Productivity

alibaba-skill-up Bundle

帮助用户管理待办事项，支持添加、删除、标记完成、列出任务等操作。

qodo-ai Bundle

Understand how code works, how a change was done before, and which repos are coupled — to answer a question, plan a code change, debug a regression, or scope a fix, using the qodo CLI's managed tools. Use when a task needs to understand a codebase, its history, or how its repos relate — especially for a repo you don't have checked out or work spanning repos — "how does X work", "where is X defined", "who changed X", "explain this service", "plan the change for X", "what would changing X affect", "which repos depend on X", "why did X regress / when did it break", "has this been fixed before", "how did we solve X".

qodo-ai Bundle

Load the coding rules from Qodo most relevant to the current coding task, using the qodo CLI's managed rules search — generate structured semantic queries from the assignment, retrieve the workspace's matching rules ranked by relevance, and apply them while writing the code. Use when the user asks to write, edit, refactor, or review code, when starting implementation planning, or on "get rules", "load qodo rules", "fetch coding rules", "relevant rules", "search rules"; skip if rules are already loaded in this conversation.

qodo-ai Bundle

Understand how code works, how a change was done before, and which repos are coupled — to answer a question, plan a code change, debug a regression, or scope a fix, using the qodo CLI's managed tools. Use when a task needs to understand a codebase, its history, or how its repos relate — especially for a repo you don't have checked out or work spanning repos — "how does X work", "where is X defined", "who changed X", "explain this service", "plan the change for X", "what would changing X affect", "which repos depend on X", "why did X regress / when did it break", "has this been fixed before", "how did we solve X".

qodo-ai Bundle

Load the coding rules from Qodo most relevant to the current coding task, using the qodo CLI's managed rules search — generate structured semantic queries from the assignment, retrieve the workspace's matching rules ranked by relevance, and apply them while writing the code. Use when the user asks to write, edit, refactor, or review code, when starting implementation planning, or on "get rules", "load qodo rules", "fetch coding rules", "relevant rules", "search rules"; skip if rules are already loaded in this conversation.

randommonicle Skill

Gets faster, more accurate answers by keeping each conversation to one matter and sending the material that bears on it without the material that does not. Use when someone is about to attach a mailbox or file export, a whole drive or client folder, or many documents at once; when a conversation has run long, drifted across unrelated matters, or started repeating itself, losing detail or contradicting something said earlier; when someone has reached or is approaching a usage limit, or asks how to make their allowance last; and when choosing which folder to point a Cowork task at. Covers what to attach and what to leave out, why completeness beats economy on a lease or a set of accounts, and when to start a fresh conversation instead of continuing.

tuanloc1105 Bundle

Claude-Code-inspired code review workflow for diffs, pull requests, branches, commits, or working-tree changes. Use for minimal, low, low-minimum/low-expanded, medium, high, extra-high/xhigh, or max/maximum-effort reviews; precision- or recall-biased bug finding; language/framework pitfalls; wrapper, proxy, decorator, or adapter correctness; three-state verification; raw JSON or typed ReportFindings output; GitHub inline comments; opt-in review artifacts; applying verified fixes with --fix; or explaining Claude-only ultra/ultrareview behavior.

tuanloc1105 Bundle

Coordinate execution of an approved version 4 $plan bundle or execution-ready $discuss tracker by launching a separate lower-cost Codex CLI session, then reconcile its work, run $simplify in the current session, and complete verification. Use when the user explicitly requests $handoff-execute or asks to hand off an accepted execution record to another Codex CLI session. Never use subagents for this workflow.

tuanloc1105 Bundle

Create or edit a technical workflow/flowchart from session context, natural-language processes, code paths, or Mermaid flowchart source. This is the permanent flowchart-only compatibility alias for technical-diagrams; do not use it for sequence, state, data-flow, or other diagram families.

tuanloc1105 Bundle

Launch an independent Codex CLI session to review findings in one exact workflow-record version 4 bundle produced by kiro-discuss, kiro-plan, or kiro-execute. Codex writes a durable review tracker into the bundle under a bounded ownership transfer; Kiro then validates and adjudicates it. Use when the user asks Kiro to obtain and track a Codex second opinion. Do not use for implementation handoff or ordinary Kiro subagent review.

