1.2K skills · sorted by relevance
Keep FastGPT build and test workflows aligned across GitHub Actions and Forgejo Actions. Adapt registry destinations, credentials, proxy settings, and platform-specific steps so the corresponding workflows support the internal network environment.
Operate FrontendIntegration resources from existing YAML definitions using kubectl, the Kubernetes command-line tool. Manage updates and enabled state, inspect build output, troubleshoot failures, and install or manage the frontend-forge extension.
Set up a modded Minecraft server from a server pack, including Java and Forge or NeoForge configuration. Adjust memory and viewing distances for the expected players, schedule world backups, and verify startup and connectivity.
Conditional discipline for projects hosted on a git forge (GitHub, GitLab, Forgejo, …): branch↔PR mapping, self-contained PR prose, review-on-forge, merge consent, and the forge audit. Trigger when: - Opening, updating, reviewing, or merging a pull/merge request. - A campaign's integration branch is ready to surface on a forge. - Auditing forge-side presence at merge-consent or campaign CLOSE. - Prompt contains: /forge, pull request, PR body, merge request, forge discipline, PR review, stacked PR.
The English summary is being prepared. Showing the original description.
Diagnoses and fixes issues in Atlassian Forge apps. Use this skill whenever a Forge app has errors, crashes, shows blank UI, fails to deploy, doesn't appear after installation, has permission issues, or produces unexpected output. Trigger on any mention of forge logs, forge deploy errors, resolver errors, blank panels, missing scopes, Custom UI not rendering, production vs dev discrepancies, or any Jira/Confluence app that "stopped working". Also trigger when the user asks to debug, troubleshoot, investigate, or fix a Forge app issue — even if they haven't used the word "Forge" but describe a Jira panel or Confluence macro acting up.
The English summary is being prepared. Showing the original description.
ForgeCAD model authoring, editing, debugging, and execution guidance for .forge.js, SVG-import, assembly, and CLI workflows. Use when building or modifying ForgeCAD geometry, structuring multi-file projects, validating scripts, or using ForgeCAD export/render tooling.
The English summary is being prepared. Showing the original description.
Optimizes Atlassian Forge apps to reduce platform consumption and avoid unnecessary costs using Atlassian's "Optimise Forge platform costs" guidance. Use when the user asks to optimize Forge app costs, reduce Forge invocations, lower GB-seconds, reduce storage or log usage, tune memory, replace polling, improve scheduled triggers, reduce KVS writes, move work to the frontend, use bridge APIs, batch API calls, add caching, or evaluate Forge Remote trade-offs. By default, perform an audit first and offer to make the recommended changes after presenting the audit. Only modify files immediately when the user explicitly asks the agent to implement or apply optimizations.
The English summary is being prepared. Showing the original description.
Performs a lightweight pre-release readiness review of Atlassian Forge apps across manifest/module wiring, architecture, runtime compatibility, dependency posture, tests, deploy readiness, and obvious security, cost, or reliability smells. Use when the user asks "review my Forge app", "pre-deploy check", "is this app ready to ship", "review manifest", "general app review", "release readiness", or asks for a broad quality pass. Do not use for deep security audits/SAST/exploitability review, cost optimization, or diagnosing a known broken app; route those to forge-security-review, forge-cost-optimizer, or forge-debugger respectively.
The English summary is being prepared. Showing the original description.
在真实 token、真实像素的 HTML 骨架上做页面与组件的设计决策：生成可点、可改、可存的设计工作台，按七层逐节点审查，保存即导出 token 与 CSS 并回写 DESIGN.md 的 token 表。用户说「开工作台」「看骨架」「讨论 XX 的设计稿」「改 token」「我保存好了，按调整后的来」时用；只要在争论比例、密度、一屏几张、行长、栏宽、留白这类要看见才能判断的问题，哪怕没提工作台也用；forge-design 第三步遇到页面、组件、布局决策时必调。不处理：DESIGN.md 散文与评分（forge-design）、产品代码（forge-eng、forge-design-impl）、效果图气质预判（Image 2）、实现后截图验收（forge-qa）。
The English summary is being prepared. Showing the original description.
在真实 token、真实像素的 HTML 骨架上做页面与组件的设计决策：生成可点、可改、可存的设计工作台，按七层逐节点审查，保存即导出 token 与 CSS 并回写 DESIGN.md 的 token 表。用户说「开工作台」「看骨架」「讨论 XX 的设计稿」「改 token」「我保存好了，按调整后的来」时用；只要在争论比例、密度、一屏几张、行长、栏宽、留白这类要看见才能判断的问题，哪怕没提工作台也用；forge-design 第三步遇到页面、组件、布局决策时必调。也负责全站唯一的设计零件库（一套模板 + 逐条确认的定制 + 守门检查）：说「零件库」「设计模板」「全站设计 token 总表」「这个算不算定制」「查一下有没有用模板外的值」时用。不处理：DESIGN.md 散文与评分（forge-design）、产品代码（forge-eng、forge-design-impl）、效果图气质预判（Image 2）、实现后截图验收（forge-qa）、设计概念问答（直接答）。
The English summary is being prepared. Showing the original description.
