Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 566 files from 1 758 authors, of which 61 913 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
公众号选题｜爆款标题｜热点追踪｜系列策划 — 公众号 AI 选题与标题生成，覆盖热点调研、选题策划、起标题、写摘要、系列排期。面向自媒体编辑、内容运营。触发词（**单独触发仅限对已有标题/摘要的修改**）：「改标题」「换个标题」「重起标题」「优化标题」「标题再想想」「换个标题试试」「改摘要」「重写摘要」「优化摘要」「摘要再优化下」。新做选题、起新标题、策划系列/内容日历、追热点都请走 aws-wechat-article-main；需要多环节串联（写+审+排+配图+发）也走 main。
公众号发布｜公众号草稿箱｜公众号群发｜图文推送｜微信 API｜wechat automation｜WeChat API automation｜auto publish｜scheduled publish — 公众号 API 发布工具，图文入草稿箱或直接群发，支持封面素材上传、发布前检查与 draft/published 模式切换。面向公众号运营、自动化内容团队、开发者。触发词：「发布」「提交」「群发」「推送」「发出去」「上传到公众号」「发到公众号」「可以发了吗」「发布前检查」。需要多环节串联（写+审+排+配图+发）请走 aws-wechat-article-main。
公众号贴图｜九宫格｜多图推送｜图片消息｜表情包 — 贴图与多图推送：从创意构思、AI 生图到公众号图片消息发布全流程，含九宫格自动排布、多图压缩、组图打包。面向公众号运营、自媒体、IP 账号。触发词：「贴图」「多图推送」「发组图」「图片消息」「九宫格」「做一组图」「图片帖子」「发几张图」「不写正文发图」「只发图不写字」。是文章内配图/封面请走 aws-wechat-article-images；需要多环节串联（写+审+排+配图+发）请走 aws-wechat-article-main。
Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails or runtime safety to an LLM agent, generate or refine a sponsio.yaml, audit tool configurations for risks (data leaks, unguarded writes, missing confirmations), explain or review existing contracts, check what Sponsio would have blocked (`sponsio report`), move from observe to enforce mode, or debug why a contract is (or isn't) firing. Triggers on phrases like "set up sponsio", "add sponsio", "install sponsio", "add guardrails", "monitor my agent", "harden my agent", "audit my agent", "generate contracts", "explain my sponsio.yaml", "sponsio report", "flip to enforce", "false positive", "why is this rule firing".
Use after installing the sponsio-openclaw plugin to wire the runtime end-to-end. The plugin install only registers hooks + skills; the contract library and per-environment overrides are configured here. Bootstraps the per-plugin contract library tree at ~/.sponsio/plugins/, generates fresh starter libraries for OpenClaw plugins / MCP servers via `sponsio plugin scan` (with `--introspect` to auto-discover tool inventory; the agent then applies the prompt from `sponsio plugin prompt openclaw` to extract semantic contracts using its own LLM context — no separate API call), tunes the shipped rules to the user's actual environment, and verifies with a smoke test. Use when the user says any of "configure sponsio-openclaw", "set up sponsio-openclaw", "first-time setup of sponsio for OpenClaw", "wire up sponsio in this OpenClaw session", "add Sponsio guardrails for my OpenClaw plugins", "tune the plugin for my environment", "the plugin is too strict / too loose", "calibrate sponsio rules", "scan this OpenClaw plugin", "generate sponsio rules for my OpenClaw plugin", "I just installed Y plugin / MCP server in OpenClaw, what should sponsio block", or asks how to make sponsio-openclaw actually block things.
