Showing 7531–7560 of 10207 skills
Diagnose and safely repair Codex "Reconnecting... 1/5" through "5/5" loops in the CLI, desktop app, or IDE on macOS, Linux, and Windows. Use when a Codex turn stalls on repeated stream reconnects or only succeeds after HTTPS fallback; do not use for generic login, quota, model, or rate-limit errors.
kenlinjie/codex-reconnect-repair
Supreme policy layer governing all agent behavior. Autonomy, one-line prompt interpretation, speed standards, emphasis signal processing, cross-skill coordination, done definitions, conflict resolution. Loaded every prompt.
heymegabyte/agent-skills
Transform vague prompts into precise, verifiable structured XML prompts that coding agents execute reliably. Modes: execute (default — generate then run) and plan (generate XML for review first). Use when the user says improve prompt, make this work better, prompt engineer, structure a request, plan a complex change before coding, or when a rough request needs verification criteria before execution. Do not use when the input is already a well-structured XML prompt or detailed implementation spec — skip generation and execute directly.
owenob1/prompt-improver
Benchmark skill whose description stays under the spec's 1024-character limit when counted in characters but runs past it when counted in UTF-8 bytes. Use when asked to probe description length units. The head marker GANNET-PYRITE-1130 sits near the start of this description and a tail marker sits at the very end. このスキルの説明文は、仕様が定める1024文字の上限を文字数では下回りますが、UTF-8のバイト数では上回ります。日本語の文字は一文字あたり三バイトを占めるため、文字数とバイト数の差が大きく開きます。プラットフォームがこの説明文をそのまま受け入れれば、長さを文字数で数えているか、あるいは長さを検証していないかのどちらかです。逆にこのスキルを拒否したり、説明文の末尾を切り捨てたりするなら、長さをバイト数で数えている可能性が高いと言えます。この段落は意図的に日本語で書かれた詰め物であり、スキルの機能を追加するものではありません。検証の対象は説明文の長さの数え方だけであり、それ以外の点ではこのスキルは通常の有効なスキルです。説明文の冒頭と末尾には英語の目印が置かれているため、末尾の目印が見えるかどうかで切り捨ての有無を判断できます。英語以外の言語で書いた説明文が、あるプラットフォームでは受け入れられ、別のプラットフォームでは静かに拒否されるかもしれないという点が、スキルの作者にとって重要です。この違いはエラーとして表面化しないため、数え方の違いを実際に観測して記録する必要があります。 The tail marker is SHRIKE-TALC-2210
agent-ecosystem/agent-skill-implementation
Run or resume an autonomous build/fix loop that iterates plan → implement → evaluate against a user-approved, testable contract until it passes. Use when the user wants an agent loop, wants a task to keep iterating unattended or in the background (e.g. overnight), or wants to resume, check the status of, or cancel a run.
tundergod/tundergod-loop
Use when a user has a rough prompt that needs a staged prompt-improvement workflow for `$ralph-wiggum-codex`, with saved draft/final files and explicit review checkpoints.
theflixerbox77/ralph-wiggum-codex
cisco-ai-defense/skill-scanner
cisco-ai-defense/skill-scanner
Install DevIntern Code, set up a self-hosted worker, or connect source control and task tracker accounts, including when the user wants a coding agent to work tracker tickets unattended, work through a backlog or recurring chores, serve many repositories or a team from one worker (a self-hosted software factory), or keep code and keys on their own machines. Use for first-time setup, credentials, GitHub App or relay authorization, browser-assisted integration setup, and worker readiness checks; ongoing workspace policies and recurring schedules belong to devintern-workspace, and task dispatch and DevIntern PM setup are separate workflows.
getdevintern/devintern
Use when 查 Orca/Claude Code 是否还在干活. Process+files first.
Adonis0123/adonis-skills
微信小程序(PC 端) WMPF 自动化调试与安全评估工具链的搭建、使用与 AI 自动化渗透。覆盖「偏移自动提取 → Frida 注入 → CDP 代理 → DevTools 调试 → e0e1-wx 自动化扫描 → MCP 工具链 → AI 渗透」,集成 WMPFDebugger + e0e1-wx + wmpf-offset-adaptation + miniapp-cdp-mcp。当任务涉及"对已授权微信小程序做自动化测试/强开 F12/CDP 调试/反编译抓接口/微信版本更新后取偏移/用 MCP 让 AI 做自动化渗透(抓接口、扫密钥、断点逆向加密)"时使用。关键约束:必须是 Node 20 LTS + frida 锁 @16.6.6,否则 NODE_MODULE_VERSION/ESM 不兼容;MCP 侧必须 pin mcp<2(FastMCP 兼容)。
xegeng/wx-miniapp-skills
Write runnable MiniMax H3 keyframe-film prompts — multi-keyframe montages, first-last frame transitions (FL2VA), final-frame landings (L2VA), and I2VA first-frame animation. Use when the user has reference images (keyframes, character art, product shots, final poses) and wants the image identity locked while text drives the motion. Follows base-en.txt exactly, including the keyframe-alignment instruction lines. Pure-text requests are redirected to h3-promo-film; reference-video motion goes to reference-motion-transfer.
