Showing 39211–39240 of 77205 skills
Run a deep session retrospective analyzing the most recent AI coding session. Uses Entire.io session data + static analysis, then the agent reviews its own work to extract learnings and generate rules.
liwala/sheal
Author and maintain AGENTS.md files — the open, tool-agnostic format for giving coding agents project context. Use when: creating AGENTS.md; writing an agent instructions file; root or nested AGENTS.md for monorepos; migrating CLAUDE.md, AGENT.md, .cursor/rules, or copilot-instructions.md to AGENTS.md; greenfield project setup before code exists; brownfield onboarding for an existing codebase; documenting build/test/lint commands, code style, PR/commit conventions, and security considerations for agents; AGENTS.md discovery and precedence rules. Works for any language, framework, or project size. DO NOT USE FOR: authoring SKILL.md skill files (use create-skill); APM package/plugin authoring (use apm-producer); language-specific style rules (use language skills e.g. csharp-best-practices).
aalmada/Stationary
Create and maintain Claude Code custom subagents (.claude/agents/*.md files). USE FOR: authoring project (.claude/agents/) or user (~/.claude/agents/) subagent files; frontmatter fields (name, description, tools, disallowedTools, model, permissionMode, maxTurns, skills, mcpServers, hooks, memory, background, effort, isolation, color, initialPrompt); writing descriptions that drive automatic delegation and 'use proactively' phrasing; invoking subagents via natural language, @-mention, session-wide --agent, or the Agent tool; restricting which subagent types a coordinator can spawn with Agent(name1, name2); nested subagents and depth limits; built-in subagents (Explore, Plan, general-purpose, claude); troubleshooting a subagent that won't load or isn't invoked. DO NOT USE FOR: GitHub Copilot CLI custom agents (use copilot-cli-custom-agents); agent teams/teammates (a different, session-spanning feature); MCP server authoring; SKILL.md authoring (use create-skill).
aalmada/Stationary
Explore a codebase with codebase-memory-mcp's knowledge graph. USE FOR: understanding unfamiliar code; finding symbols, callers, dependencies, and architecture; following documentation, service, or deployment relationships; comparing indexed snapshots; checking graph evidence and coverage. DO NOT USE FOR: installing or configuring CBM; use the codebase-memory skill. For human visual exploration, use codebase-memory-lens.
aalmada/Stationary
Explore a codebase visually with codebase-memory-mcp Lens. USE FOR: starting or using CBM Lens; browsing source alongside graph relationships; viewing architecture, routes, hotspots, and index coverage; editing architecture decision records through the local UI. DO NOT USE FOR: agent-driven structural code discovery when the CLI is available; use the codebase-memory skill.
aalmada/Stationary
Use codebase-memory-mcp to estimate which tests a code change can affect. USE FOR: graph-based test selection; test-impact analysis from a diff; deciding whether CBM evidence supports a targeted test run. DO NOT USE FOR: replacing test execution or claiming full coverage from a partial graph.
aalmada/Stationary
Create and maintain GitHub Copilot CLI custom agents (.agent.md files). USE FOR: authoring .github/agents or ~/.copilot/agents profiles; frontmatter fields (description, target, name, model, tools, mcp-servers, disable-model-invocation, user-invocable, deferred-tool-loading, skills, reasoning-effort, sidekick); writing descriptions that drive auto-delegation (the CLI routes on description quality, like skills); building orchestrator + specialist squads with the task tool; /fleet parallel subagents; built-in agents (explore, task, research, code-review, rubber-duck, security-review, general-purpose); subagent depth/concurrency limits; list_agents and write_agent coordination. DO NOT USE FOR: VS Code-only fields beyond target (agents: allowlist, handoffs) or GitHub.com cloud agent configuration; MCP server authoring; SKILL.md authoring (use create-skill).
aalmada/Stationary
Automate GitHub Copilot CLI in GitHub Actions workflows. USE FOR: installing/running `copilot -p` in workflow steps, choosing GITHUB_TOKEN vs a personal access token (COPILOT_GITHUB_TOKEN) for authentication, setting the copilot-requests write permission, minimal-permission tool allowlisting (--allow-tool, --deny-tool, --no-ask-user, -s/--silent, --output-format=json), triggers (schedule, workflow_dispatch, push), the recommended GitHub Agentic Workflows (gh-aw) alternative to direct CLI invocation, and security/cost considerations (fork PR prompt-injection risk, billing attribution, cost centers). DO NOT USE FOR: embedding the Copilot agent runtime into your own application (use copilot-sdk instead); general GitHub Actions authoring unrelated to Copilot; the Copilot code review or PR features outside of CLI automation.