Use after `/plugin install sponsio-claude-code` to wire the runtime end-to-end. The plugin install only registers hooks + skills; the contract library and per-environment overrides are configured here. Bootstraps the per-plugin contract library tree at ~/.sponsio/plugins/, installs bundled starter libraries for popular MCP servers (github, filesystem, playwright), generates fresh starter libraries for plugins / MCP servers that don't ship one (via `sponsio plugin scan`), tunes the shipped rules to the user's actual environment (workspace path, expected call volume, dev/CI/prod profile), and verifies with a smoke test. Use when the user says any of "configure sponsio-claude-code", "set up sponsio-claude-code", "first-time setup of sponsio", "wire up sponsio in this Claude Code session", "add Sponsio guardrails for my MCP tools", "tune the plugin for my environment", "the plugin is too strict / too loose", "calibrate sponsio rules", "scan this plugin", "generate sponsio rules for X", "create a contract library for my plugin", "I just installed Y plugin / MCP server, what should sponsio block", or asks how to make sponsio-claude-code actually block things.
Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails or runtime safety to an LLM agent, generate or refine a sponsio.yaml, audit tool configurations for risks (data leaks, unguarded writes, missing confirmations), explain or review existing contracts, check what Sponsio would have blocked (`sponsio report`), move from observe to enforce mode, or debug why a contract is (or isn't) firing. Triggers on phrases like "set up sponsio", "add sponsio", "install sponsio", "add guardrails", "monitor my agent", "harden my agent", "audit my agent", "generate contracts", "explain my sponsio.yaml", "sponsio report", "flip to enforce", "false positive", "why is this rule firing".
独立校验与审查文件系统短剧项目中的故事、剧本、资产、连续性、资产图片提示词、分镜、关键帧和视频提示词。用户提出“审稿/检查剧本”“检查资产或连续性”“检查图片/视频提示词”“审查或诊断模板感”，或判断一集能否交付文本或 JSON 时使用；只发布审查问题、审查结论和修订要求，不代替负责人修改来源文件。
维护者专用的短剧 know-how 学习、验证与生命周期治理。仅在维护者明确要求从其当前会话提供的授权只读文本源学习完整短剧项目链，并把私有观察逐步转成去标识、去复刻、经盲测与独立审查的公共 reference、rubric 或 synthetic fixture 候选时使用；不用于普通创作、公开运行时取数、媒体生成或粗略数据分析。
编剧环节：创作或修订中文短剧、漫剧单集卡、因果节拍与可拍摄的 Markdown 剧本，也负责把现有中文剧本以保留原文、预览语义差异、创作者接受后发布的方式规范化。用户提出“写/改一集短剧”“把大纲写成剧本”“优化场景/对白”“去模板感地修订”“去 AI 味润色”“续写下一集”或提供现成剧本要求进入后续制作时使用；不负责资产、分镜、媒体提示词或终审。
将中文小说、短剧或漫剧想法、梗概、改编材料或已有系列笔记发展成可追溯的改编方案、戏剧方向、创作简报、导演阐述、故事引擎与分集地图，并按题材与制作形态（画风）选择写法。用户提出“导入小说做短剧”“开发短剧/漫剧”“做故事设定/系列大纲/分集规划”“写导演阐述”“这个题材怎么写”“定画风/制作形态”“把这个点子变成短剧”或需要梳理人物冲突与集间交接时使用；已有剧本可直接进入写作、资产或审查流程，不强制补开发文件。
为已接受的短剧镜头和关键帧编写或修改可复制的通用视频提示词与运动规格。用户提到视频提示词、文生视频、图生视频动作、人物表演过程、运镜、对白口型、环境运动、镜头时长、起止状态或把分镜转成视频提示词时直接使用；只描述单个已编镜头内的运动、表演、摄影与声音，不生成视频，不调用模型或供应商接口，也不改写分镜边界。
从短剧剧本拆解并统筹角色/造型、场景/视图、道具/状态和跨场连续性。用户说‘拆角色/场景/道具’、‘做资产表/角色表/场景表/道具表’、‘判断复用还是新变体’、‘更新造型/道具状态’，或拿现成剧本直接做视觉资产准备时使用；本 skill 不写资产图提示词，也不生成图片或视频。
为已确认的短剧角色、造型、场景、视角、道具和状态编写或修改可复制的通用资产图片提示词。用户提到角色设定图、三视图、人物参考图、场景设定图、场景空镜、场景板、道具图、造型或状态变体、局部编辑提示词，或要求用自然语言修改现有图片提示词时直接使用；只产出结构化规格与 Markdown 文本，不生成图片，也不调用模型或供应商接口。
把已接受的中文短剧剧本和资产转成原文落实表、有戏剧动机的镜头、连续性边界与冻结关键帧提示词。用户提出“拆分镜/设计镜头/做镜头表”“写首帧/关键帧提示词”“检查轴线、站位、视线、持物连续性”，或需要在不生成媒体的前提下把竖屏短剧、漫剧的剧本内容转成可拍的画面时使用。
基于文件系统初始化、继续、恢复和交付短剧或漫剧项目，并提供本地 Dashboard 管理项目文本与预览项目媒体。面向编剧、漫剧工作室与编导。用户提出“创建/继续短剧项目”“看进度/下一步”“打开 dashboard/项目控制台”“恢复中断或不完整发布”“交付文本包”，或任务跨多个环节、意图不明确而需要先判断当前状态与负责技能时使用；明确的写作、资产、提示词、分镜或审查请求由对应子 skill 直接处理。
