关于
This CLI tool installs pre-built skills, agents, and teams from the agent-almanac repository into your supported agentic framework. It automatically detects your framework, resolves dependencies, and can sync installations using a manifest file. Use it to quickly bootstrap agentic capabilities in a new project or maintain a consistent setup across multiple frameworks.
快速安装
Claude Code
推荐npx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/install-almanac-content在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Install Almanac Content
Use agent-almanac CLI to install skills, agents, teams into any supported agentic framework.
When Use
- Setting up new project, need to install agentic skills, agents, teams
- Installing all skills from specific domain (
r-packages,devops) - Targeting multiple frameworks simultaneously (Claude Code, Cursor, Copilot)
- Creating or syncing declarative
agent-almanac.ymlmanifest for reproducible setups - Auditing installed content for broken symlinks or stale references
Inputs
- Required: Content to install -- one or more skill, agent, team IDs (
create-skill,r-developer,r-package-review) - Optional:
--domain <domain>-- install all skills from domain instead of naming individual IDs - Optional:
--framework <id>-- target specific framework (default: auto-detect all) - Optional:
--with-deps-- also install agent skills + team agents+skills - Optional:
--dry-run-- preview changes without writing to disk - Optional:
--global-- install to global scope instead of project scope - Optional:
--force-- overwrite existing content - Optional:
--source <path>-- explicit path to agent-almanac root (default: auto-detect)
Steps
Step 1: Detect Frameworks
Run framework detection to see which agentic tools present in current project:
agent-almanac detect
Scans working directory for configuration files + directories (.claude/, .cursor/, .github/copilot-instructions/, .agents/) + reports which frameworks active.
Got: Output lists one or more detected frameworks with adapter status. No frameworks detected? Universal adapter (.agents/skills/) used as fallback.
If fail: CLI not found? Ensure installed + on PATH. Detection returns nothing but you know framework is present? Use --framework <id> to specify explicit. Run agent-almanac list --domains to verify CLI can reach registries.
Step 2: Search for Content
Find skills, agents, teams by keyword:
agent-almanac search <keyword>
Browse by category:
agent-almanac list --domains # List all domains with skill counts
agent-almanac list -d r-packages # List skills in a specific domain
agent-almanac list --agents # List all agents
agent-almanac list --teams # List all teams
Got: Search results or filtered lists display matching content with IDs + descriptions.
If fail: No results appear? Try broader keywords. Verify almanac root reachable: agent-almanac list should show full skill count. Can't find root? Pass --source /path/to/agent-almanac.
Step 3: Install Content
Install one or more items by name:
# Install specific skills
agent-almanac install create-skill write-testthat-tests
# Install all skills from a domain
agent-almanac install --domain devops
# Install an agent with its skills
agent-almanac install --agent r-developer --with-deps
# Install a team with its agents and their skills
agent-almanac install --team r-package-review --with-deps
# Target a specific framework
agent-almanac install create-skill --framework cursor
# Preview without writing
agent-almanac install --domain esoteric --dry-run
# Install to global scope
agent-almanac install create-skill --global
CLI resolves content from registries, selects appropriate adapter for each detected framework, writes files to framework-specific paths (.claude/skills/ for Claude Code, .cursor/rules/ for Cursor).
Got: Output confirms number of items installed + target framework(s). Installed content appears in correct framework directory.
If fail: Items not found? Verify ID matches name field in registry (skills/_registry.yml, agents/_registry.yml, teams/_registry.yml). Files already exist + installation skipped? Use --force to overwrite.
Step 4: Verify Installation
Run health check on all installed content:
agent-almanac audit
Audit specific framework or scope:
agent-almanac audit --framework claude-code
agent-almanac audit --global
See what currently installed:
agent-almanac list --installed
Got: Audit reports all installed items healthy with no broken references. --installed listing shows each item with type + framework.
If fail: Audit reports broken items? Reinstall with --force. Symlinks broken? Verify almanac source path hasn't moved. Run agent-almanac install <broken-id> --force to repair.