维护每个功能一份给人看的「需求设计文档」（docs/modules 下，一个功能一份）：待拍板置顶，按需写背景、目标、流程、布局、状态、交互细节、业务规则、召回、AI 生成（prompt）、效果、成本、系统，先图后字，只写当前设计，末尾记关键改动，附出图与上线前检查。新建、更新、同步、补充这份文档都用它，别直接手改——它有固定写法和检查。用户说「出设计文档」「PRD 太长看不懂」「把设计文档同步一下」「重拍截图」「上线前看文档跟上没有」时用；用户抱怨看不到功能现在的设计、不知道最近改了什么时也用；forge 各阶段改了规则、文案、交互、布局、阈值、prompt、模型、架构后收尾也用，哪怕用户没明说。不处理写给 AI 的 PRD/DESIGN（forge-prd、forge-design）、骨架上定布局（forge-design-lab）、改 prompt 本身（prompt-craft）、进度（forge-status）。
The English summary is being prepared. Showing the original description.
Investigate forged Kerberos authentication tickets in Active Directory by checking Windows logs for unusual encryption, excessive ticket lifetimes, and missing authentication requests. Produce a JSON report of suspicious indicators with risk ratings.
Set up model training with torchforge for reinforcement learning, where rewards guide improvement. Covers training configurations, custom reward and loss functions, and distributed execution with Monarch and TorchTitan, keeping algorithm experiments separate from infrastructure concerns.
Guides reinforcement learning, where models learn from rewards, using torchforge and PyTorch. Covers reward design, custom loss functions, and distributed training so researchers can experiment with algorithms while keeping infrastructure concerns separate.
Performs a white-box security review of Atlassian Forge apps using structured, Forge-specific security rules and evidence-driven reporting. Use when the user asks for a Forge security review, security audit, vuln assessment, pentest-style code review, authz review, tenant isolation analysis, web trigger hardening, or static analysis execution for a Forge app.
The English summary is being prepared. Showing the original description.
Guide a first-time Forge builder through deploying a stock Rovo Agent, then turning it into Forge Guru, a documentation companion. Use for Forge onboarding, a first Forge or Rovo app, or resuming this tutorial. Route unrelated existing-app changes, debugging, reviews, and connector work to the specialist skills.
The English summary is being prepared. Showing the original description.
并行会话巡检：扫 .forge/active.md，按硬信号（worktree 是否存在、分支是否已合并）判僵尸，一次确认批量清理并联动 backlog；不用时间戳启发式。 触发方式：用户说"forge 状态"、"看下谁在跑"、"清理 worktree"、"forge-status"；forge-bugfix 启动时只读巡检。
The English summary is being prepared. Showing the original description.
QA 纯验收（只测不修）：Mode A 完整验收（test-spec → 10 维度断言引擎 → 报告 + User Gate）；Mode B 供 forge-bugfix P6 调用做单 bug 回归并回填 BF 报告。 铁律：每个测试必须有 pass/fail 和深层断言；console.error 零容忍；不猜端口，只用传入的 app_url。 触发方式：Mode A 用户说"测试"、"QA"、"forge-qa"或 forge-dev 调度；Mode B 由 forge-bugfix P6 调用（传 review_doc）。
The English summary is being prepared. Showing the original description.
Guides users through removing a stored fact with Codewhale’s Context Lens memory controls. It identifies the intended fact, explains the forget action, and distinguishes confirmed deletion from an action that has not yet completed.
Build and operate AutoGPT agents that carry out multi-step workflows. Covers a visual editor for connecting processing blocks, scheduled and webhook triggers, deployment, execution monitoring, and benchmarks for evaluating agent performance.
Manage FrontendExtension resources in frontend-forge, from creation and package generation to downloading, publishing, and unpublishing. Inspect generated files, Kubernetes jobs, and status information to diagnose packaging or publishing failures.
Generate FrontendIntegration YAML for frontend-forge from a simplified configuration containing one menu and one or more pages. Define resource tables or embedded iframe pages, with the bundled generator expanding menu placements into the required YAML structure.
Move an existing mod to a newer game version or another mod loader while preserving its behavior and values. Organize source comparisons, scripted data extraction, tests, visual checks, and handoff documents for a long migration.
Manage git worktrees across any repository with the `gwm` Rust binary (CLI + ratatui TUI). Use when the user asks to create / list / remove / bootstrap / switch / link worktrees, run a command across worktrees (`gwm exec`) or reclaim build artifacts (`gwm clean`), materialise a PR into a worktree (`gwm review`), drive a multi-repo workspace (`--workspace`), run the JSON daemon / statusline (`gwm daemon`, `gwm statusline`), list or pin AI-agent sessions per worktree (`gwm agents`, Claude Code / Codex / opencode / Mistral Vibe detection), seed config from a preset (`gwm init --preset`), diagnose with `gwm doctor`, drive tmux/zellij, or wire `gcd` via `gwm shell-init`. Also covers multi-forge (#419): GitHub via `gh` **or** GitLab via `glab`, the `forge` / `[forge_hosts]` keys, and `gwm trust add`. Triggers on `gwm`, `gwq`, `git worktree`, `.gwm.toml`, `forge`, `forge_hosts`, `glab`, `gwm trust add`, GitLab MR, `gwm create`, `gwm list`, `gwm exec`, `gwm clean`, `gwm review`, `gwm daemon`, `gwm statusline`, `gwm agents`, `gwm note`, `gwm bootstrap`, `gwm doctor`, `gwm switch`, `gwm tmux`, `gwm zellij`, `gwm link`, `gwm status`, `gwm shell-init`, `gcd`, `feat/#`, `fix/#`, GitHub issue/PR linking on a worktree.
The English summary is being prepared. Showing the original description.