Use this skill to drive Compose HotSwan from an AI agent (Claude Code, Cursor, any MCP client) so the agent can edit a Kotlin file, trigger a hot reload, capture a device screenshot, evaluate the result against a design intent, and iterate without a human in the loop. Covers the seven HotSwan MCP tools (hotswan_get_status, hotswan_reload, hotswan_take_screenshot, hotswan_start_snapshot, hotswan_stop_snapshot, hotswan_select_variant, hotswan_build_and_install), the canonical edit-reload-screenshot loop, snapshot-based rollback, and when to fall back to a full install for schema changes. Use when the developer says "get the AI to tune this screen until it matches a mock", asks "can the AI see what changed?" or "can the AI screenshot the device?", sets up a Claude Code or Cursor workflow that needs MCP tool access, or wants AI-driven UI iteration.
Use this skill to teach Claude exactly which Kotlin and Compose changes hot-reload under Compose HotSwan and which trigger a full incremental rebuild fallback. Root cause is Android Runtime (ART) class schema immutability; only method bodies are mutable at runtime, so any change to fields, signatures, constructors, interfaces, inline functions, or new resource ids forces a rebuild. Covers the supported-changes table, the rebuild-forcing list, the diff-then-batch workflow that keeps a hot-reload session inside the fast path, and the inline-function and new-resource-id pitfalls. Trigger when the user asks "why did this rebuild?", "why isn't this hot reloading?", wants to learn HotSwan's boundaries before adopting it, or when reviewing a refactor that risks pushing a hot-reload session into a full rebuild.
Use this skill to tune Jetpack Compose lazy-layout prefetch with LazyLayoutCacheWindow (Compose Foundation 1.9+, @ExperimentalFoundationApi) and pausable composition in prefetch (Compose Foundation 1.10+, default on). Covers configurable Dp-based ahead/behind cache windows plumbed through rememberLazyListState(cacheWindow = ...), NestedPrefetchScope for items containing inner lazy layouts (HorizontalPager inside a LazyColumn row), version requirements, and the trade-off between memory pressure and idle-frame work. Use when the developer mentions dropped frames at high scroll velocity, prefetch window, ahead/behind extents, LazyLayoutCacheWindow, NestedPrefetchScope, pausable composition for prefetch, or wants composition retained for items briefly scrolled past. Item-level fixes (keys, contentType) live in a sibling skill.
Use this skill to install and verify Compose HotSwan end to end so a developer goes from zero to working sub-second hot reload on a real device or emulator in one session. Covers the JetBrains IDE plugin install, the `com.github.skydoves.compose.hotswan.compiler` Gradle plugin wiring, the canonical `hotSwanCompiler { enabled = true; debugOnly = true }` DSL block, the HotSwan tool window flow, and the first save-to-reload verification. Trigger when the user mentions HotSwan, Compose hot reload, instant UI update, "save and see", "no rebuild", live edit on device, fast Compose iteration, or already has the JetBrains plugin installed and asks how to apply the Gradle compiler plugin.
