最近新增
刚加入收藏的新技能，抢先试用。
review-all
leodearden
"Deep, infrequent, human-attended review of a WHOLE project's architectural and code quality against docs/code-quality.md — pins one tree, takes a whole-repo metrics snapshot (a report, never a gate), refreshes the stale instruments in delta mode (/hotspot-survey --refresh, /review --since) and consumes the census codebook, then runs a heuristic-driven architecture pass: one seat per area judging all fourteen heuristics and both stances, cross-area seats for SPOT / layering / orthogonal dimensions / stateless interactions, a skeptic per seat blinded to proposals, a synthesis joined by finding key with every prior instrument's open findings, and a critic of that synthesis; ends in deliberation with the human, a program doc and /prd per stream, and files the completion-driven trigger for the next run. ALWAYS use this skill for: '/review-all', 'review the whole project against the quality heuristics', 'whole-repo architecture and code-quality review', 'what should we refactor across the whole codebase', 'the quarterly factory self-review', or when the human gate task 'Run /review-all on <project>' dispatches. This is a serious commitment — the first dark-factory run measured 22.9M subagent tokens (8.6M of them in the Phase 2 instrument refreshes), 8 h of machine time for phases 1–4 and one full deliberation sitting plus the /prd work — so state the cost, Phase 2 included, and get a go before phase 2 (--full or --yes skips only the wait, never the posting). NOT for: does-it-run correctness of landed work (/review), bug-history hotspots alone (/hotspot-survey), confusion sightings (/census), one module (/study), one bug (/deb), authoring the remediation PRDs (/prd — fed by this skill's program doc), or anything unattended."
review
leodearden
"Deep, multi-phase code review — runs tests/lint/typecheck, audits architecture for stubs, broken wiring and quality-heuristic violations against docs/code-quality.md, then routes findings into tasks or deliberation. Incremental by default: re-reviews what changed since the last committed review report and re-verifies that report's open findings. ALWAYS use this skill for: /review commands, requests to verify software actually works end-to-end, post-orchestrator quality checks ('the tasks are done but does it actually work?'), finding stubs/NotImplementedError/placeholders, checking integration health across modules, finding dead code or orphan modules, auditing cross-module consistency after merges, running the full test suite with analysis (not just 'run pytest'), qualitative test coverage analysis ('are the tests just mocking everything?'), and a dispatched 'Run /review on <project>' human gate. This is NOT for: single-file PR reviews, creating review briefings (/review-briefing), historical bug-hotspot mining (/hotspot-survey), deciding which quality instrument to run (/review-all), unblocking tasks, explaining code, fixing lint, running tests without analysis, or implementing tasks. When in doubt about whether the user wants a deep project-wide review vs a simpler action, USE this skill — it handles scoping internally."
reflect
leodearden
"End-of-session reflection that captures decisions, discoveries, surprises, and insights to fused-memory. Use this skill when the user wants to wrap up a session, reflect on what happened, save learnings, or says things like 'let's wrap up', 'end of session', 'save what we learned', 'reflect on this session', or '/reflect'. Also trigger when a session has been substantive and the user signals they're done."
prd
leodearden
"Author and decompose PRDs under implementation-chain-completeness gates that prevent incomplete/ill-formed work from reaching the orchestrator. ALWAYS use this skill for: /prd commands, authoring a new PRD, decomposing a committed PRD into tasks, queueing tasks from a PRD into the orchestrator. Triggers on requests like 'let's write a PRD for X', 'draft a PRD', 'decompose this PRD', 'queue tasks from <prd>.md', or any mention of starting/finishing PRD-shaped work. Walks G1 (consumer named), G2 (user-observable leaf signal), G3 (assumed-substrate verified), G4 (cross-PRD seam ownership), G5 (design-first when stakes are high), G6 (premise validity), and the meta-gate 'would this PRD produce a complete/coherent/cohesive/good design under decompose-and-queue without further oversight?' before saving or queueing. Adapts to the current project via an optional overlay at .claude/skills/prd/project.md. This is NOT for: editing existing PRDs without re-running gates, running tasks (use /orchestrate), reviewing landed code (use /review), unblocking tasks (use /unblock)."