aalmada/Stationary
Embed the GitHub Copilot agent runtime into your own application using the Copilot SDK. USE FOR: CopilotClient/createSession setup, streaming responses, custom tools, permission handlers, hooks (pre/post-tool-use, session-start), custom agents and sub-agent delegation, MCP servers, skill and plugin directories, session persistence, fleet mode, steering/queueing, calling the SDK from skill scripts/ to run one bounded non-deterministic AI step inside an otherwise deterministic script, and choosing an auth/deployment path (CLI setup, backend services, multi-tenancy, GitHub OAuth, BYOK). Covers Node.js/TypeScript (@github/copilot-sdk), Python (github-copilot-sdk), Go (github.com/github/copilot-sdk/go), Rust (github-copilot-sdk crate), .NET (GitHub.Copilot.SDK), and Java (copilot-sdk-java). DO NOT USE FOR: authoring SKILL.md files consumed by VS Code Copilot (use create-skill instead); using the Copilot IDE extension or chat UI directly; general LLM/chat API integration unrelated to the Copilot SDK.
aalmada/Stationary
Create or update AI agent skills (SKILL.md + reference files) for any harness that supports the format: GitHub Copilot, Claude Code, Cursor, Codex, Gemini CLI, Windsurf, Kiro, OpenCode, and more. Use when: authoring a new skill from scratch, improving or restructuring an existing skill, deciding how to split content across files, writing skill frontmatter, choosing trigger phrases for the description field, organizing reference files. Covers skill architecture, compact writing rules, frontmatter constraints, and research using official documentation and Microsoft Learn. DO NOT USE FOR: general coding tasks, VS Code extension development, non-skill documentation.
aalmada/Stationary
Measure C#/.NET performance with BenchmarkDotNet instead of stopwatches. USE FOR: BenchmarkDotNet console project setup, BenchmarkSwitcher.FromAssembly; [Benchmark]/[Benchmark(Baseline = true)]; [Params]; [GlobalSetup]/[GlobalCleanup]; [MemoryDiagnoser] allocation columns; [BenchmarkCategory]/[GroupBenchmarksBy]/[CategoriesColumn]/[HideColumns]; reading Mean/Error/StdDev/Ratio/Allocated results and BenchmarkDotNet.Artifacts output; avoiding dead-code elimination via return values; comparing .NET runtimes/versions via AddJob/WithRuntime; ManualConfig job classes with WithEnvironmentVariable and RatioStyle.Trend; testing environment-variable variants via .runsettings, `dotnet test -e`/`-s`, Visual Studio run-settings. DO NOT USE FOR: SIMD API selection (dotnet-simd, has its own SIMD-width benchmarking config); LINQ/enumerable tradeoffs (dotnet-enumerable); generic math (dotnet-generic-math).
aalmada/Stationary
Write and optimize C#/.NET enumerables, iterators, and LINQ usage. USE FOR: choosing IEnumerable<T>/IReadOnlyCollection<T>/IReadOnlyList<T>/ICollection<T>/IList<T>/IAsyncEnumerable<T> for params/returns; foreach codegen and value-type vs reference-type enumerator performance (List<T>, arrays, Span<T>, ImmutableArray<T>, ArraySegment<T>); avoiding boxed enumerator allocations; Count() vs Any() vs Count property complexity traps; First()/Single()(OrDefault) cost and predicate-overload collapsing; ToList()/ToArray() allocation cost vs lazy evaluation; returning Enumerable.Empty<T>()/yield break instead of null; writing yield-based iterators, lazy validation, coroutines, behavior trees; writing async iterators with await foreach/yield return, EnumeratorCancellation/WithCancellation token propagation, ConfigureAwait; handling enumerables via reflection/Roslyn (NetFabric.Reflection/CodeAnalysis). DO NOT USE FOR: SIMD/vectorized span math (dotnet-simd); generic math over numeric types (dotnet-generic-math).
aalmada/Stationary
C# 11+ generic math with static abstract interface members in System.Numerics. USE FOR: writing generic numeric algorithms; constraining type parameters to INumber<T>/IFloatingPoint<T>/ITrigonometricFunctions<T>; implementing custom numeric types with operator overloads; defining static abstract interfaces (IAngleUnits pattern); CreateChecked/Saturating/Truncating cross-type conversions; AdditiveIdentity/MultiplicativeIdentity; singleton bridge pattern for static abstract at runtime; ISpanFormattable/ISpanParsable; generic Sum/Average/Lerp methods; Half/float/double/decimal compatibility. DO NOT USE FOR: Unity math; pre-.NET 7 System.Math/MathF workarounds; Python/JavaScript numerics.
