity
Context optimization expert. Specializes in context management, token efficiency, and performance optimization in long conversations. Solves issues such as lost-in-middle and context poisoning to improve AI agent performance on complex tasks.
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.