Productivity

majiayu000 Bundle

Use when filing an approved task spec as a GitHub issue with a local archive and optional worktree implementer. Don't use for spec drafting without human interrogation and redaction gates.

majiayu000 Bundle

Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.

majiayu000 Bundle

End-to-end PM workflow - from data analysis to pragmatic Linear tickets. Analyzes user behavior, identifies opportunities, creates specs, and audits for simplicity.

majiayu000 Bundle

View and manage the runtime changelog for observability

majiayu000 Bundle

Gather evidence and context before planning or as a standalone briefing. Supports code and business deliverables by classifying execution track and routing to progressive execution skills.

majiayu000 Bundle

Run a learning retrospective on the Kai harness. Mines gate-failure logs and 30-day performance results into lessons, triages candidate lessons (promote/keep/retire), and graduates repeated lessons into enforced gate checks with golden corpus cases. Use when "retro", "what have we learned", "triage lessons", "promote lessons", "why does this keep failing", "harness retrospective", or monthly / after any heavy content sprint.

majiayu000 Bundle

Creates a new album with the correct directory structure and templates. Use IMMEDIATELY when the user says 'make a new album' or similar, before any discussion.

majiayu000 Bundle

Use for self-correcting implementation. Implements the reflexion loop: implement, validate, self-critique, retry (max 3 iterations).

majiayu000 Bundle

This skill should be used when the user asks to "reply to email", "respond to email", "draft reply", "email reply", or wants to respond to a specific message. Drafts replies with safety confirmation that never auto-sends.

majiayu000 Bundle

Safe git workflow for Codex. Use when asked to stage/branch/revert/inspect changes, or mentions 差分/ブランチ or "git add/status/diff/switch/revert". For commit quality use git-smart-commit.

majiayu000 Bundle

Generate a specification template for non-trivial changes using Spec-Driven Development. Creates GitHub issue + spec file following the 4-stage workflow (Specify → Clarify → Tasks → Implement).

majiayu000 Bundle

Guide for creating new Claude Code skills. Use when you need to create a new skill to package expertise or workflow into a reusable capability that Claude can automatically invoke.

majiayu000 Bundle

ATS-focused CV tailoring workflow from job URL/text/image to bullet-point output and optional Google Drive upload.

majiayu000 Bundle

Git operations with intelligent commit messages and workflow optimization. Use when committing changes, managing branches, or optimizing git workflows.

majiayu000 Bundle

Create or update an AIDE skill in .aide/skills with valid frontmatter and a concise workflow.

majiayu000 Bundle

Ralph Wiggum-inspired automation loop for specification-driven development. Orchestrates task implementation, review, cleanup, and synchronization using a Python script. Use when: user runs /loop command, user asks to automate task implementation, user wants to iterate through spec tasks step-by-step, or user wants to run development workflow automation with context window management. One step per invocation. State machine: init → choose_task → implementation → review → fix → cleanup → sync → update_done. Supports --from-task and --to-task for task range filtering. State persisted in fix_plan.json.

majiayu000 Bundle

Background job processing and scheduled task patterns.

majiayu000 Bundle

Confidence-based code review that filters issues to 80+ threshold, eliminating false positives and noise. Reviews implementation against plan or requirements for bugs, quality issues, and project conventions. Use after completing major features, before merging to main, or after each task in multi-step workflows. Do NOT use for quick fixes, single-line changes, or when you need immediate feedback - the thorough review adds overhead best reserved for significant changes.

majiayu000 Bundle

Guide user through inbox processing, clarifying and organizing items one at a time using the clarify and organize workflow. Automatically invoked when user wants to process their inbox.

majiayu000 Bundle

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive guides with exact file paths, code examples, and verification steps; task granularity 2-5 minutes per step

majiayu000 Bundle

Systematically debug issues using Sherpa's Bug Hunt workflow. Activates when fixing bugs, investigating errors, debugging broken functionality, or handling regressions. Prevents symptom-fixing by enforcing reproduction-first approach.