Use this skill to run an end-to-end Jetpack Compose performance audit when the symptom is broad ("the app feels sluggish", "scroll is rough everywhere", "we're starting a perf sprint", "what should we fix first?"). Orchestrates the four-phase Measure → Diagnose → Fix → Verify loop by sequencing the 25 focused skills (release-mode setup, R8, Baseline Profiles, Compose Compiler reports, stability inference, Layout Inspector, `@TraceRecomposition`, stabilization, strong skipping, phase-deferral, derivedStateOf, lazy layouts, lazy prefetch, Modifier.Node, modifier ordering, flow collection, effects, CI gates, hot-reload) and produces a written audit report with Before/After Macrobenchmark numbers. Use when the developer wants a perf sprint kickoff, a pre-release perf gate, onboarding to a perf-troubled codebase, or a written deliverable. Use when the user mentions "audit", "perf review", "perf sprint", "where do I start", or has no specific symptom yet.
Use this skill to fix scroll jank, lost item state, and broken animateItem() animations in LazyColumn, LazyRow, LazyVerticalGrid, and LazyHorizontalGrid. Covers stable item keys, contentType for mixed-type feeds, Modifier.animateItem() requirements, hoisting modifier chains and painters out of the items lambda, and validating item composable stability. Use when the developer mentions LazyColumn jank, dropped frames while scrolling, items losing scroll state on insert/remove/reorder, mixed feeds of cards/headers/ads feeling sluggish, animateItem() not animating, RecyclerView view-type analog, key parameter, or contentType parameter. The prefetch-window tuning lives in a sibling skill.
Use this skill to keep Jetpack Compose state alive across HotSwan hot reloads by understanding the three escalating tiers Compose HotSwan uses (tier 1 targeted recomposition, tier 2 composition reset, tier 3 Activity.recreate) and choosing edits and state holders that stay inside tier 1 where scroll position, lazy items, dialog state, and per-composable remember values all survive. Explains which edits force escalation, which state holders survive each tier, and how to hoist transient UI state when the iteration loop must escalate. Use when the developer says "scroll jumped to top after a hot reload", "lost dialog state", "lazy column re-fetched", "tab selection reset", asks why HotSwan reload escalated to tier 2 or 3, plans a refactor and needs to know which scope it touches, or wants to know which state holders survive composition reset.
Use this skill to configure R8 correctly for a Jetpack Compose application — full mode by default, `proguard-android-optimize.txt`, resource shrinking on, and minimal keep rules because Compose ships consumer ProGuard rules. Covers AGP 8.0+ R8 full mode default, R8's Compose-aware optimizations (lambda grouping, `sourceInformation()` stripping, composable arg constant-folding, `ComposerImpl` devirtualization), legitimate keep needs (`@Serializable`, Hilt entry points, reflective `Saver`s), and the AGP 8.x missing-rule reporter / R8 retrace. Cited gain is roughly 75 percent startup and 60 percent frame-render improvement debug-to-release. Use when setting up a new Compose app, when a PR adds an over-broad keep like `-keep class androidx.compose.** { *; }`, when a release build crashes after enabling minification, when APK size needs reduction, or when first enabling minification.
Use this skill to instrument a Jetpack Compose composable with `@TraceRecomposition` from `skydoves/compose-stability-analyzer` so per-recomposition diffs (which state or parameter changed, what value transition) print to logcat under the `Recomposition` tag. Works in release-with-debug-symbols builds where Android Studio Layout Inspector cannot reach, and feeds the IntelliJ / Android Studio plugin's live recomposition heatmap (green under 10, yellow 10–50, red 50+). Covers the Gradle plugin setup, the `ComposeStabilityAnalyzer.setEnabled(BuildConfig.DEBUG)` runtime gate that keeps the instrumentation out of production, and the handoff to debug-time Layout Inspector and CI `stabilityCheck`. Use when the user mentions `@TraceRecomposition`, "trace recomposition", "compose-stability-analyzer", "recomposition logcat", "recomposition heatmap", "release-mode recomposition counts", or needs to confirm a stability fix in a release-like build.
