SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

agentskillsagentskills/agentskills

Provides a skill packaging specification for AI agents that can be authored, discovered, activated, and executed,…

No ratings yet Rate this skill
Stars26.4k
Forks1.9k
Watchers26.4k
Open Issues105

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/agentskills/agentskills.git

OverviewOverview

Key Features

Provides a skill packaging specification for AI agents that can be authored, discovered, activated, and executed, turning domain knowledge and operational procedures into skill packages agents can call directly. Key capabilities include: 1. Domain expertise encapsulation: writes expert knowledge and decision rules of a specific domain into skill files so agents can invoke them directly in matching tasks, reducing ad-hoc prompt stacking; 2. Repeatable workflow definition: solidifies multi-step operational procedures into repeatable skills so the same workflow yields consistent results across invocations instead of re-describing steps each time; 3. Cross-product reuse: the same skill package can be reused across different agent products and runtime environments without rewriting logic per platform; 4. Skill discovery: provides a skill inventory and metadata so agents or users can search and identify available skills; 5. Skill activation: matches and activates the corresponding skill based on task context so the agent loads the right capability at the right time; 6. Skill execution: drives the agent to complete concrete operations according to the skill definition, turning skill descriptions into actual execution steps.

Use Cases

Writing reusable skill packages for agents, capturing domain expertise, defining repeatable workflows, reusing the same skill across products, skill discovery and activation, skill execution orchestration.

Target Roles

AI / Algorithm Engineer, Full-stack / Indie Developer, Product Manager (PM), DevOps / Operations Engineer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID69
Data sourceGitHub
Repositoryagentskills/agentskills
CategoryAI & Agent Skills / Agent Skill Framework & Workflows
Primary languagePython
LicenseApache License 2.0
Default branchmain
GitHub repository ID1117639997
Node IDR_kgDOQp3VPQ
Rank#60 (position within the source ranking)
Site-wide popularity rank#75 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

010k20k30k2026-10-102026-10-222026-10-10 · 26,0072026-10-14 · 26,0072026-10-16 · 26,0072026-10-22 · 26,372
  • Now26,372
  • Previous point · 10-16 26,007
  • vs previous point +365
  • 4 data points 12 days
05001k1.5k2k2026-10-102026-10-222026-10-10 · 1,9562026-10-14 · 1,9562026-10-16 · 1,9562026-10-22 · 1,939
  • Now1,939
  • Previous point · 10-16 1,956
  • vs previous point -17
  • 4 data points 12 days

TimelineTimeline

Repository created2025-12-16 15:47:1911 months ago
Data last updated2026-10-26 11:43:0821 days ago
Last commit2026-08-09 20:36:043 months ago

CommitLatest commit

committed by Patrick-Erichsen. Category: New Features & Capability Expansion. Commit message: docs: add OpenClaw to client showcase (#492).

69ef37e Patrick-Erichsen 2026-08-09

Next stepsNext steps