orchestrate
leodearden
"Implement software from a PRD or task tree using the dark-factory orchestrator. Use this skill when the user wants to: run the orchestrator against a PRD, check orchestrator/task status, resolve blocked tasks, resume stalled work, or manage concurrent TDD workflows. Trigger on mentions of PRDs, orchestrating implementation, running tasks through the pipeline, checking task status, or resolving blocked/failed tasks — even if the user doesn't say 'orchestrator' explicitly."
merge-queue
leodearden
"Merge a task branch to main via the orchestrator's merge queue using the submit→poll protocol. Use this skill whenever you need to merge a completed task branch into main and the orchestrator might be running — it submits via merge_request(wait_secs=100) then polls merge_status until the outcome is terminal, preventing races without blocking indefinitely. Trigger this when an agent says 'merge to main', 'submit merge', 'merge task branch', finishes fixing a blocked task and needs to merge, or any time code on a task branch is ready to land on main. If the escalation MCP isn't reachable, the skill falls back to direct merge. Prefer this over raw git merge --no-ff whenever working in the dark-factory repo."
factory-init
leodearden
"Onboard a software project — new or existing — as a dark-factory orchestrator target. Use whenever the user wants to 'factory-init' a repo, 'set up' or 'wire up' a project for the orchestrator, 'make this repo a dark-factory target', 'register a new project', or 'onboard <repo> into the factory' — or points at a directory and asks to get it ready for autonomous development, even if they don't say 'factory-init'. It confirms dark-factory is installed (installing it is out of scope), ensures a git repo, picks a hyphen-free project_id and a free escalation port, writes the per-project config, and registers the project with fused-memory reconciliation, then routes to review-briefing→review (existing code) or a goals discussion→/prd batch (greenfield), optionally adding a supervised systemd unit. NOT for: installing dark-factory itself (a separate skill), running the orchestrator (/orchestrate), writing a single PRD (/prd), creating a review briefing (/review-briefing), or unblocking a task (/unblock)."
/do — package this decision, then execute it in a fresh context
leodearden
"Hand the direction just agreed in this conversation off to a fresh context for autonomous execution. ONLY runs when the user explicitly types /do — never auto-invoke it. Enters plan mode, distills the whole preceding discussion into a self-contained plan, and appends the user's fixed execution protocol (implement in a worktree → /merge-queue → /reflect) so the plan runs end-to-end after 'Clear Context and Follow Plan'."
curate-fused-memories
leodearden
"Run the memory-consolidation curation sitting: batch-rule the backlog of 'Human gate: consolidate duplicate cluster' tasks and execute the resulting consolidations against the fused-memory Mem0 corpus under the gate-3200 retain-and-tag shape. Use when the user says 'run the curation sitting', 'consolidate duplicate memories', 'batch-rule the consolidation gates', 'clean up the Mem0 corpus', 'curate memories', 'adjudicate the duplicate-cluster gates', or wants the memory-consolidation backlog (task 3524 / esc-3524-1) worked. This is NOT for: ordinary memory writes (use /memory), the reconciliation escalation queues (recon-escalation-watcher), unblocking stuck tasks (/unblock), or a single ad-hoc near-exact dedup that recon Stage 1/2 can absorb inline — per the 2026-08-02 policy, new clusters route through inline Stage 1/2 consolidation, not new gate tasks."
記帳
itshanyu
在記帳討論串處理「金額 備註」格式的記帳訊息：AI 分類後寫入 Google Sheets。只在指定討論串生效。
secure-code-review
GitQuuu
Code-review checklist for correctness, security, robustness and performance in ASP.NET Core + EF Core APIs and Angular frontends, with severity levels and a findings format. Use when reviewing a diff, pull request or file for bugs and vulnerabilities (not layer structure, which the dotnet-n-layer skill covers).
dotnet-testing
GitQuuu
Unit-testing conventions for .NET with NUnit 4, Arrange-Act-Assert and FakeItEasy, for N-layer solutions (Service, BLL, ResponseService, Hangfire jobs, repositories). Use when writing, fixing or reviewing C# tests, deciding what to test, or running dotnet test.
