Loading...
Loading...
Found 72 Skills
Specification-driven implementation — Execute implementation from specs to PR. Reads issue-to-pr-workflow.md as playbook, enforces coding-rules.md as quality gates, tracks progress via tasks.md checkboxes with resume capability. English triggers: "Implement from spec", "Start implementation", "Execute spec tasks" 日本語トリガー: 「仕様書から実装」「実装を開始」「specタスクを実行」
Daily startup and closeout rituals. Use when: (1) starting the workday; (2) wrapping up the day. NOT for: mid-day task management (use task); compound loop (use work); memory directly (use memory).
List pending todos and select one to work on
Transform Claude Code into an AI Scientist that orchestrates research workflows using tree-based hypothesis exploration. Triggers on "research project", "scientific experiment", "run experiments", "AI scientist", "tree search experimentation", "systematic study".
Configure kata workflow toggles and model profile. Triggers include "settings".
Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.
ABC Jenkins Project Deployment Skill. Supports intelligent parameter inference and interactive triggering of Jenkins builds, automatically retrieves Git branch and tag information. This skill is triggered when users request "Deploy Jenkins", "Trigger Build", "Deploy Project", "Jenkins Deployment" or similar operations. Requires environment variables JENKINS_USER and JENKINS_TOKEN.
Backend-agnostic task management. Use when: (1) creating, listing, updating, or archiving tasks; (2) analysing task status; (3) setting up task backend. NOT for: memory population (use memory); session management (use memory session).
Generate a branded social media image announcing a new feature or update. Analyzes git history, auto-detects brand from codebase (Tailwind, CSS vars, design tokens), replicates UI elements, and captures via Playwright. Use when the user wants to create an announcement image, says 'feature image,' 'announcement graphic,' 'social image for feature,' or wants to visually announce a code change.
Generate a handoff document after implementation work is complete — summarizes changes, risks, and review focus areas for the review pipeline. Use when done coding and ready to hand off for review.
Records completed work progress to .trellis/workspace/ journal files after human testing and commit. Captures session summaries, commit hashes, and updates developer index files for future session context. Use when a coding session is complete, after the human has committed code, or to persist session knowledge for future AI sessions.
Runs ML experiments reproducibly — single runs or autonomous BFS batches. Single mode: isolated venv, time-budgeted, failure-handled, logs to RESEARCH.md. BFS mode (opt-in): designs N hypotheses, runs each for a fixed budget, compares via a single verifiable metric, keeps improvements and git-resets failures — fully autonomous until done. Respects the RESEARCH.md supervision policy for notifications, approvals, and stop limits. Trigger phrases: "run experiment", "train model", "explore design space", "find best config", "autoresearch".