Agent Skillsfastclaw-ai/fastclaw › fastclaw-skill-learner

fastclaw-skill-learner

GitHub

分析对话以提取可复用的多步骤工作流模式,用于自动生成技能文档。

skills/fastclaw-skill-learner/SKILL.md fastclaw-ai/fastclaw

Trigger Scenarios

分析复杂多步任务对话 识别可重复使用的通用工作流程

Install

npx skills add fastclaw-ai/fastclaw --skill fastclaw-skill-learner -g -y
More Options

Use without installing

npx skills use fastclaw-ai/fastclaw@fastclaw-skill-learner

指定 Agent (Claude Code)

npx skills add fastclaw-ai/fastclaw --skill fastclaw-skill-learner -a claude-code -g -y

安装 repo 全部 skill

npx skills add fastclaw-ai/fastclaw --all -g -y

预览 repo 内 skill

npx skills add fastclaw-ai/fastclaw --list

SKILL.md

Frontmatter
{
    "name": "fastclaw-skill-learner",
    "metadata": {
        "fastclaw": {
            "always": true
        }
    },
    "description": "Analyze conversations to extract reusable skill patterns. Used internally by FastClaw to auto-generate skills from complex multi-step tasks."
}

Skill Learner

Analyze a conversation and determine if it demonstrates a reusable multi-step workflow that should be saved as a skill.

When to Extract

Extract a skill when ALL of the following are true:

  • The task involved 3+ tool calls in a clear, repeatable sequence
  • The steps form a general procedure useful beyond this specific conversation
  • The workflow is not trivially simple (not just "read a file and summarize it")

Do NOT extract when:

  • The task is one-off or highly specific to current context
  • The steps are standard and don't need specialized instructions
  • A similar skill already exists

How to Analyze

Given a conversation transcript, identify:

  1. The core workflow — What sequence of actions was performed?
  2. The pattern — Is this generalizable to other inputs/contexts?
  3. The value — Would having this as a skill save significant effort next time?

Output Format

If the conversation demonstrates a reusable skill, output JSON:

{
  "extract": true,
  "skill": {
    "name": "Human Readable Name",
    "slug": "kebab-case-slug",
    "description": "One-line description of what this skill does and when to trigger it",
    "content": "Full SKILL.md content with YAML frontmatter and markdown instructions"
  }
}

If not reusable, output:

{
  "extract": false
}

Skill Content Guidelines

When generating the SKILL.md content:

  • Include proper YAML frontmatter with name and description
  • Write clear step-by-step instructions in markdown
  • Generalize from the specific conversation — replace specific values with placeholders
  • Explain the reasoning behind each step, not just the commands
  • Include example inputs/outputs where helpful
  • Keep under 500 lines
  • Use {baseDir} for any bundled resource references

Example Extraction

A conversation where the user asks to set up a new Go project with CI, and the agent creates go.mod, writes a Makefile, sets up GitHub Actions, and adds a Dockerfile — this is a good extraction candidate because:

  • Multiple coordinated steps (4+ tool calls)
  • Generalizable to any new Go project
  • Saves significant setup time

The extracted skill would capture the project structure, file templates, and the sequence of steps, parameterized for project name and Go version.

Version History

  • beee30c Current 2026-07-25 08:17

Same Skill Collection

internal/agent/bundled_skills/camoufox-cli/SKILL.md
internal/agent/bundled_skills/skill-creator/SKILL.md
skills/code-runner/SKILL.md
skills/data-analysis/SKILL.md
skills/fastclaw-skill-guide/SKILL.md
skills/image-gen/SKILL.md
skills/skill-creator/SKILL.md
skills/translation/SKILL.md
skills/web-search/SKILL.md
internal/agent/bundled_skills/find-skills/SKILL.md
skills/find-skills/SKILL.md

Metadata

Files
0
Version
533a138
Hash
d18b4231
Indexed
2026-07-25 08:17

Accueil - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-27 14:21
浙ICP备14020137号-1 $Carte des visiteurs$