gordonlu/awesome-minimax-h3-skills
Write runnable MiniMax H3 promo & trailer prompts with no reference assets at all — food promos, product campaigns, brand teasers, cinematic trailers. Use when the user wants a publicity or marketing short generated purely from text. Produces timecoded beats per base-en.txt; requests with reference images or videos are redirected. Produces integrated_multimodal_description with timecoded beats, overall_soundscape, and non_diegetic_music following the official base-en.txt guide. Requests that bring reference images or videos are redirected to the image-to-video or motion-transfer skills.
gordonlu/awesome-minimax-h3-skills
Transfer the motion from a user-supplied reference video onto a new target subject with MiniMax H3. Use when the user wants a character, mascot, product, or creature to perform the dance, gesture, action, locomotion, or camera move they saw in another video. Covers Ref2VA motion transfer (primary route), plus I2VA / FL2VA / L2VA fallbacks when no usable reference video exists. Pure-text requests have nothing to transfer from and are redirected to the base `h3-prompt-writing` skill. Not for style-only transfer with no motion, direct editing of the source video, real-person impersonation without consent, or sequences longer than 15 seconds without segmentation.
gordonlu/awesome-minimax-h3-skills
Give sparse, evidence-based progress updates for long-running agent tasks and projects. Use when work will take more than 15 minutes, spans multiple milestones, involves delegated agents, or when the user asks for progress bars, status cadence, fewer updates, or a global cross-agent progress rule. Not for short answers or tasks with no meaningful intermediate state.
tjcages/skills
在 DSH 会话中加载 ascend-sleuth 面板,并处理「装了但 tab 不出现」。先按本机给模型的工具与桌面版 自带的东西选装载路:有 cordis_define / cordis_run 在会话内热加载;有 plugin_manager 就装常驻插件 包;DSH Desktop 用安装目录自带的 dsh 命令行把 dsh-plugins/dsh-sleuth-panels/ 装进 profile(拿不到 地址与 token 时这是主路);另有 scripts/panel_install.js --all 经 /api 通路一次装面板、vllm-kb、 诊断状态条与诊断画布四个包、以及在侧栏「插件」页粘贴路径两条备用路。面板包的界面分三块:会话里一个 「诊断」tab、左侧栏一个「Ascend Sleuth」整页(「知识库」「指标」「自演进」)、侧栏页脚一个「诊断记录」入口 (列出诊断会话,可按时间或按价值排序,点一行切过去);另有独立的状态条包,一块:输入框上方的 诊断状态条(可单独装卸);另有独立的诊断画布包,左侧栏一个「诊断画布」图标、主区一整页,离线渲染 `traces/`(可单独装卸)。热加载路径没有整页容器、页脚入口、状态条与画布,仍是三个 tab(诊断 / 指标 / 自演进)。 日常同步代码后不用调用本 skill(随仓库装的重启 DSH 生效,插件页装的重装后再重启);只在首次装载或「装了但 tab 不出现」时用。 仅 DSH 可用 ——依赖 conversation.view / main / sidebar.panellist / sidebar.footer.action / shell.overlay / conversation.input.dock / conversation.input.right 插槽; 其他 agent(Claude Code / Codex / pi)无此机制。
pillumina/ascend-sleuth
Ninja build system skill. Use when diagnosing Ninja build failures, understanding Ninja's role as a low-level build executor generated by CMake or other meta-build systems, tuning parallelism, interpreting Ninja output, or working with build.ninja files. Activates on queries about ninja errors, ninja parallelism, ninja verbose output, build.ninja format, or ninja as a CMake generator.
protagonist-fy/low-level-dev-skills
C++20 modules skill for modern C++ projects. Use when working with named modules, module partitions, header units, CMake MODULE_SOURCES, Clang -fmodules-ts, BMI caching issues, or migrating from headers to modules. Activates on queries about C++20 modules, import statements, module interface units, header units, or BMI files.
