{
  "markdown": "# skillers\n\nLearn from your workflow patterns and suggest skills, hooks, and agents to automate repetitive work.\n\n## How It Works\n\n1. Work normally - your AI tool saves conversation transcripts automatically (Claude Code, Codex, OpenCode)\n2. `/skillers compact` - Analyze transcripts and extract recurring patterns into weighted knowledge\n3. `/skillers recommend` - Get actionable suggestions for automation\n\n## Commands\n\n| Command | Description |\n|---|---|\n| `/skillers show` | Show status, transcript stats, and knowledge themes |\n| `/skillers compact [--days=N]` | Analyze transcripts and extract patterns |\n| `/skillers recommend` | Suggest skills, hooks, and agents to create |\n\n## What It Finds\n\n- Pain points (\"this auth flow is broken again\")\n- Repeated requests (\"run tests after editing auth/\")\n- Task themes (\"refactoring the login module\")\n- Wishes (\"I wish the AI knew our API patterns\")\n- Workflow sequences (multi-step patterns you follow consistently)\n\n## What It Ignores\n\n- API keys, passwords, or secrets\n- One-off tasks that won't recur\n- Normal productive work without friction\n\n## Architecture\n\n```\nTranscripts (Claude Code, Codex CLI, OpenCode)\n  ↓ /skillers compact (auto-detects installed tools)\nKnowledge themes (weighted JSON, frequency + recency + cross-session)\n  ↓ /skillers recommend (ecosystem-aware)\nRanked suggestions → user picks → scaffold via existing tools\n```\n\n## Part of agentsys\n\n- https://github.com/agent-sh/agentsys\n- https://agentskills.io\n",
  "bytes": 1484,
  "sha": "bc6616dff157617ee2fe7c961c79a7a8683a3ddfd92e2c3643969bbc19a3f14e",
  "repo_slug": "agent-sh/skillers",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_agent_sh_skillers_skillers_9ee3b557/readme"
}