3in-in-no
Community@tinner-deinno
tinner in innova de
Agent Skills by 3in-in-no
Showing 93 vetted skills indexed across 1 GitHub repositories.
model-thaiLLM
Route Thai language tasks to specialized ThaiLLM models by detecting task intent.
recap
Summarize handoffs, focus, and git state to restore session context.
model-openclaude
Launch OpenClaude with selectable model providers for Thai and multilingual prompts.
model-MDES
Route prompts to the MDES Ollama endpoint for Thai and general model responses.
management-talk
Rewrite engineering updates into leadership-ready communication for JIRA, Slack, and email.
debug-mantra
Diagnose runtime errors through reproduction, fail-path tracing, and hypothesis testing.
scrutinize
Verify plans, PRs, and code changes against stated intent and execution paths.
learn
Generate organized codebase documentation into a local docs workspace.
monitor
Display real-time TUI dashboards for multi-agent gang status and logs.
trace
Search git history, repos, and Oracle memory to locate project files and code.
model-copilot
Sends prompts to GitHub Copilot-capable models with selectable model IDs and token usage logging.
self-improve
Run PDCA cycles to store goal attempts as learning history.
talk-to
Route user messages to target Oracle agents via contacts and persistent threads.
learnself
Learns from session history and transfers pending work between agents via packaged, status-tracked handoffs.
post-mortem
Generate a canonical engineering post-mortem record for a fixed bug.
team-agents
Coordinate parallel agent teams for complex tasks with dependencies and status tracking.
dig
Mine Claude Code jsonl session files to reconstruct timelines and attribute work to repositories.
jit
Route slash-command tasks and status queries to the Boss Orchestrator.
awaken
Initialize an Oracle identity by collecting inputs and writing CLAUDE.md and memory artifacts.
rrr
Generate session retrospectives, AI diaries, and lessons learned files.
model-GPT
Sends prompts to the OpenAI API with automatic model selection and token logging.
mdes-ollama
Select token-safe AI models by testing the mdes.ollama endpoint with fallback.
model-claude
Route coding tasks to Sonnet, Opus, or Haiku models via flags or settings.
xray
Audit Claude Code auto-memory, installed Oracle skills, and session history.