ahel is live on Product Hunt today. Upvote

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

2,669 results · page 25 of 89

  • task-planningSkillProductivity

    Use when work spans multiple steps, phases, or sessions, when resuming a task started earlier, when the user asks for a plan/roadmap/progress tracking, or when they use the `/dxos:project` command (any verb — list, tasks, new, end, track, hydrate, resume). Covers the project registry, maintaining a

    Ready to connect★ 520

    github.com/dxos/dxos518 stars

    View details
  • speckit-convergeSkillProductivity

    Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

    Ready to connect★ 518

    github.com/opsmill/infrahub512 stars

    View details
  • speckit-git-featureSkillProductivity

    Validate Jira/JPD ticket reference and create a feature branch

    Ready to connect★ 518

    github.com/opsmill/infrahub512 stars

    View details
  • speckit-opsmill-autoSkillProductivity

    Run the full speckit workflow end-to-end — specify, plan, critique, tasks,

    Ready to connect★ 518

    github.com/opsmill/infrahub512 stars

    View details
  • ktloSkillProductivity

    Instructions to fetch assigned Linear issues in the current cycle and potentially kick off a development session.

    Ready to connect★ 505

    github.com/coinbase/cds499 stars

    View details
  • use-avibeSkillProductivity

    Safely inspect and modify local Avibe configuration, routing, runtime settings, watches, scheduled tasks, Avibe Cloud remote access, and operational state.

    Ready to connect★ 505

    github.com/avibe-bot/avibe498 stars

    View details
  • use-avibe-harnessSkillProductivity

    Use Avibe Harness for durable Agent delegation, Sessions, scheduled Tasks, Watches, Runs, queues, and work that must continue beyond the current turn.

    Ready to connect★ 505

    github.com/avibe-bot/avibe498 stars

    View details
  • huggingface-bestSkillProductivity

    Find and compare recommended Hugging Face models for a task using benchmarks, model size, and device constraints. Use for model selection questions; use huggingface-local-models for GGUF setup and hf-cli for Hub operations.

    Ready to connect★ 504

    github.com/waybarrios/opencode-power-pack490 stars

    View details
  • huggingface-llm-trainerSkillProductivity

    Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.

    Ready to connect★ 504

    github.com/waybarrios/opencode-power-pack490 stars

    View details
  • plan-initiativeSkillProductivity

    Interview-driven initiative → milestones → tasks: per-milestone interview, a topo-sorted sequence, and optional filing of each milestone as a ticket with blocks/blocked-by cross-refs.

    Ready to connect★ 501

    github.com/me2resh/apexyard498 stars

    View details
  • tasksSkillProductivity

    Flat actionable task list across the portfolio with direct URLs — PRs to review, issues to triage, comments, failing CI.

    Ready to connect★ 501

    github.com/me2resh/apexyard498 stars

    View details
  • gsdSkillProductivity

    Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents

    Ready to connect★ 490

    github.com/allgpt-co/quickvoice491 stars

    View details
  • gsd-plan-checkerSkillProductivity

    Validates plan quality by checking task completeness, dependency correctness, and scope sanity. Spawned by /gsd:plan-phase orchestrator.

    Ready to connect★ 490

    github.com/allgpt-co/quickvoice491 stars

    View details
  • gsd-plannerSkillProductivity

    Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by plan-phase orchestrator.

    Ready to connect★ 490

    github.com/allgpt-co/quickvoice491 stars

    View details
  • gsd-verifierSkillProductivity

    Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed.

    Ready to connect★ 490

    github.com/allgpt-co/quickvoice491 stars

    View details
  • gsd:add-todoSkillProductivity

    Add a todo item to track tasks

    Ready to connect★ 490

    github.com/allgpt-co/quickvoice491 stars

    View details
  • gsd:check-todosSkillProductivity

    Check todo list status

    Ready to connect★ 490

    github.com/allgpt-co/quickvoice491 stars

    View details
  • gsd:execute-phaseSkillProductivity

    Execute phase tasks using wave-based parallel execution

    Ready to connect★ 490

    github.com/allgpt-co/quickvoice491 stars

    View details
  • product-decision-agentSkillProductivity

    Chinese product decision Agent. For scenarios in mainland China internet products, operations, growth, monetization, data, project execution, and organizational collaboration: product planning, requirements analysis, PRDs, requirement prioritization, scheduling, version planning, Roadmap, MVP, gradu

    Ready to connect★ 485

    github.com/mxyhi/ok-skills487 stars

    View details
  • dart-use-ffigenSkillProductivity

    Guide agents to use `package:ffigen` to automatically generate FFI bindings instead of writing them manually. Use this skill when a task involves writing new FFI bindings, extending C/Objective-C/Swift integrations, or replacing hand-crafted `dart:ffi` setups.

    Ready to connect★ 484

    github.com/dart-lang/skills466 stars

    View details
  • genomilabSkillProductivity

    Run or continue patient-authorized, genome-informed GenomiLab investigations in the current Claude, Codex, or other MCP agent task. Use when a patient asks to open the Research Desk, investigate a condition against their active genome, review an existing investigation, supply follow-up information,

    Ready to connect★ 482

    github.com/exon-research/genomi481 stars

    View details
  • self-media-content-strategySkillProductivity

    Turns account positioning and business goals into an actionable social media content strategy. Use for account cold start, repositioning, setting content mix, planning column series, building a topic pool, scheduling weekly or monthly content calendars, assessing capacity, and assigning platform rol

    Ready to connect★ 480

    github.com/yanhua1010/self-media-content-workflow481 stars

    View details
  • aqe-plan-qualitySkillProductivity

    Create risk-based quality and test plans for Agentic QE changes. Use when scoping a feature, translating requirements into verification work, selecting QE specialties, assessing testability, or deciding which `.claude/agents/v3/qe-*.md` capabilities should inform a task. Do not use merely to execute

    Ready to connect★ 478

    github.com/proffesor-for-testing/agentic-qe473 stars

    View details
  • github-project-managementSkillProductivity

    Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

    Ready to connect★ 478

    github.com/proffesor-for-testing/agentic-qe473 stars

    View details
  • iterative-loopSkillProductivity

    Runs continuous AI iteration loops that repeat build-test-fix cycles until success criteria are met. Use when building features requiring test-driven refinement, implementing tasks with clear pass/fail criteria, or automating iterative improvement workflows.

    Ready to connect★ 478

    github.com/proffesor-for-testing/agentic-qe473 stars

    View details
  • n8n-trigger-testing-strategiesSkillProductivity

    Webhook testing, schedule validation, event-driven triggers, and polling mechanism testing for n8n workflows. Use when testing how workflows are triggered.

    Ready to connect★ 478

    github.com/proffesor-for-testing/agentic-qe473 stars

    View details
  • Swarm OrchestrationSkillProductivity

    Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.

    Ready to connect★ 478

    github.com/proffesor-for-testing/agentic-qe473 stars

    View details
  • confirm-failures-are-causally-linked-to-the-task-before-reportinSkillProductivity

    confirm failures are causally linked to the task before reporting rejection

    Ready to connect★ 469

    github.com/zaxbyhub/opencode-swarm464 stars

    View details
  • pre-phase-briefingSkillProductivity

    Full execution protocol for MODE: PRE-PHASE BRIEFING -- phase-start context assembly, evidence review, and task readiness checks.

    Ready to connect★ 469

    github.com/zaxbyhub/opencode-swarm464 stars

    View details
  • swarm-planSkillProductivity

    Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.

    Ready to connect★ 469

    github.com/zaxbyhub/opencode-swarm464 stars

    View details

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.

53,462 of the 53,895 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.

See how to connect your AI