aalmada/Stationary
Design, implement, debug, review, and test Reactive Extensions for .NET (Rx.NET) pipelines with System.Reactive. USE FOR: IObservable<T>/IObserver<T>; Observable creation and adapters; LINQ-style operator selection; hot/cold/connectable streams; Subjects; Publish/Replay/RefCount/AutoConnect; schedulers and concurrency; disposal and cancellation; errors/retry; backpressure limits; Task/event/IAsyncEnumerable interop; virtual-time TestScheduler tests; Rx.NET 7 migration and UI packages. DO NOT USE FOR: ReactiveUI application architecture; RxJS/RxJava syntax; simple .NET events with no stream composition; producer-consumer workloads requiring built-in backpressure (prefer Channels or IAsyncEnumerable).
aalmada/Stationary
Vectorize hot loops in C#/.NET the right way — reach for System.Numerics.Tensors (TensorPrimitives) first, then System.Runtime.Intrinsics (Vector128/256/512) for hand-written algorithms, hardware intrinsics only as a last resort. USE FOR: choosing between TensorPrimitives, Vector<T>, Vector128/256/512, and X86/Arm/Wasm intrinsics; MemoryMarshal/LoadUnsafe/StoreUnsafe span-to-vector patterns; hardware-acceleration checks (IsHardwareAccelerated, IsSupported); widest-vector-first code paths with scalar/small-input fallbacks; masked remainder handling for non-idempotent vs idempotent ops; lane-crossing pitfalls with Vector256/512 horizontal reductions; eliminating bounds checks/branches in scalar/remainder code; multi-core parallelization via Parallel.Invoke chunking over TensorPrimitives calls; testing SIMD paths via DOTNET_Enable* env vars and .runsettings; benchmarking with BenchmarkDotNet job configs. DO NOT USE FOR: GPU compute (CUDA/TorchSharp); SIMD in non-.NET languages.
aalmada/Stationary
Repository and solution-level scaffolding best practices for .NET: .slnx solution format, Directory.Build.props shared MSBuild properties, Directory.Packages.props central package management (CPM), .editorconfig, SourceLink, deterministic/reproducible builds, global.json SDK pinning. USE FOR: scaffolding a new .NET repo or solution; choosing .sln vs .slnx; sharing MSBuild properties (TargetFramework, LangVersion, Nullable, ImplicitUsings, TreatWarningsAsErrors, EnforceCodeStyleInBuild, EnableNETAnalyzers, Deterministic) across every project; configuring SourceLink for debuggable NuGet packages; central package version management and GlobalPackageReference; pinning the SDK with global.json; .editorconfig code-style rules; CI-only ContinuousIntegrationBuild flag; reproducible/deterministic builds and packages; repo root file checklist. DO NOT USE FOR: C# language feature choices (use csharp-best-practices); benchmarking (use dotnet-benchmarking); generic math (use dotnet-generic-math).
aalmada/Stationary
ALWAYS use this skill whenever creating, editing, or reviewing any Markdown (.md) file — README.md, SKILL.md, AGENTS.md, CONTRIBUTING.md, changelogs, or any other Markdown documentation — even for small edits. Write and review Markdown files for consistent, correctly-rendering formatting: heading hierarchy and spacing, list marker and indentation consistency, fenced code block languages and blank-line spacing, table pipe and column consistency, link and image conventions, and whitespace hygiene. USE FOR: authoring or reviewing README.md, SKILL.md, AGENTS.md, or any Markdown documentation; fixing inconsistent headings, lists, code fences, or tables; fixing issues reported by Markdown linters such as markdownlint; choosing link/image/emphasis styles; general Markdown formatting conventions. DO NOT USE FOR: non-Markdown formats (reStructuredText, AsciiDoc); prose tone or content-quality review; the SKILL.md authoring workflow itself (see create-skill); AGENTS.md content structure (see agents-md).
aalmada/Stationary
Author Mermaid diagrams inside ```mermaid fenced code blocks in markdown files (README, AGENTS.md, PR descriptions, chat responses). Covers every stable, non-experimental diagram type: flowchart, sequence, class, state, entity relationship, user journey, Gantt, pie, quadrant, requirement, gitGraph, block, packet, kanban, XY chart, event modeling. Use when: picking a diagram type; writing correct fence syntax; documenting architecture, processes, timelines, schemas, or data relationships compactly for humans and agents alike, since a diagram conveys structure in far fewer tokens than prose. DO NOT USE FOR: the Mermaid Live Editor or mermaid.ai chat (fence syntax only); experimental or beta diagrams (swimlanes, mindmap, timeline, sankey, architecture, radar, treemap, venn, ishikawa, wardley, cynefin, treeView, ZenUML, C4); general Markdown formatting (use markdown-best-practices).