Use this skill to ensure Jetpack Compose performance numbers reflect production reality by measuring against a release variant with R8 enabled, Live Literals disabled, and Compose Compiler reports read from the release output directory. Covers why debug builds lie (interpreted Compose runtime, JIT warmup, Live Literals constant-getters), how to set up a release-with-symbols measurement build, and how to wire Macrobenchmark, Compose Compiler reports, Layout Inspector, simpleperf, and Android Studio Profiler against it. Cited result is roughly 75 percent startup gain and 60 percent frame-render gain debug to release. Use when the developer reports "slow startup", "jank", "dropped frames", "high recomposition count", or quotes timings from `assembleDebug`, Layout Inspector, or `CompilationMode.None`. Use when reviewing a perf bug, setting up a CI perf gate, or before filing a perf regression.
Use this skill to diagnose and fix Jetpack Compose Modifier ordering bugs — wrong paint region for background, wrong click area for clickable, wrong clipping for clip, wrong measurement for padding/size, surprising graphicsLayer scope. Covers the wrap-the-next-modifier mental model, the canonical pitfalls (padding vs background, clickable placement, clip before background, graphicsLayer placement), and why hoisting an entire Modifier chain via remember { Modifier.… } is rarely a real perf win because Compose already interns identical chains. Use when the developer asks "why does the click area extend past the visible button", "why is my background painted in the wrong place", "does Modifier order matter", "should I cache my Modifier chain", or reviews a diff that reorders modifiers.
Use this skill to generate and measure Jetpack Compose Baseline Profiles end-to-end with the AGP 8.2+ Baseline Profile Generator module and the Macrobenchmark harness. Covers writing the `BaselineProfileRule` journey for cold startup plus first-scroll, generating `baseline-prof.txt`, verifying it shipped at `assets/dexopt/baseline.prof`, measuring with `MacrobenchmarkRule` under `CompilationMode.Partial(BaselineProfileMode.Require)`, and emitting accurate time-to-fully-drawn via `ReportDrawn` / `ReportDrawnWhen` / `ReportDrawnAfter` from `androidx.activity.compose`. Compose ships unbundled, so every Compose UI app benefits — cited gains around 30% faster startup and 40% smoother first-scroll. Use when the user mentions "baseline profile", "macrobenchmark", "slow cold startup", "first-scroll jank", "StartupTimingMetric", "FrameTimingMetric", "ReportDrawn", "TTFD", or preparing a release build for performance measurement.
Use this skill to decide when Jetpack Compose derivedStateOf is the right tool and when it is pure overhead. Covers the "input frequency must exceed output frequency" rule, the mandatory remember { derivedStateOf { } } wrapper, the canonical pitfall of capturing non-state variables by initial value (and the remember(key) fix), and the snapshotFlow alternative for fire-and-forget side effects on derived values. Use when the developer mentions derivedStateOf, scroll-position-driven booleans, threshold checks, firstVisibleItemIndex, "show FAB on scroll", recomposition counts that don't drop after wrapping a value, or asks whether a computed string concatenation should use derivedStateOf.
Use this skill when a Compose tree uses SubcomposeLayout, BoxWithConstraints, or Scaffold and the developer reports extra measure passes, slow first frame, or layout passes running content composition repeatedly. Covers why SubcomposeLayout composes its slots during the measure phase, why BoxWithConstraints forces a subcomposition for every new Constraints value, why nesting Scaffold or BoxWithConstraints multiplies the cost, when a custom Layout or Modifier.layout { } replaces SubcomposeLayout, and how to use SubcomposeLayoutState's slot reuse policy and precompose APIs when SubcomposeLayout is genuinely required. Use when the developer mentions BoxWithConstraints, SubcomposeLayout, Scaffold, "extra measure pass", "double measurement", "first frame slow", "subcompose", or notices that wrapping content in BoxWithConstraints regresses scroll perf inside a LazyColumn.
