Loading...
Loading...
Found 123 Skills
Capture and resolve deferred items from a session ('we'll come back to that'). Use $ARGUMENTS as the promise text, or --list / --resolve N.
Deterministic plan lifecycle management via scripts/plan-manager.py: create, track, check, complete, and abandon task plans. Use when user says "/plans", needs to create a multi-phase plan, track progress on active plans, or manage plan lifecycle (complete, abandon, audit). Do NOT use for one-off tasks that need no tracking, feature implementation, or debugging workflows.
Record and track work progress by maintaining a structured personal Lark/Feishu spreadsheet discovered by the literal [worklog] title marker. Use when the user records fragmented work todos or progress, marks work complete, adds task aliases, creates a new work-log task and its long-lived document, updates related links or design decisions, rolls the log into a new day or month, inspects the current work-log structure, or authorizes creation of a new one. Requires the official lark-shared, lark-drive, lark-sheets, and lark-doc skills.
Epic decomposition into trackable issues. Triggers: "create a plan", "plan implementation", "break down into tasks", "decompose into features", "create beads issues from research", "what issues should we create", "plan out the work".
Use beads (bd) for persistent task tracking in coding projects. A git-backed issue tracker designed for AI agents with dependency graphs, hierarchical tasks, and multi-agent coordination.
ADHD-optimized task state machine with abandonment detection and interventions. Use when: (1) user initiates any task, (2) providing solutions to problems, (3) detecting context switches, (4) user says "done", "completed", "finished", (5) session ends with pending tasks, (6) >30 minutes since solution provided. Tracks complexity, clarity, domain (BUSINESS/MICHAEL/FAMILY/PERSONAL), and triggers interventions.
Specification-driven development with structured phases: Initialize, Plan, Tasks, Implement+Validate. Creates structured feature specs with traceability to requirements. Use when: starting projects, planning features, implementing with verification, or tracking decisions across sessions. Triggers on "map codebase", "initialize", "initialize project", "create feature", "plan", "tasks", "implement", "validate", "archive".
Use for planning work
Implements approved specification proposals by working through tasks sequentially with testing and validation. Use when implementing changes, applying proposals, executing spec tasks, or building from approved plans. Triggers include "openspec implement", "implement", "apply change", "execute spec", "work through tasks", "build feature", "start implementation".
Review code for quality, security, and pattern compliance, then auto-fix Critical/High issues. Grounds every finding in actual codebase reference files.
Write the daily memory log entry. Use at end of day to record what happened.
Generates detailed, architect-quality GitHub issues from short instructions. Analyzes the project's actual stack, architecture, and codebase before writing. Detects duplicate issues with intelligent multi-strategy search, validates and creates labels, enforces title conventions, controls scope, and publishes via `gh` CLI with robust error handling. Use this skill whenever the user wants to create a GitHub issue, report a bug, propose a feature, request a refactor, or file any kind of technical issue — even if they just say something brief like "we need to fix the auth flow" or "create an issue for X". Also triggers on: "open an issue", "file a bug", "I want to propose...", "add this to the backlog", "gh issue", or any request that implies creating a trackable work item on GitHub.