Migrate a .NET 10 project or solution to .NET 11 and resolve all breaking changes. This is a MIGRATION skill — use it when upgrading from .NET 10 to .NET 11, NOT for writing new programs. USE FOR: upgrading TargetFramework from net10.0 to net11.0, fixing build errors after updating the .NET 11 SDK, resolving source-breaking and behavioral changes in .NET 11 runtime, C# 15 compiler, and EF Core 11, adapting to updated minimum hardware requirements (x86-64-v2, Arm64 LSE), and updating CI/CD pipelines and Dockerfiles for .NET 11. DO NOT USE FOR: .NET Framework migrations, upgrading from .NET 9 or earlier, greenfield .NET 11 projects, or cosmetic modernization unrelated to the upgrade. NOTE: .NET 11 is in preview. Covers breaking changes through Preview 3.

Activation requires either supplied .NET coverage reports/percentages/line, branch, or condition metrics, or an explicit request to collect .NET coverage for analysis. USE FOR: interpreting that evidence, including Cobertura data, partial conditions, plateaus, target arithmetic, project-wide coverage-backed CRAP, and coverage-backed refactoring safety. Analyze supplied reports directly without rerunning tests or installing tools. DO NOT USE FOR: requests with neither coverage evidence nor explicit coverage-collection intent, including hypothetical change-survival questions (use test-gap-analysis); CRAP or refactoring safety for one named target (use crap-score); or requests owned by test-tagging, find-untested-sources, test-anti-patterns, run-tests, or code-testing-agent.

Fix MSBuild targets that generate files during the build but those files are missing from compilation or output. USE FOR: generated source files not compiling (CS0246 for a type that should exist), custom build tasks that create files but they are invisible to subsequent targets, globs not capturing build-generated files because they expand at evaluation time before execution creates them, ensuring generated files are cleaned by the Clean target. Covers correct BeforeTargets timing (CoreCompile, BeforeBuild, AssignTargetPaths), adding to Compile/FileWrites item groups, using $(IntermediateOutputPath) instead of hardcoded obj/ paths. DO NOT USE FOR: C# source generators that already work via the Roslyn pipeline, T4 design-time generation that runs in Visual Studio, non-MSBuild build systems.

Install a .NET SDK locally for safe preview testing, specific-version pinning, or reproducible team setups — without modifying the system-wide installation. USE FOR: trying .NET previews safely, testing specific SDK versions, installing MAUI or other workloads on a preview, updating or replacing an existing local SDK, creating reproducible team/CI install scripts, configuring global.json paths. DO NOT USE FOR: system-wide SDK installs, .NET hosts older than 10, runtime-only installs, or projects not using SDK-style commands.

Activate this skill when BenchmarkDotNet (BDN) is involved in the task — creating, running, configuring, or reviewing BDN benchmarks. Also activate when microbenchmarking .NET code would be useful and BenchmarkDotNet is the likely tool. Consider activating when answering a .NET performance question requires measurement and BenchmarkDotNet may be needed. Covers microbenchmark design, BDN configuration and project setup, how to run BDN microbenchmarks efficiently and effectively, and using BDN for side-by-side performance comparisons. Do NOT use for profiling/tracing .NET code (dotnet-trace, PerfView), production telemetry, or load/stress testing (Crank, k6).

Author and review GitHub Actions workflow YAML safely so syntactically-valid YAML can't ship a workflow that GitHub Actions refuses to run. USE FOR: editing, adding, or reviewing any file under .github/workflows/, writing run-name/name/if/env/run values that contain ${{ }} expressions, diagnosing a run that fails with 'This run likely failed because of a workflow file issue' and no jobs starting, deciding when a workflow scalar must be quoted, validating workflows with actionlint. DO NOT USE FOR: authoring application YAML unrelated to GitHub Actions, Azure Pipelines, GitLab CI, or non-workflow YAML. SCOPE: this skill covers *syntactic/structural* correctness of workflow YAML (quoting, parsing, actionlint); for *semantic and functional* workflow design (what a workflow should do, agentic-workflow behavior), see .github/agents/agentic-workflows.agent.md — the two are complementary. INVOKES: actionlint (downloaded pinned binary) plus git/grep for inspection.

Depth-first RE investigation loop for a single binary or function cluster: decompile→rename→retype→comment→re-read, with context-rot guards and on-task checks. Use when triage has already identified the interesting area and the goal is full understanding: what does function X do, identify cryptographic primitives, locate C2 protocol, recover data structures. Triggers on: 'deep analysis', 'understand function', 'recover struct', 'crypto identification', 'C2 protocol', 'reverse this binary fully', 'what does this function do'.

Hunt ReDoS (CWE-1333, Catastrophic Backtracking) — identify regexes with nested quantifiers or overlapping alternation that cause super-linear matching time, trace tainted input paths to regex sinks, demonstrate timing PoC, and validate with response-time delta. Covers PCRE/RE2/V8/Python re engine differences. Triggers on: 'ReDoS', 'regex denial', 'catastrophic backtracking', 'redos', 'regex complexity', 'nested quantifiers', 'regex amplification', 'CWE-1333'.

Internal — invoked headlessly by the peon eval server; humans should run `peon eval <pack>` instead. Execute one PeonPing reroll job — invoked headlessly by the peon eval server as: "Use the peon-ping-remix skill to execute the reroll job at <path>". Reads the job JSON (scope, category, index, caption), rewrites the affected sound prompt(s) to honor the caption, re-renders via scripts/pack-render.py, and logs the change to eval-log.json.