Use this skill to author new custom Jetpack Compose modifiers and migrate legacy ones from Modifier.composed { } to Modifier.Node + ModifierNodeElement<T>. Covers the persistent-node lifecycle (onAttach, onDetach, onReset, coroutineScope), the specialized node interfaces (DrawModifierNode, LayoutModifierNode, SemanticsModifierNode, PointerInputModifierNode, CompositionLocalConsumerModifierNode, LayoutAwareModifierNode, GlobalPositionAwareModifierNode, ObserverModifierNode, DelegatingNode, TraversableNode), why ModifierNodeElement MUST be a data class for diffing, and the manual-invalidation knobs (invalidateDraw, invalidateMeasurement, invalidatePlacement, shouldAutoInvalidate). Use when the developer mentions Modifier.composed, custom modifier, ModifierNodeElement, Modifier.Node, "rewriting our drawBehind helper", node lifecycle, or sees Modifier.composed { } in a code review.
Use this skill to find which Jetpack Compose composables are recomposing and why, using Android Studio Layout Inspector recomposition counts and skip counts, the per-parameter Argument Change Reasons (Changed / Unchanged / Uncertain / Static / Unknown) introduced in Android Studio Hedgehog and later, and runtime `@TraceRecomposition` from `compose-stability-analyzer` for production-like measurement. Walks through enabling counts, mapping each Argument Change Reason to a fix, and confirming the result in a release build. Use when the developer says "this should be skipping but isn't", "I want to see recomposition counts", asks what "Uncertain" or "Unknown" means in the inspector, or needs to confirm a stability or strong-skipping fix actually worked end-to-end.
Use this skill to push frequently-changing Jetpack Compose state reads (scroll position, animation values, drag offsets) out of the Composition phase and down into Layout or Draw using lambda-based modifiers like Modifier.offset { }, Modifier.layout { }, Modifier.graphicsLayer { }, Modifier.drawBehind { }, and Modifier.drawWithCache { }. Covers the three-phase model (Composition, Layout, Draw), why a state read at phase N invalidates phase N and every phase below, the modifier-phase cheat sheet, and lambda providers (() -> T) for hoisting hot values across composables. Use when the developer mentions every-frame work, scroll jank, animation jank, dropped frames, animated alpha or offset, "the whole subtree recomposes on scroll", Modifier.alpha(state.value), Modifier.offset(x.dp), or graphicsLayer.
Use this skill to reason about Jetpack Compose's Strong Skipping Mode — the default since Kotlin 2.0.20 — including what it changes about skippability, when it does and does not auto-`remember` lambdas, and which escape hatches (`@DontMemoize`, `@NonSkippableComposable`, `@NonRestartableComposable`, `@ReadOnlyComposable`) apply where. Covers verifying the mode is active, auditing lambda capture sites, and the gaps where strong skipping does not memoize (`LazyListScope.items {}`, `Modifier.pointerInput {}`, object expressions, non-@Composable scopes). Use when the developer asks "do I still need @Stable?", "does this composable skip?", "why does this still recompose despite strong skipping", "when do I need @DontMemoize or @NonSkippableComposable?", is migrating from older Compose, or sees auto-remembered lambdas in compiler output.
Use this skill to diagnose Jetpack Compose stability problems by enabling and reading the Compose Compiler Reports (classes.txt, composables.txt, composables.csv, module.json). Covers the Gradle DSL, the release-only build requirement, and how to interpret per-class and per-composable stability annotations including stable, unstable, runtime, restartable, skippable, readonly, @static, and @dynamic markers. Use when the developer asks "why does this recompose", reports jank, dropped frames, slow scroll, high recomposition count, suspects an unstable parameter, mentions Compose Compiler Reports, classes.txt, composables.txt, module.json, or wants to know which composables are non-skippable. The fix lives in a sibling skill — this one only diagnoses.
Use this skill to migrate Compose UI from `collectAsState()` to `collectAsStateWithLifecycle()`, hoist `Flow<T>` parameters out of composables, and apply `.conflate()` / `.distinctUntilChanged()` / `snapshotFlow` so background CPU and battery stop draining and chatty flows stop invalidating the UI per emission. Covers ViewModel `StateFlow`/`SharedFlow` consumers, sensor and location streams, and the "Flow as composable parameter" antipattern. Trigger when the user mentions `collectAsState`, `collectAsStateWithLifecycle`, lifecycle-aware flow collection, `Lifecycle.State.STARTED`, background battery drain from a Compose screen, `snapshotFlow`, `Flow` parameter on a composable, conflate, or distinctUntilChanged.