dotnet-new-solution
GitQuuu
Bootstraps a new solution for this stack from scratch with the dotnet and Angular CLIs - Web API (controllers) + Services + DataAccess + NUnit tests, SQLite (app.db) as the starting database, ASP.NET Core Identity with JWT, central package management, development configuration in appsettings.Development.json, and an Angular + PrimeNG + Tailwind app. Use when starting a new project or repo, or when asked how to set one up.
dotnet-n-layer
GitQuuu
Conventions for ASP.NET Core N-layer modular monoliths (API → Services → Data Access) with thin controllers and feature-sliced service modules (Controller → BLL → Service → Unit of Work/Repository). Use when writing, placing or reviewing C# in such a solution, e.g. adding an endpoint or use case, a controller action, BLL, service, repository, DTO, DI registration or Hangfire job.
dotnet-identity-jwt
GitQuuu
Authentication and authorization for the ASP.NET Core Web API with ASP.NET Core Identity (users, roles, passwords, lockout) and JWT bearer access tokens with rotating refresh tokens, plus the matching Angular auth store. Use when adding or changing login, registration, refresh/logout, roles, [Authorize] policies, the current-user id, token settings, or the frontend auth flow.
devops-github-actions
GitQuuu
Three-branch strategy (development → staging → prod) with GitHub Actions - CI on pull requests, deploy per environment to Azure (App Service + Static Web Apps) or MonsterASP (Web Deploy), release and back-merge pull requests, branch rulesets, environment secrets and the bot identity for agent PRs. Use for CI/CD, pipelines, deployments, branch protection, releases, hotfixes, environments or hosting questions.
angular-frontend
GitQuuu
Conventions for Angular frontends (v20+, signals, standalone, zoneless/OnPush) built with PrimeNG components and Tailwind CSS that talk to a versioned ASP.NET Core API. Use when writing, placing or reviewing Angular code, e.g. a feature, component, page layout, PrimeNG table/form/dialog, route, API service, interceptor, or a spec file, or when wiring the frontend to a backend endpoint.
ado-plan
GitQuuu
Plans Azure DevOps Product Backlog Items for the agent team - reads PBIs tagged agent-plan (or a given PBI id), has the planner agent break each into tasks, and creates them as child Tasks tagged agent-proposed for the product owner to approve. Use when the user says plan the backlog, plan PBI 123, break down this item, or similar.
ado-deliver
GitQuuu
Builds one approved Azure DevOps Task end to end with the agent team - picks the next Task tagged agent-ready (or a given id), claims it, creates a branch, runs fullstack-developer, tester and reviewer, then commits, pushes, opens a linked pull request and updates the work item. Use when the user says take the next task, deliver task 456, work the backlog, or similar.
webrtc-turn-troubleshooting
HMS091
排查 WebRTC 通话（Nextcloud Talk/Matrix/Jitsi）跨网络连不上、TURN/STUN 配置与 coturn 排障、CGNAT 判断、托管 TURN 方案选型（Metered 等）
webrtc-turn-server
HMS091
诊断和修复 WebRTC 通话问题（Nextcloud Talk / Matrix / Jitsi）：WiFi 能通但 4G/5G 不通 = TURN 服务器缺失或不可达。覆盖 Nextcloud occ 配置检查（配置在数据库不在 config.php）、coturn 容器排查、STUN/端口探测、CGNAT 识别、托管 TURN 服务评估（Metered 等）、修复方案（公网IP转发 / 云服务器 coturn / Cloudflare TCP 隧道）。用户是中文非技术用户，全程代操作，需用户亲自做的步骤（打运营商电话、登录路由器、注册云账号）给话术/截图级指引。
nas-docker-deploy
HMS091
"Deploy, test, and sync Docker projects between Windows local source and Synology NAS (192.168.1.200). Covers Laravel, static sites, and other Docker Compose projects."
coturn-turn-server
HMS091
TURN/coturn 服务器配置与 WebRTC 跨网通话排障（Nextcloud Talk 等）。症状：WiFi/局域网通话正常但 4G/5G 或异地失败；自建 TURN 端口转发；托管 TURN 服务（如 Metered.ca）兼容性评估。
comfyui
HMS091
Generate images, video, and audio via diffusion workflows.