majiayu000 Bundle

AI-Driven Specification-Driven Development (SDD) workflow orchestrator - guides skill selection and general SDD methodology

majiayu000 Bundle

Transform vague ideas into concrete, validated project concepts. Clarifies problem statements, identifies target users, ruthlessly scopes MVPs, challenges assumptions, and documents vision in PLANNING.md, TASK.md, and AI_MEMORY.md.

majiayu000 Bundle

Use during REFACTOR phase of TDD or when code duplication is suspected. Defines search-first workflow and safe refactoring practices.

majiayu000 Bundle

Manage Temporal workflows: server lifecycle, worker processes, workflow execution, monitoring, and troubleshooting for Python SDK with temporal server start-dev.

majiayu000 Bundle

Use this skill for ANY task involving jj or jujutsu version control. ALWAYS trigger when the user mentions jj, jujutsu, revsets, change IDs, bookmarks, or oplog. Also trigger when the user wants to squash, split, or reorder commits in a stack, write a revset query, absorb fixup changes, undo or restore a previous operation, resolve conflicts after rebasing, recover from force-pushes, rewrite protected/immutable commits, view change evolution (evolog), or try parallel approaches. Trigger even if "jj" is not explicitly said — "changes" instead of "commits", "stack" instead of "branch", "absorb", "squash into the right commit", "undo my last operation", "conflict after rebase", or "compare approaches in parallel" are strong jj signals. This skill contains critical non-obvious rules (like always using -m flags) that prevent broken workflows.

majiayu000 Bundle

Enforces development phases. Triggers on implement, build, create, fix, refactor.

majiayu000 Bundle

Bootstrap a task into a synced feature branch — one shot, zero confirmations. Detects the source from the args: GitHub issue ('#100', 'issue 100', 'gh issue 100', or bare '100'), Jira key ('PROJ-42'), or a local spec file path; ad-hoc conversation otherwise. Fetches the task, derives {type}/{number}/{slug}, syncs the default branch, creates and pushes the branch, and writes specs/context/<id>.md. Use only when the user explicitly asks to start a task or create a work branch — never trigger automatically.

majiayu000 Bundle

Write a multi-email nurture/onboarding/launch sequence with a goal per email. Use when asked to write an email sequence, a welcome/onboarding series, a nurture drip, a launch sequence, or a re-engagement series. Produces the sequence map (trigger, timing, goal per email) plus the full copy for each email — subject, body, and one CTA — designed to move the reader one step at a time.

majiayu000 Bundle

Pressure-tests a decision, plan, or idea before it is committed to — surfacing the assumption it rests on, the case against it, and what would have to be true for it to work. Use this when weighing options, when a plan needs challenging before commitment, when you have already decided and want a genuine gut check, when processing meeting notes into decisions, or when competing initiatives need ranking. Distinct from `chief-executive`, which owns direction; this one interrogates a specific decision.

majiayu000 Bundle

Work with video and audio links. Activate when user shares a YouTube link, video URL, or any media link - regardless of the task (download, info, convert, extract, list, or explore). Uses yt-dlp for all operations.

majiayu000 Bundle

Apply improvements to Claude Code skills systematically. Workflow for planning updates, implementing changes, validating improvements, and documenting changes. Use when applying review recommendations, updating skills based on feedback, enhancing existing skills, or implementing systematic improvements across multiple skills.

majiayu000 Bundle

Behaviour-Driven Development, Red-Green-Refactor cycle for test-driven development

majiayu000 Bundle

Test-driven development guidance for Tetris game logic. Use when writing tests, fixing test failures, improving test coverage, or implementing game mechanics. Auto-triggers on phrases like "write a test", "test this function", "improve coverage", "fix failing tests", or "add game logic". Emphasizes Result<T,E> pattern and property-based testing with fast-check.

majiayu000 Bundle

List pending todos and select one to work on

majiayu000 Bundle

Complete verification steps before ending the session