Productivity

xuiltul Skill

Zoom 회의 청취 담당 워크플로. RTMS를 통해 도착하는 회의 트랜스크립트를 조용히 이해·기록하고, 긴급 사항만 상사에게 에스컬레이션하며, 회의 종료 후 사람의 승인을 받은 뒤 리포트를 게시한다. Use when: source=zoom 인 inbox 메시지(「[Zoom会議実況 チャンク#N …]」 또는 「[Zoom会議終了 …]」 헤더 포함)를 수신했을 때.

leeyudok Skill

Use when the user invokes /grill-me or asks to have an idea, feature request, or spec grilled, stress-tested, interrogated, or challenged before implementation. Opt-in alternative to superpowers:brainstorming — the user picks one or the other per task.

shinianay Bundle

把口语化、零散、重复的会议记录/聊天记录/会议笔记整理成结构化的会议纪要，输出「会议摘要 + 关键结论 + 行动清单 + 风险与待确认事项」四部分。当用户提供会议记录、聊天记录、录音转写稿、零散会议纪要或会议笔记，并要求整理、总结、提炼待办时使用；当用户说「整理会议纪要」「提取会议待办」「总结这次会议」「把这段记录整理一下」时也应使用。本技能严禁编造原始材料中不存在的信息，未知项一律标记为「待确认」。

brenordv Bundle

Write production-quality Rust code following industry best practices and idiomatic patterns. Use for any Rust coding task including applications, libraries, refactoring, debugging, or code review.

gloomyweather Bundle

REQUIRED for CachyOS-specific system administration: kernels, optimized repos, schedulers, hardware profiles, boot and snapshots, packaged desktop defaults, handheld systems, and CachyOS packaging. Use for linux-cachyos*, Kernel Manager, ISA repos, scx_loader, chwd, Limine, snapper, cachy-chroot, Noctalia/UWSM, deckify, or CachyOS-PKGBUILDS. Do not use for ordinary application work or a vanilla Arch system unless the task is adding or managing CachyOS repositories.

brenordv Bundle

Write production-quality Python code following PEP 8, type safety, and comprehensive testing standards. Use for any Python coding task including new features, refactoring, debugging, or building complete applications.

brenordv Skill

Linux system troubleshooting workflow for diagnosing and resolving system issues, performance problems, and service failures.

stbenjam Bundle

Guides the {{SKILL_ID}} workflow. Use when the user needs {{SKILL_ID}} task support; customize this description with concrete triggers and outcomes.

stbenjam Skill

Review declared permissions. Use when checking a local workflow.

jebauza Skill

Closes a spec implemented with /worktree-spec-impl. Run from the primary checkout, on the spec's base branch (develop, a task branch, main…). Verifies the branch already contains its base and is clean, fast-forwards the base to it, runs the checks, and cleans up the worktree, its database and its port. Integrates one branch at a time. Never pushes.

jebauza Bundle

Implements an approved spec in an isolated git worktree so several agents can work in parallel. Validates that the state means "Approved" (in any language), creates .trees/spec-NN-slug from the current branch (develop, a task branch, main… or --base), bootstraps it (ignored files, node_modules, own port and database), implements step by step with pauses to review diffs, and finally merges the base branch into the spec's branch resolving conflicts so it is ready for /worktree-merge.

stbenjam Skill

Turn raw meeting notes into a structured summary with owners and due dates. Use when documenting a meeting.

awinogradov Bundle

Perform deep analysis of the codebase, recent changes, and the requested task. Create a validated implementation plan

awinogradov Bundle

Map this repository broadly, write a durable context brief to .claude/context/brief.md, then take surgical fixes one at a time with no plan, branch, or PR machinery. Use when you have an area rather than a task — "help me understand this repo", "explore the refactoring flow" — and want the codebase understood before deciding what to change.

awinogradov Skill

Scan codebase for TODO/FIXME comments, verify actuality, create GitHub issues, and update links

hugobatista Bundle

Use when creating or modifying Renovate configuration for automated dependency management. Covers renovate.json config, GitHub Actions workflow, and Forgejo Actions workflow templates for supply-chain hardened dependency updates.

awinogradov Bundle

Resolve task intent, reuse validated evidence, and acquire missing planning context and emit a Context Map. Use when plan or run needs issue, standards, branch, and codebase context without loading raw documents into the parent conversation.

tettethu Skill

Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.

tettethu Skill

Run VibeGame's standard end-to-end game development workflow with reviewer gates. Use when the user wants to create a game from zero or evolve an existing game across multiple stages.

ghbalf Skill

Create new FreeCAD AI skills, modify existing skills, and iteratively improve them. Use when users want to create a skill from scratch, update or optimize an existing skill, capture a workflow as a reusable skill, or improve an existing skill's instructions. Also trigger when the user says "turn this into a skill", "make a skill for X", "save this as a command", or similar.

nli33 Skill

Use when asked to check, flag, or discuss whether text reads as AI-generated or human-written — analyzing an essay, email, post, or document for AI writing tells. Reference only; does not instruct rewriting or "humanizing" text.

dprakash2101 Skill

Classify a software request just enough to select a safe, proportionate workflow. Use at the start of implementation, investigation, review, testing, or Git work when the needed workflow is not already obvious.

dprakash2101 Skill

Perform safe Git branch, stage, commit, and push operations for engineering work. Use only when the user requests Git operations or they are an explicit required step; never infer permission to commit or push.

dprakash2101 Skill

Reorient work when the user interrupts, replaces the objective, or redirects an in-progress coding task. Use only when the newest instruction makes prior intent or plans obsolete.

dprakash2101 Skill

Design, implement, or review Entity Framework Core queries, writes, migrations, and DbContext usage. Use only when a .NET task changes EF Core persistence behavior or investigates database performance/correctness.

khe618 Bundle

Use when the user asks for work to be driven to completion against acceptance criteria and graded by Jev, or says "jev", "jev goal", "jev this", "grade it with jev", "goal mode", or "keep going until it passes". Also use when asked to self-grade a finished task instead of dispatching a reviewing subagent.

xiangxn Skill

Apply modern idiomatic Go best practices whenever writing, modifying, reviewing, or refactoring Go code. Prefer Go standard library conventions and official Go guidance. Avoid unnecessary abstractions, dependencies, complexity, and speculative optimization. This skill provides language and engineering guidance only; it does not prescribe project architecture, dependency choices, lint configurations, or workflow tooling.

agentic-lineage Skill

Collect the target role and source material needed before reviewing a resume.

danthamanvoiss Skill

Generate a 30-day content plan from provided business context and goals.

danthamanvoiss Skill

Help users and harnesses choose the smallest useful combination of router and direct skills for a task.

danthamanvoiss Skill

Route video planning work to the right script, storyboard, edit-plan, or video-calendar skill with concise production-stage clarification.

danthamanvoiss Skill

Draft post-meeting recap, commitments, and next-step follow-up messages with explicit unknowns.

danthamanvoiss Skill

Explain the quickest reliable way to use the router hierarchy for a new task or new harness installation.

danthamanvoiss Skill

Plan recurring video publishing schedule with themes, formats, dependencies, and review cadence.

danthamanvoiss Skill

Plan social content operations rhythm, approvals, repurposing logic, and KPI tracking workflow.

danthamanvoiss Skill

Sanity-check whether the selected router path and skill stack are the clearest minimal fit for the task.