最近新增

刚加入收藏的新技能,抢先试用。

显示 2353-2376 / 共 2400 个技能
griffinwork40

gather

griffinwork40

"Parallel context-gathering for a code area. Use when you need to understand a module, feature, or subsystem and would otherwise read 3+ files sequentially — dispatches two agents in parallel to map structure and test coverage in one wave."

智能体 61 4个月前
griffinwork40

fix-pr

griffinwork40

"One-verb pipeline for the operator's highest-frequency manual loop: fetch a PR's unresolved reviewer feedback (inline review comments, review-summary bodies, and issue-level conversation comments) and failing CI checks, triage each issue via parallel read-only probes, fix the validated items in an isolated managed worktree via a budget-bounded subagent, verify with the project's test gates, and push the fix back to the PR branch. Replaces the retyped recipe 'send a subagent in a worktree to fix <PR feedback>, then push.' Use when a PR has review comments or red CI that needs addressing — e.g. 'fix pr 286', 'address the review on #215', 'CI is red on the worktree-sweep PR'. Never force-pushes, never touches main, fails closed on missing gh auth or un-pushable fork PRs."

注释 61 7天前
griffinwork40

false-completion-gate

griffinwork40

"Fires when a state-mutating task is about to be declared Done (success summary or completion verdict) — to catch silent success, the highest-frequency invisible agent failure where confident 'done' language hides work that never landed. Decomposes the completion into receipt-checkable assertions, then dispatches a reconciliation auditor that cross-references each claim against the session's tool-call LEDGER (did the producing action fire?) and a fresh postcondition READ-BACK of the named artifact (does the file/test/commit exist and match?), gating the Done behind a BACKED/UNBACKED/UNVERIFIABLE verdict plus a bounded repair loop. Distinct from shadow-verify, which RE-DERIVES an investigation finding's correctness — this reconciles a COMPLETION against execution receipts, never re-deriving the claim. Use before any Done/success in implementation, fix, refactor, migration, or multi-file write work. Skip text-terminal sessions (explanation, Q&A) and work that already failed loudly."

CLI 工具 61 2个月前
griffinwork40

diagnose

griffinwork40

"Parallel root-cause analysis for bugs and failing tests. Use when a test fails, a bug is reported, or behavior is unexplained — dispatches sub-agents to form and validate hypotheses in isolated worktrees."

调试 61 28天前
griffinwork40

devils-advocate

griffinwork40

"Adversarially critique a proposal by generating alternatives. Dispatches 3 parallel critics (pragmatist, paranoid, architect lenses) — each invents one alternative approach — then a synthesis step ranks all 4 options and recommends the top choice. When the proposal was authored by someone other than the agent (inherited plan, someone else's PR, external review), a 4th steelman critic runs in the same parallel wave and strengthens the original first, so it is judged at its strongest rather than its weakest. Use when a plan, fix, scoping, decomposition, or named recommendation will drive decisions and you want structured alternative-generation before committing. Complements /shadow-verify — that skill re-derives factual claims; this one critiques whether the chosen approach itself is best."

代码评审 61 2个月前
griffinwork40

contract

griffinwork40

"Reference convention for sub-agent I/O schemas. Loaded by orchestrator skills via /contract and into agents via the skills: field."

设计 61 3个月前
griffinwork40

automate

griffinwork40

"Set up a scheduled headless afk run that pushes a summary to Telegram. Use when the user wants to automate a recurring task via the afk daemon scheduler (cron) with push-notified results."

自动化 61 17天前
corbitsdev

corbits-code

corbitsdev

A coding agent TUI that gets out of your way. Flexible agent loops, smart compaction, fully open source.

MLOps 2 24天前
corbitsdev

scribe

corbitsdev

Fixture skill for unit tests — documentation workflow instructions.

测试 2 24天前
weside-ai

claude-rules

weside-ai

Load the .claude/rules guidance that applies to the files you are about to touch; use before planning, editing, reviewing, testing or deploying in this repo.

智能体 0 1个月前
ToanMobile

verify-app

ToanMobile

Run affected app feature checks, inspect evidence, or maintain this project's verifier when source or accepted behavior changes.

代码生成 2 8天前
ToanMobile

writing-skills

ToanMobile

Dùng khi tạo, sửa hoặc audit skill trong thư mục skills/ của dự án. Bỏ qua khi chỉ sử dụng skill hoặc sửa typo không đổi contract.

CLI 工具 2 1个月前
ToanMobile

worktree-sandbox

ToanMobile

"Quản lý môi trường thử nghiệm song song (Parallel Worktree Sandboxes) trên macOS APFS: nhân bản CoW siêu tốc (<100ms, 0-byte đĩa), nạp .worktreeinclude, cách ly dependencies, so sánh diff trọng tài và tự động dọn dẹp sạch sẽ (auto-clear) ngay khi merge vào main để chống rác Git. Kích hoạt khi cần chạy A/B testing giữa các agent, thử nghiệm nhiều giải pháp song song, hoặc gõ /sandbox."