Use this skill to set up a CI gate that fails the build when Compose stability silently regresses, using the `skydoves/compose-stability-analyzer` Gradle plugin (primary) or the `j-roskopf/ComposeGuard` plugin (alternative for non-Android multiplatform). Covers applying `com.github.skydoves.compose.stability.analyzer`, configuring the `composeStabilityAnalyzer { stabilityValidation { ... } }` DSL, generating a `.stability` baseline with `:stabilityDump`, committing it to version control, and wiring `:stabilityCheck` into a GitHub Actions or other CI job. Use when the team wants a stability SLO, when an unstable parameter slipped into a shared data class and went unnoticed until jank was reported, when migrating a large app to strong skipping, or when the user mentions stabilityCheck, stabilityDump, baseline drift, ComposeGuard, or "fail the build on stability regression".
Use this skill to choose the cheapest correct effect API in Jetpack Compose — `LaunchedEffect`, `DisposableEffect`, `SideEffect`, `rememberUpdatedState`, and skydoves/compose-effects' `RememberedEffect` and `ViewModelStoreScope`. Covers stale-callback bugs in long-lived `LaunchedEffect`, setup/teardown for non-coroutine subscribers, avoiding a coroutine scope just to react to a key change, and per-row ViewModels in a `LazyColumn`. Trigger when the user mentions LaunchedEffect, DisposableEffect, RememberedEffect, SideEffect, rememberUpdatedState, ViewModelStoreScope, effect restarts unexpectedly, leaked listener, or per-item ViewModel.
Use this skill to fix unstable Jetpack Compose types once a stability diagnosis has identified them. Covers the three-tier strategy — make the type truly stable with val plus immutable fields, mark with @Immutable or @Stable when the source is owned, and use stabilityConfigurationFiles for third-party or Java types. Explains the compiler-level difference between @Immutable and @Stable (static expression promotion), kotlinx.collections.immutable for List/Set/Map parameters, and the StableHolder wrapper escape hatch. Use when the developer asks how to stabilize a User class, a List parameter, java.time.LocalDateTime, a Flow parameter, or when the compiler report shows unstable params and the developer wants the fix. The diagnostic step lives in a sibling skill.
Use this skill to explain why the Compose compiler classified a class or composable parameter as stable, runtime, unknown, or unstable. Covers the 12-phase inference algorithm, the five compiler-level stability types (Certain / Runtime / Unknown / Parameter / Combined), the generic bitmask encoding (Pair=0b11, ImmutableList=0b1), the Known Stable Constructs registry, and the runtime `$stable: Int` field generated by `@StabilityInferred`. Use when the developer asks "why is X classified as Y?", when a stability report shows a surprising `runtime stable`, `unknown`, or `unstable` verdict, when generics, inheritance, cycles, interfaces, or cross-module classes are involved, or when the user mentions `$stable`, `@StabilityInferred`, separate compilation, or "the compiler thinks my class is unstable but it looks fine".
Use this skill to install and operate the `skydoves/compose-stability-analyzer` IntelliJ / Android Studio plugin so the developer sees Compose stability feedback live in the editor instead of waiting for a Gradle build. Covers installing the plugin from disk, configuring the `Settings → Tools → Compose Stability Analyzer` panel, reading the four gutter colors (green stable, red unstable, yellow runtime, gray no-params), the per-parameter hover documentation, the inline parameter hint badges, and the `UnstableComposable` weak-warning inspection with its `@Suppress("NonSkippableComposable")` and `@Suppress("ParamsComparedByRef")` quick fixes. Use when the user mentions gutter icons, inline hints, the stability inspection, the IDEA plugin, real-time stability feedback while editing, or asks why a composable is flagged as non-skippable in the editor.