Step 5: Manage with Manifest (Optional)
Reproducible setups → use declarative agent-almanac.yml manifest:
# Generate a starter manifest
agent-almanac init
Creates agent-almanac.yml in current directory with detected frameworks + placeholder content lists. Edit file to declare desired skills, agents, teams:
source: /path/to/agent-almanac
frameworks:
- claude-code
- cursor
skills:
- create-skill
- domain:r-packages
agents:
- r-developer
teams:
- r-package-review
Then install everything declared in manifest:
agent-almanac install
Reconcile installed state with manifest (install missing, remove extra):
agent-almanac sync
agent-almanac sync --dry-run # Preview first
Got: Running install with no arguments reads manifest + installs all declared content. Running sync brings installed state into alignment with manifest, adding missing items + removing undeclared.
If fail: sync reports "No agent-almanac.yml found"? Run agent-almanac init first. Manifest resolves to 0 items? Check skill/agent/team IDs match registry entries exact. Comment lines starting with # ignored.
Step 6: Manage Teams as Campfires (Optional)
Campfire commands provide warm, team-oriented alternative to install --team:
# Browse all available team circles
agent-almanac campfire --all
# Inspect a specific circle (members, practices, pattern)
agent-almanac campfire tending
# See shared agents between teams (hearth-keepers)
agent-almanac campfire --map
# Gather a team (install with arrival ceremony)
agent-almanac gather tending
agent-almanac gather tending --ceremonial # Show each skill arriving
agent-almanac gather tending --only mystic,gardener # Partial gathering
# Check fire health (burning / embers / cold)
agent-almanac tend
# Scatter a team (uninstall with farewell)
agent-almanac scatter tending
Campfire state tracked in .agent-almanac/state.json (git-ignored, local to project). Fires have thermal states: burning (used within 7 days), embers (within 30 days), cold (30+ days). Running tend warms all fires + reports health.
Shared skills protected during scatter — if skill needed by another gathered fire, stays installed. Shared agents walk between fires rather than being duplicated.
All campfire commands support --quiet (standard reporter output) + --json (machine-parseable) for scripting.
Got: Teams gathered + managed with state tracking. campfire --all shows fire states. tend reports health.
If fail: Campfire state corrupted? Delete .agent-almanac/state.json + re-gather teams. gather fails? Check team name matches entry in teams/_registry.yml.
Checks
-
agent-almanac detectshows expected frameworks -
agent-almanac list --installedshows all intended content -
agent-almanac auditreports no broken items - Installed skills resolve in target framework (
/skill-nameworks in Claude Code) - Using manifest →
agent-almanac sync --dry-runreports no changes needed
Pitfalls
- Forgetting
--with-depsfor agents + teams: Installing agent without--with-depsinstalls only agent definition, not referenced skills. Agent present but unable to follow skill procedures. Always use--with-depsfor agents + teams unless already installed dependencies separately. - Manifest drift: After manual install or remove content, manifest falls out of sync with actual installed state. Run
agent-almanac syncperiodically, or always install through manifest to keep aligned. - Scope confusion (project vs global): Content installed with
--globalgoes to~/.claude/skills/(or equivalent); project-scope content goes to.claude/skills/in current directory. Skill not found? Check whether installed in wrong scope. - Stale source path: agent-almanac repository moved or renamed?
--sourcepath in manifests + auto-detection breaks. Updatesourcefield inagent-almanac.ymlor re-runagent-almanac init. - Framework not detected: Detector looks for specific files + directories. Freshly initialized project may not have these yet. Use
--framework <id>explicit until project has expected structure, or rely on universal adapter. - Campfire thermal state confusion: Fires go cold after 30 days without use. Running
agent-almanac tendresets timer for all gathered fires. Fire shows as "cold" → still fully installed — thermal state reflects recency of use, not installation health.
See Also
create-skill-- author new skills to add to almanac before installingconfigure-mcp-server-- set up MCP servers that agents may need after installationwrite-claude-md-- configure CLAUDE.md to reference installed skillsaudit-discovery-symlinks-- diagnose symlink issues for Claude Code skill discoverydesign-cli-output-- terminal output patterns used by CLI reporter + campfire ceremony
GitHub 仓库
Frequently asked questions
What is the install-almanac-content skill?
install-almanac-content is a Claude Skill by pjt222. Skills package instructions and resources that Claude loads on demand, so Claude can perform install-almanac-content-related tasks without extra prompting.
How do I install install-almanac-content?
Use the install commands on this page: add install-almanac-content to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does install-almanac-content belong to?
install-almanac-content is in the Meta category, tagged ai.
Is install-almanac-content free to use?
Yes. install-almanac-content is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