tuanloc1105 Bundle

Incremental teaching and comprehension verification workflow for Codex sessions. Use when the user asks Codex to act as a wise/effective teacher, make sure they deeply understand a session, explain code or changes step by step, maintain a learning checklist, quiz the user, require restatement before moving on, or keep a goal active until the user demonstrates mastery of the problem, solution, edge cases, design decisions, and broader impact.

nwave-ai Skill

Routes an observed defect request into the DES steps that deliver the fix.

shoootyou Skill

Structured spec-driven workflow for planning and executing software projects with Codex CLI.

shoootyou Skill

Structured spec-driven workflow for planning and executing software projects with GitHub Copilot CLI.

cklxx Bundle

When a repeated workflow should be codified as a reusable skill → auto-create skill files, optionally using Codex/Claude.

idanbeck Bundle

Zmail Skill - Custom Email for Agents

pskoett-pskoett-ai-skills Bundle

Monitors context window health during large, long-running, multi-session, or explicitly context-sensitive work. Uses bounded external anchors, one cold-context review when self-recovery is uncertain, and a clean handoff on real drift. Do not auto-activate merely because a medium task has an intent frame and plan.

pskoett-pskoett-ai-skills Bundle

[Beta] Session-start scan that surfaces relevant learnings, recent errors, and eval status before work begins. Bridges the outer loop back into the inner loop by making accumulated knowledge visible at task start. Activated via SessionStart hook or manually before major tasks.

refly-ai Bundle

个性化冷邮件生成工具，根据潜在客户信息自动生成高度个性化的开发信，提升打开率和回复率

cacr92 Skill

当用户要求TDD、测试驱动开发、先写测试或提到红绿重构时使用。

buldee Skill

Safe git workflow with destructive command protection. Use when committing changes, creating branches, managing git workflow, or handling merge conflicts.

buldee Skill

Structured planning for multi-step tasks. Use when starting features requiring 3+ steps, migrating or refactoring large codebases, or when task complexity clearly exceeds a single change.

buldee Skill

Evidence-based verification before claiming completion. Use before committing, creating PRs, or claiming a task is done. Never claim success without proof.

ayoubben18 Skill

The intelligent entry point to the AB Method. Use when the user isn't sure which workflow they need, asks whether to create a goal or a task, or wants to understand how the AB Method works end to end. Routes intent to the right workflow instead of reimplementing it.

ayoubben18 Skill

Run an existing task autonomously to completion — each remaining mission in a subagent with tdd, tracker updated per mission, a commit after every green mission. Use when the user wants to hand off a well-defined task and review commits instead of missions.

ayoubben18 Skill

Create a focused task and break it into test-driven missions. Use when the user wants to start a new feature, fix a bug, or begin implementation work.

ayoubben18 Skill

Append new missions to an existing task. Use when requirements changed or scope grew on a task already underway.

ayoubben18 Skill

Continue an existing task from its progress tracker. Use when the user wants to resume, continue, or pick up earlier task work.

ayoubben18 Skill

Resume a handoff (a side-topic spun off mid-grill) and turn it into a test-driven task. Use when the user wants to continue grilling on a deferred topic captured under docs/handoffs/.

ishandutta2007 Bundle

Skill: ax Extract Workflow

affaan-m Bundle

Generate review drafts of counterparty master agreements from one template plus a JSON spec, with role-selected clauses and a Schedule A workflow limited to the executed agreement's notice authority. Use when you need reproducible drafting and separately reviewed execution preparation.

terrylica Bundle

Gmail Commander health check across all subsystems. TRIGGERS - gmail health, email bot status, gmail diagnostics, gmail bot check.

terrylica Bundle

Cal.com Commander health check across all subsystems. TRIGGERS - calcom health, calendar bot status, cal.com diagnostics, booking bot check.

terrylica Bundle

Initialize git-town in current repository with fork-aware configuration. One-time setup.

terrylica Bundle

Tether (install/uninstall) hooks that enforce git-town over raw git commands in Claude Code. Renamed from 'hooks' to avoid.

dhofheinz Bundle

Enforce git commit best practices and workflow guidance