aalmada/Stationary
Convert data to/from TOON (Token-Oriented Object Notation) for lower-token LLM context. Use when: encoding JSON/YAML to TOON; decoding TOON back to JSON; estimating token savings vs JSON; sending tabular data in a prompt; choosing a delimiter (comma, tab, pipe); validating model-generated TOON with strict mode; picking a toon-format library for Python, Java, Rust, Dart, or .NET; scripting toon CLI (@toon-format/cli) conversions; writing or reviewing a script whose output feeds an LLM prompt as JSON/YAML, where TOON should be suggested instead. Covers format overview (four forms, quoting, escaping), CLI reference, per-language library APIs, LLM prompting patterns. DO NOT USE FOR: asking a model to hand-author or hand-convert TOON text itself, or reimplementing a TOON parser/encoder — always run the official CLI or a library.
aalmada/Stationary
Free-first paid advertising audit and optimization skill, focused on the 3 platforms where 95% of advertiser spend lives: Meta, Google, TikTok. Guided onboarding (/ads start) saves context once and step-by-step OAuth walkthroughs; continuous coach (/ads next) ranks Quick Wins after each audit. ~158 weighted checks with scoring, parallel agents, industry templates, and AI creative generation.
Hainrixz/claude-ads
Modern, interactive alternative to `/do` — clarify intent up front, then take a task end-to-end with a serial AI review gauntlet (lens debate (lowy ⇄ hickey) → codex debate → simplify → code-police, each editing the branch in turn) → CI → evidence. ONLY invoke when the user explicitly types `/be` or `$be`; never auto-select from a natural-language request.
srid/emanote
Review code for quality, simplicity, and common mistakes before declaring work complete.
srid/emanote
Iteratively study and apply elegant coding patterns. Each iteration - understand the code, research what simple and elegant code looks like, apply learnings, verify with CI. Use as a standalone refactoring pass or when the user asks to make code more elegant, simple, or idiomatic.
srid/emanote
Audit code for correctness and rigor — logic errors, silent error swallowing, wishful thinking, and unjustified fallbacks. This is not a style review; it's a logic review. Use when you want a focused correctness audit separate from the full code-police pass.
srid/emanote
Evaluate code (especially LLM-generated) for structural simplicity using Rich Hickey's "Simple Made Easy" framework. Use this skill whenever reviewing a PR, diff, or code snippet for accidental complexity — particularly when the code was generated by an AI coding assistant and line-by-line review isn't feasible. Also use when the user asks about complecting, simplicity vs. easiness, structural coupling, or concept deduplication. Trigger on phrases like "is this simple", "does this complect", "review for complexity", "structural analysis", or any reference to Hickey, Simple Made Easy, or grey-box review.
srid/emanote
Evaluate architecture and module boundaries for volatility-based decomposition using Juval Lowy's framework (from "Righting Software", building on Parnas 1972). Use when reviewing module splits, service boundaries, new abstractions, or any decomposition decision. Trigger on phrases like "where should this boundary be", "how to split this", "module boundaries", "encapsulate change", "volatility", or references to Lowy, Parnas, or "Righting Software". Complements /hickey (interleaved concerns) with a different lens (change encapsulation).
srid/emanote
odu MCP server launcher — drive CI from a coding agent. `bin/serve` resolves odu via Nix and runs `odu mcp` in the cwd. See the repo README for the tools/resources and override knobs.
srid/emanote
Adversarial "perfection" review — hold a change to an *ideal* bar, not just a correct one, assuming eternal time, unlimited energy, and no ship pressure. Use when the user asks to review "for perfection", to make a defect "impossible to express", or to hunt where a defect "relocates" across review rounds. Grounds every claim in the diff, fans out adversarial verifiers via Workflow, and reports residual surfaces with a structural fix for each. ONLY invoke when the user explicitly asks for a perfection / ideal-bar review.
srid/emanote
Iterative measurement-driven improvement loop. Measure, profile, mutate, re-measure, commit. Works for performance, bundle size, complexity, test coverage — anything quantifiable. Use when the user wants to systematically improve a metric through repeated cycles of profiling and targeted changes.
srid/emanote
How a downstream app consumes the shared @kolu/surface stack (@kolu/surface · surface-app · surface-nix-host · surface-mcp) — declaring a typed reactive surface, serving it, consuming it (SolidJS hooks or a CLI), and mirroring a remote surface over ssh. Grounded in the real consumers: kolu, pulam-web, drishti, odu, and the TUIs. Load when wiring a surface server/client/mirror, or reaching for getHostSession / a link / the `.use()` hooks. CHANGING the framework is gated separately — `.claude/rules/surface.md` (a paired, CI-green drishti PR pinned to final kolu HEAD).
srid/emanote