skillers
Learn from your workflow patterns and suggest skills, hooks, and agents to automate the repetitive work. Skillers reads your AI conversation
Open source Open in the app JSON README (API)
About
Learn from your workflow patterns and suggest skills, hooks, and agents to automate the repetitive work. Skillers reads your AI conversation transcripts (Claude Code, Codex CLI, OpenCode), extracts recurring patterns into themed weighted-knowledge files, then recommends concrete skills/hooks/agents to codify them. Two phases: `/skillers compact` analyzes transcripts and writes `.skillers/<theme>.md` knowledge files; `/skillers recommend` reads accumulated knowledge plus your existing plugin/skill ecosystem and suggests automations that don't already exist. The output is "here are 4 patterns I see you doing manually every week and the exact SKILL.md / hooks.json that would automate each."
Details
- Kind
- Plugins
- Topic
- Developer tools
- Publisher
- agent-sh
- Origin
- marketplace
- Category
- ferramentas
- Stars
- 3
- Forks
- 1
- Last push
- 2026-05-30T09:49:30Z
- Repository state
- ativo
- Language
- JavaScript
- Added
- 2026-08-30 01:48:58
- Updated
- 2026-08-30 01:48:58
- Origin id
agent-sh/skillers/skillers
README
# skillers
Learn from your workflow patterns and suggest skills, hooks, and agents to automate repetitive work.
## How It Works
1. Work normally - your AI tool saves conversation transcripts automatically (Claude Code, Codex, OpenCode)
2. `/skillers compact` - Analyze transcripts and extract recurring patterns into weighted knowledge
3. `/skillers recommend` - Get actionable suggestions for automation
## Commands
| Command | Description |
|---|---|
| `/skillers show` | Show status, transcript stats, and knowledge themes |
| `/skillers compact [--days=N]` | Analyze transcripts and extract patterns |
| `/skillers recommend` | Suggest skills, hooks, and agents to create |
## What It Finds
- Pain points ("this auth flow is broken again")
- Repeated requests ("run tests after editing auth/")
- Task themes ("refactoring the login module")
- Wishes ("I wish the AI knew our API patterns")
- Workflow sequences (multi-step patterns you follow consistently)
## What It Ignores
- API keys, passwords, or secrets
- One-off tasks that won't recur
- Normal productive work without friction
## Architecture
```
Transcripts (Claude Code, Codex CLI, OpenCode)
↓ /skillers compact (auto-detects installed tools)
Knowledge themes (weighted JSON, frequency + recency + cross-session)
↓ /skillers recommend (ecosystem-aware)
Ranked suggestions → user picks → scaffold via existing tools
```
## Part of agentsys
- https://github.com/agent-sh/agentsys
- https://agentskills.io