agent-skills

Activation MethodThe mechanism by which an agent activates a skill.Agent File FormatOn-disk format a client expects for agent/subagent definition files. Different AI agent products have converged on different representations for the same…Agent File FormatThe on-disk file format this client reads for agent definitions. Installers must write each Agent in this format when deploying to this client. Named…Agents (cross-client default)The cross-client interoperable default. Any AI agent product that reads from the .agents/ tree can consume skills and agents deployed under this client. Pick…Allowed ToolsOptional, experimental. Tools that are pre-approved to run without user confirmation when this skill is active. Serialized to SKILL.md as a space-separated…Asset ResourceStatic resources in assets/ such as templates, images, or data files.BashExecute shell commands.BodyFull markdown content for this section, including prose, code blocks, tables, and lists. This is rendered directly in the SKILL.md output. CatalogAt session start, agents load only the name and description of each available skill - just enough to know when it might be relevant. Claude CodeAnthropic's Claude Code CLI and desktop agent. Reads skills from .claude/skills/ and subagent definitions from .claude/agents/ at both project and user scopes.…ClientAn AI agent runtime or product that discovers and uses skills (and, from 1.2.0, agent/subagent definitions) from known on-disk locations. Each Client instance…Client IDShort identifier used on the command line to select a client when installing a skill or agent (e.g., "agents", "claude-code", "codex", "gemini"). Lowercase…CommandA shell command to execute this script.CompatibilityOptional. Max 500 characters. Indicates environment requirements such as intended agent product, required system packages, or network access. ContentThe text content of this resource.DescriptionRequired. 1-1024 characters. Describes what the skill does and when to use it. Should include keywords that help agents identify relevant tasks. Disclosure TierA stage in the progressive disclosure architecture that controls how much of a skill is loaded into agent context and when. Discovery PathA filesystem location where agents scan for installed skills. Superseded in 1.1.0 by the Client class. Retained for backward compatibility. Discovery ScopeWhether a discovery path is project-level or user-level.EditMake targeted edits to existing files.File Read ActivationModel-driven activation where the agent uses its standard file-read tool to read the SKILL.md file. Gemini CLIGoogle's Gemini CLI. Reads subagent definitions from .gemini/agents/ as Markdown files with YAML frontmatter, the same format Claude Code uses. Skill discovery…GlobFind files by pattern.GrepSearch file contents by pattern.Has AssetEmbedded static assets within this section. Provides structured metadata for programmatic extraction alongside the body content. Has ReferenceEmbedded reference material within this section. Provides structured metadata for programmatic extraction alongside the body content. Has ResourceA supporting file bundled with this skill. Use for standalone resources not tied to a specific section. For section-local resources, use…Has ScriptEmbedded executable scripts within this section. Provides structured metadata for programmatic extraction alongside the body content. Has SectionOrdered list of content sections that form the skill's documentation. Each section becomes a headed section in the generated SKILL.md. Sections are rendered in…InstructionsWhen a task matches a skill's description, the agent reads the full SKILL.md body into context. LanguageThe programming language of the script (e.g., bash, python, javascript).LicenseOptional. The license applied to the skill. May be referenced by name (e.g., "license: MIT") or embedded inline for custom licenses. Markdown with YAML FrontmatterA plain Markdown file beginning with a YAML frontmatter block (delimited by triple-dash lines) that carries the agent's name, description, tools, model, and…MetadataOptional. Arbitrary key/value metadata on the skill, modeled as a list of MetadataEntry instances. Clients can use this to store additional properties that the…Metadata EntryA single key/value pair in a skill's metadata map. The Agent Skills spec allows arbitrary string-to-string metadata on a skill; each entry in that map is…Metadata KeyThe key portion of a metadata entry.Metadata ValueThe value portion of a metadata entry.NameRequired. 1-64 characters, lowercase letters, numbers, and hyphens only. Must not start or end with a hyphen, must not contain consecutive hyphens, and must…OpenAI CodexOpenAI's Codex CLI. Reads skills from the cross-client .agents/skills/ tree and reads subagent definitions from .codex/agents/ as TOML files. The TOML schema…Path PatternThe filesystem path pattern for this discovery location.Path ScopeWhether this path is project-level or user-level.Project Agent DirectoryRelative directory path, from the project root, where this client expects project-scoped agent (subagent) definitions to live. The installer writes one file…Project Agents SkillsCross-client interoperable skills in the project directory.Project Client SkillsClient-specific skills in the project directory.Project ScopeSkills specific to a project or repository.Project Skill DirectoryRelative directory path, from the project root, where this client expects project-scoped skills to live. The installer appends the skill's name to this path to…ReadRead file contents.Reference ResourceAdditional documentation in references/ that agents can read on demand.Resource TitleA short title describing this resource.ResourcesThe agent follows the instructions, loading referenced scripts, documentation, and assets on demand as needed. Script ResourceExecutable code in scripts/ that agents can run.SkillA directory containing a SKILL.md file that provides an AI agent with instructions, scripts, and resources to perform a specific task. Follows the open Agent…Skill File NameFile name the client reads to discover a skill's frontmatter and instructions inside each skill directory. Defaults to "SKILL.md" for clients that follow the…Skill ResourceA supporting file bundled with a skill.Skill SectionA section of skill content with a title, markdown body, and optional embedded resources. Sections are ordered within a skill and each becomes a headed section…Tier OrderThe sequence number of this tier in the progressive disclosure architecture.TitleThe section heading. Rendered as a level-2 markdown heading (##) in the generated SKILL.md. Token BudgetRecommended token cost for this tier.TOMLA TOML file where all agent configuration - including the developer instructions that serve as the system prompt - lives under named keys, not separated into a…ToolA capability that an agent can invoke, such as reading files, running shell commands, or searching code. Skills declare which tools they are pre-approved to…Tool ActivationModel-driven activation via a dedicated activate_skill tool registered by the agent runtime. User Agent DirectoryDirectory path, rooted at the user home directory, where this client expects user-scoped agent definitions to live. The literal "~" at the start is expanded to…User Agents SkillsCross-client interoperable skills in the user home directory.User Client SkillsClient-specific skills in the user home directory.User Explicit ActivationUser-initiated activation via slash command (/skill-name) or mention syntax ($skill-name). User ScopeSkills available across all projects for a user.User Skill DirectoryAbsolute-ish directory path, rooted at the user home directory, where this client expects user-scoped skills to live. The literal "~" at the start is expanded…Web FetchFetch content from a URL.Web SearchSearch the web.WriteWrite or create files.