Use this skill to drive the active investigation features of the `skydoves/compose-stability-analyzer` IntelliJ / Android Studio plugin: the static Recomposition Cascade visualizer that walks the call graph from a root `@Composable`, and the live Recomposition Heatmap that streams `D/Recomposition` events from a connected device''s logcat into block inlays above each instrumented composable. Covers the `Compose Stability Analyzer` tool window''s three tabs (Explorer, Cascade, Heatmap), the cascade analyzer''s static PSI walk with depth cap and cycle detection, the ADB logcat command the heatmap consumes, and the toggle/clear actions. Use when the user asks "what gets dragged in if I change this composable", "how many times did this recompose during that scroll", "what is the blast radius of this state change", or mentions the cascade tab, the heatmap tab, the recomposition inlays, or `Toggle Recomposition Heatmap`.
Classify whether a data-backed request is LP, MILP, QP, routing, or non-optimization analytics.
Infer optimization structure from uploaded tables and identify minimal clarifications before cuOpt modeling.
Run cuOpt in the NemoClaw sandbox — probe/smoke gates, prefer cancelable Python gRPC jobs, use legacy remote execution only when that API is unavailable, then vendored cuOpt skills.
Map interpreted optimization problems into cuOpt-native models for the fast path with minimal clarifying questions.
Troubleshoot cuOpt LP/MILP problems including errors, wrong results, infeasible solutions, performance issues, and status codes. Use when the user says something isn't working, gets unexpected results, or needs help diagnosing issues.
> variable/constraint reference for the max-supply base model.
Choose fast direct-to-cuOpt solve versus replayable or auditable model artifact mode.
Coordinate uploaded data plus a natural-language question into interpretation, clarification, cuOpt solve, and a user-facing answer.
> Generate a Datadog Terraform provider data source end to end and open a review-ready (operationIds), artifact name, cardinality, description, and overwrite target; (2) Generation — build an annotated OpenAPI slice with slice_and_annotate.py, run tfgen on it, run make docs/build, and commit onto a new branch; (3) PR — a quick runtime-risk scan (trusting the generator for correctness), draft the standard PR body with disclaimers + testing guide, and open the PR with `gh`. Use this skill whenever the user wants to generate a Datadog data source, mentions tfgen / generator-v2, slice_and_annotate, an OpenAPI operation they want a data source for, opening a PR for a generated data source, evaluating generated code against goldens, or writing cassette / acceptance-test instructions — even if they don't say "skill".
> End-to-end workflow to diagnose, reproduce, fix, and validate a failing Datadog Terraform provider integration test. Takes any input pointing at other description of what's failing. Runs autonomously through 8 phases — identify → validate in CI → reproduce locally → plan fix → execute → open draft PR → monitor → report.
Run Datadog Terraform provider acceptance tests with proper RECORD modes and capture output for analysis. This agent is invoked via Task tool and writes results to files.
Migrate lane for fskill-creator; analyzes a legacy skill directory into behavior map, function split proposal, and source evidence.
Create lane for fskill-creator; normalizes user briefs into create_context for the main skill to generate functional skills.
Create, maintain, or migrate functional skills; supports creating from a requirement brief and migrating an existing legacy skill directory into a functional skill structure.
Edit CapCut / JianYing video projects — read and write subtitles, timing, speed, volume, templates, animations (fade/ken-burns), and cut long-form to shorts. Use when the user mentions capcut, jianying, subtitles, video editing, draft_content.json, draft_info.json, or cutting videos.
Speak the last response aloud using text-to-speech
Stop any currently playing text-to-speech audio
>- Workaround for Claude Code filtering BMP PUA Unicode (U+E000-U+F8FF). Supplementary PUA Nerd Font icons like (U+F0000+, e.g. nf-md-github, nf-md-kubernetes, nf-md-battery) can be written directly. BMP PUA icons (Powerline, Font Awesome, Devicons) require placeholder syntax like {{ U+E0A0 }} or {{ nf-fa-star }} (without spaces), which hooks auto-convert. Invoke when reading or writing Starship configs, tmux themes, shell prompts, or statuslines.
Claude Skills — questions
Answers built from the skills we actually parsed.