Post a "what's changed since the last release" recap to the release Slack channel for final QA. Groups merged PRs by author and classifies each as feature / bug fix / task. Use when the user wants a release recap, a changelog since the last tag, or to prep QA before cutting a release from main.

Multi-agent, browser-driven QA pass over a branch or PR — scope it, plan it, fan out one subagent per testing area in its own isolated sandbox, compile a severity-ranked markdown report. Use for an "E2E test", "QA pass", "manual test", or "bug bash" request — broader than driving the UI to check one fix (see `playwright`) or reviewing a diff (see `code-review`).

Look at Kiln's UI in a real browser, and run its end-to-end tests. Use when checking UI you are changing, taking a screenshot of the app, driving the app with playwright-cli, starting the dev sandbox with playwright_server.sh, running or debugging `npm run tests:e2e`, or working with the seeded fixture project that gives the app's screens data to render.

Use for standalone Matrix admin requests (register users, create rooms, manage membership, upload files). Also use when you need to send a file to the admin via Matrix media upload. Do NOT use for Worker/project creation — those handle Matrix operations internally.

Guidelines for Ascend NPU kernel / Triton-Ascend backend performance work in the FLA repo. Covers profiling with torch_npu, PipeUtilization/MemoryUB CSV analysis, Cube/Vector/MTE/UB bottleneck diagnosis, and kernel optimization (UB tiling, grid splits, fusion/split, varlen, G_T_CONTIG gate loading, constexpr DMA-path split / TAIL_MODE, extract_slice, MTE OOB, int32 address overflow, tl.cast vs constexpr .to, make_block_ptr int32 offsets, correctness gates, tl.dot left-operand clobber). NPU kernels must not use num_warps/num_stages. Per-kernel catalog: references/cases.md (incl. causal_conv1d core-grid). Use when working on NPU profiling, kernel_details/op_statistic, aic_metrics, fla triton_ascend backends (ops or modules), g transpose stride-1, UB overflow, dual-path DCE, grid limits, int64 pointer math, tl.dot reuse, or Ascend performance.

Technical reference for writing or editing open-slide pages — file contract, 1920×1080 canvas, type scale, layout, palette/visual direction, assets, speaker notes, stepped reveals, page transitions, and morph transitions. Consult this whenever you are about to write or modify any file under `slides/<id>/`, including from inside the `create-slide` or `apply-comments` workflows, or for any ad-hoc slide edit. Triggers on phrases like "edit slide", "tweak this page", "fix the layout", "change the palette", "reveal one by one", "add a transition", "morph transition", "write the speaker notes", "generate the script / talk track", "investigate the slide framework", "how do slides work here".

Use this skill when the user wants to create, draft, author, or extract a slide theme in this open-slide repo. Triggers on phrases like "create a theme", "make a theme called X", "extract a theme from <slide>", "build a theme from these images". Produces two paired files under `themes/` — `<id>.md` (palette, typography, layout, fixed Title/Footer components, motion) and `<id>.demo.tsx` (a runnable demo slide that the dev-UI Themes panel previews). Do NOT use for editing real slides — only for authoring the theme bundle.

Use only when a developer explicitly asks to clean, prune, tidy, or organize DeepChat SDD documentation after implementation and validation. Scans docs/features, docs/issues, and docs/architecture; prefers multi-agent review when available; removes completed issue docs when a linked GitHub issue is closed or implementation and validation evidence proves the bug no longer exists, drops stale plans and legacy task files from completed feature or architecture goals, and deletes obsolete feature or architecture docs.

用体验而不是定义来教授概念、原理或检验观点：先给与学习者认知水平相称的局面，让其选择，再用公平的意外显化认知缺口，结构化后才命名，并以迁移局面循环复测。USE WHEN 用户调用 '/ljg-teach'、说 '用情境教我'、'别先讲答案'、'通过案例让我学会'，或希望通过选择与反馈理解一个概念或观点。NOT FOR 直接定义查询（用 ljg-is/ljg-word）、八维概念解剖（用 ljg-learn）、伴读文本（用 ljg-read）。

盲区扫描——读昨天你与 AI 的全部对话，照出暴露的思维盲区（不是不懂的知识，是让某类真相一直看不见的思维习惯），再从微信读书挑一本书的一章精准补上，落成一篇完整分析笔记。Use when user says '扫盲区', '盲区', '照盲区', '看看我的思维盲区', '我昨天想漏了什么', 'blind spot', 'ljg-blind', '/ljg-blind', or wants yesterday's AI conversations analyzed for cognitive blind spots plus a targeted weread chapter to fill them. 可选参数：传一个日期(YYYY-MM-DD)扫那天而非昨天。NOT FOR 纵向深钻一个观点（用 ljg-think）、一个领域降秩（用 ljg-rank）、陪读一篇文本（用 ljg-read）、找一个领域的约束（用 ljg-constraint）。

Read-only readiness check for a generator model version (covered, generatable for you, gated) and the post-deploy launch instructions — publish, then remove the gate — filled in with the version's real URLs and commands. Use after a new generator model's deploy lands, or whenever someone asks where a launch stands. Called by onboard-generator-model; usable on its own.