智能体 2 24天前
ToanMobile

video2dsprite

ToanMobile

Turn one approved master still into a character's whole animated sprite set - one image-to-video clip per action (idle, walk, run, attack, jump, hurt, cast and so on), all from that still, generated through generate2dmedia route_media.py (the xAI API when a key is configured, else the local Grok CLI) - then gate each take, key it with a soft matte, register it to the master, pick loops or retime actions, finish (HD by default, pixel on request) and package fixed-canvas frames, alpha WebM, packed MP4 for iPhone and a PNG fallback with engine metadata and a JS runtime. Also processes a supplied clip. Use for character and creature animation, fluid motion and any video-to-sprite work. Not for FX, icon or prop sheets (generate2dsprite), maps or plate loops (generate2dmap), code-drawn animation (codeart2d, only on request) or calling a video API by itself (generate2dmedia).

设计 2 11天前
ToanMobile

verification-before-completion

ToanMobile

Dùng khi sắp tuyên bố xong/fixed/PASS/green, trước commit/PR được User yêu cầu, hoặc khi kiểm kết quả từ agent khác. Bỏ qua khi chỉ khám phá/đọc và chưa đưa completion claim.

CLI 工具 2 8天前
ToanMobile

unity-gc-audit

ToanMobile

Kiểm toán và triệt tiêu cấp phát bộ nhớ rác (Garbage Collection - GC Allocation) trong Unity 6, hướng tới Zero-GC per frame trong Update loop. Tự động kích hoạt khi chỉnh sửa C# scripts, game loop, physics update, LINQ trong game, hoặc khi phát hiện game bị khựng (GC Spike Freeze / Hitching).

游戏开发 2 12天前
ToanMobile

ui-ux-pro-max

ToanMobile

"Design Intelligence & UI/UX Engine cho Mobile (SwiftUI, Flutter, Jetpack Compose, React Native) và Game (Unity 6 uGUI, Casual Puzzle, Arcade). Dùng khi thiết kế giao diện mới, chọn bảng màu, font chữ, styling button, juice/micro-interactions, haptic feedback, hoặc audit thẩm mỹ giao diện giúp UI không bị phèn/template mặc định."

设计 2 21天前
ToanMobile

tdd-workflow

ToanMobile

Dùng khi thêm/sửa logic testable, viết regression test hoặc audit test quality cho Target Project / Codebase bằng RED→GREEN an toàn. Bỏ qua config/rendering thuần cần verification khác; không xóa hay revert user work để tạo RED.

调试 2 8天前
ToanMobile

taste-mobile-app

ToanMobile

Dùng khi thiết kế hoặc dựng màn hình/luồng mobile mới (Jetpack Compose, SwiftUI, Flutter, React Native) hay làm lại giao diện mobile trông rập khuôn. Bỏ qua khi chỉ sửa logic không đổi UI, game Unity (dùng ui-ux-pro-max) hoặc web.

设计 2 15天前
ToanMobile

spec-driven-development

ToanMobile

Dùng khi feature/refactor/risky flow cần spec trước code, yêu cầu mơ hồ, hoặc thay đổi chạm từ 2 module, 3 file hay hơn 200 LOC net diff. Bỏ qua typo, config không đổi behavior và bug local đã rõ root cause.

调试 2 1个月前
ToanMobile

session-handoff

ToanMobile

Dùng khi User gọi /session-handoff để chuyển công việc đang dở sang session/người khác hoặc sắp hết context. Bỏ qua fact cần lưu lâu dài; dùng .agents/instincts.md cho nội dung persistent.

认证鉴权 2 1个月前
ToanMobile

security-checklist

ToanMobile

Dùng khi đổi external Intent/URI/file handling, exported component, permission, WebView, auth/cloud, network security, telemetry privacy hoặc trước release/security review. Bỏ qua UI thuần và rename không đổi behavior.

文件操作 2 1个月前
ToanMobile

qc

ToanMobile

"Chạy lint, unit test và QA gate cho dự án. Phát hiện build tool trước (Gradle, npm/pnpm/yarn, pytest, go, cargo, xcodebuild, dotnet); các mục ktlint/Metalava/Translation gate chỉ dành cho dự án Android/Gradle."

游戏开发 2 12天前
ToanMobile

qa-visual

ToanMobile

Chụp màn hình và audit layout cho project có qa.config.json. Dùng khi cần capture các route × viewport khai trong qa.config.json, tự đăng nhập bằng form login của app để chụp được màn sau login, dò lỗi bố cục đo trên DOM (tràn khung, lệch align, chồng lấp, chạm cạnh màn hình), suy design token từ CSS thực tế, upload ảnh lên Cloudflare R2 và đính vào PR. Kích hoạt khi người dùng nói "chụp màn", "screenshot các trang", "audit layout", "check giao diện", "UI có lệch không", "đính ảnh vào PR".

代码评审 2 1个月前