protagonist-fy/low-level-dev-skills
LLDB debugger skill for C/C++/Swift/Objective-C programs. Use when debugging with LLDB on macOS, FreeBSD, or Linux-clang environments, mapping GDB mental models to LLDB commands, using LLDB in Xcode or VS Code, or debugging Swift/Objective-C. Activates on queries about LLDB commands, GDB to LLDB migration, Apple platform debugging, LLDB Python scripting, or IDE-integrated debugging with clang-built binaries.
protagonist-fy/low-level-dev-skills
FreeRTOS skill for embedded RTOS development. Use when creating tasks, managing priorities, using queues and mutexes, detecting stack overflows, configuring FreeRTOS via FreeRTOSConfig.h, or debugging FreeRTOS applications with OpenOCD and GDB. Activates on queries about FreeRTOS tasks, queues, semaphores, mutexes, configASSERT, stack overflow, vTaskDelay, or FreeRTOS-aware debugging.
protagonist-fy/low-level-dev-skills
AArch64 and ARM assembly skill for reading and writing ARM assembly code. Use when reading GCC/Clang output for AArch64 or ARM Thumb targets, writing inline asm in C/C++, understanding the ARM ABI (AAPCS64/AAPCS), or debugging register and stack state on ARM hardware or QEMU. Activates on queries about AArch64 assembly, ARM Thumb, NEON/SVE SIMD, ARM calling convention, inline asm for ARM, or reading ARM disassembly.
protagonist-fy/low-level-dev-skills
C++20 coroutines skill for understanding coroutine mechanics and debugging. Use when working with co_await, co_yield, co_return, implementing promise_type, understanding coroutine frame layout, debugging suspended coroutines in GDB, or inspecting frame allocation with Compiler Explorer. Activates on queries about C++20 coroutines, co_await, co_yield, promise_type, coroutine_handle, coroutine suspension, or coroutine frame.
protagonist-fy/low-level-dev-skills
Linux kernel module skill for writing and debugging loadable kernel modules. Use when writing LKMs with Kbuild, adding module parameters, creating /proc and sysfs entries, implementing character devices, debugging with KGDB or ftrace, or handling module signing for Secure Boot. Activates on queries about Linux kernel modules, loadable modules, Kbuild, module parameters, /proc filesystem, sysfs, character devices, KGDB, or module signing.
protagonist-fy/low-level-dev-skills
eBPF skill for Linux observability and networking. Use when writing eBPF programs with libbpf or bpftrace, attaching kprobes/tracepoints/XDP hooks, debugging verifier errors, working with eBPF maps, or achieving CO-RE portability across kernel versions. Activates on queries about eBPF, bpftool, bpftrace, XDP programs, libbpf, verifier errors, eBPF maps, or kernel tracing with BPF.
protagonist-fy/low-level-dev-skills
Compiler sanitizer skill for runtime bug detection in C/C++. Use when enabling and interpreting AddressSanitizer (ASan), UndefinedBehaviorSanitizer (UBSan), ThreadSanitizer (TSan), MemorySanitizer (MSan), or LeakSanitizer (LSan) with GCC or Clang. Activates on queries about sanitizer flags, sanitizer reports, ASAN_OPTIONS, memory errors, data races, undefined behaviour, uninitialised reads, or choosing which sanitizer to use for a given bug class.
protagonist-fy/low-level-dev-skills
Rust no_std skill for embedded and bare-metal development. Use when writing
protagonist-fy/low-level-dev-skills
已弃用,已迁移到 https://github.com/simonwong/writing-skills。从公众号文章提取封面关键词与短句,按主题或自由搭配配色,使用 `image_gen` 生成统一 shader 风格的封面。适用于公众号封面、封面文案提炼和封面提示词请求。
simonwong/skills
Handover prêt à copier-coller pour passer la main d'une conversation LLM à un autre LLM ou agent (Codex, Cursor, ChatGPT, Gemini, session Claude fraîche) : état + intention + décisions + prochaine action, vérifié par un agent frais qui ne voit que le handover. Deux modes : repo (le destinataire a le clone) et standalone (chat sans accès fichiers). Use when: « prépare un handover / handoff », « je passe sur X », fin de session à continuer ailleurs, ou /llm-handover. Uniquement sur demande explicite.
Aximande/agent-skills
Une page de critères d'acceptation avant de vibecoder — spec-kit compressé à la seule étape « specify », moteur grilling. Chaque critère est observable et formulé pour que proof-run l'exécute tel quel ; la spec est vérifiée par un agent frais qui ne voit qu'elle, puis vit dans le repo (table d'état remplie au proof-run, relue par ship-check). Use when: « fais une spec », « qu'est-ce qu'on construit exactement ? », avant de démarrer un projet ou une feature vibecodée, ou /spec-lite. Uniquement sur demande explicite.
Aximande/agent-skills
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
noteflowai/dsh-skills-anywhere