Showing 47761–47790 of 77205 skills
Independent senior-engineering quality auditor — architecture, ownership, domain integrity, abstraction, and maintainability. Use as `--gate` inside the ck:cook pipeline (blocks a phase on BLOCKER/HIGH/current-change MEDIUM findings) or call directly with `--audit`, `--diff`, `--changed` on any repository, directory, or file. Never writes tests and never edits production code — it returns structured findings only; ck:cook or ck:fix apply the fix.
DangQuangSE/team-development-skills
Standalone testing skill — owns writing and running tests, verifying behavior, and two-pass TDD orchestration. Default mode analyzes changed scope and runs the relevant tests; `--unit`/`--integration`/`--e2e`/`--all` scope by test type; `--verify` reruns exactly the prior failures; `--all-phases <plan>` sweeps every completed phase for regression. `--tdd --prepare`/`--tdd --verify` bracket `ck:cook` for red-green TDD. Never edits production code, and blocks until a phase's `ck:quality` gate is APPROVED (except `--tdd --prepare`, which runs before any implementation exists).
DangQuangSE/team-development-skills
Dispatch to the right problem-solving technique based on how you're stuck
DangQuangSE/team-development-skills
Design and scaffold multi-agent squads/swarms using the graph orchestration pattern (nodes = agents, edges = dependencies/data flow). USE FOR: designing a coordination topology for a multi-agent squad (sequential pipeline, parallel fan-out/aggregation, branching, feedback loop, cyclic); building an orchestrator agent that delegates to specialist agents; setting up an adversarial/tribunal code or document review with independent reviewers; scaffolding a squad's agent files for a target coding-agent harness (e.g. Copilot CLI or Claude Code custom agents). DO NOT USE FOR: authoring a single agent's frontmatter/prompt body (use copilot-cli-custom-agents, claude-code-custom-agents, or the target harness's own skill); SKILL.md authoring (use create-skill); ad-hoc multi-agent chat with no explicit topology.
NetFabric/intelligentium
Find, inspect, query, redact, and troubleshoot logs, transcripts, sessions, and OpenTelemetry data from coding-agent harnesses on Windows, macOS, Linux, and WSL. USE FOR: GitHub Copilot in VS Code; Copilot CLI; Claude Code; OpenAI Codex; Gemini CLI; OpenCode; Cursor, Windsurf, Kiro, or other VS Code-family editors; locating log files; diagnosing tool or model failures; correlating turns, subagents, and tool calls; querying JSONL, plaintext, or SQLite without spending model tokens; preparing sanitized diagnostics. DO NOT USE FOR: application logs unrelated to coding agents; uploading raw logs; treating unstable transcript schemas as public APIs.
NetFabric/intelligentium
ALWAYS use when writing or reviewing agent-facing Markdown, including project instructions, skills and references, and custom-agent definitions. Covers only their shared content style: compact executable instructions, scannable information, active language, factual precision, and token efficiency. DO NOT USE FOR: artifact-specific structure, routing descriptions, metadata schemas, or prompt-body requirements; general Markdown documents; Markdown syntax or rendering rules.
NetFabric/intelligentium
Choose and tune which AI model a custom agent, subagent, or squad node should use. USE FOR: picking a model by task capability tier (general-purpose coding/writing, fast/cheap, deep reasoning/debugging, multimodal); efficiency-first vs. capability-first starting strategies; tuning an effort/reasoning-effort parameter instead of switching models; call cadence vs. provider prompt-cache TTL; cost-tier ranking and cost ceilings; cross-provider or cross-model-family diversity for independent/adversarial review; per-harness model field syntax and resolution order (GitHub Copilot CLI, Claude Code, VS Code custom agents); extending this framework to a new harness. DO NOT USE FOR: authoring the rest of an agent's frontmatter or prompt body (use copilot-cli-custom-agents, claude-code-custom-agents, or the target harness's own skill); designing squad topology (use agent-graph-orchestration); SKILL.md authoring (use create-skill).
NetFabric/intelligentium
Produce, consume, validate, and navigate Open Knowledge Format (OKF) bundles. Use when: creating an OKF knowledge bundle; converting catalogs, wikis, schemas, metrics, runbooks, or APIs to OKF; parsing or indexing OKF; designing an OKF producer or consumer; validating OKF v0.2 conformance; traversing index.md files and concept links; minimizing agent context while reading OKF documentation; handling provenance, trust, lifecycle, sources, or Attested Computation concepts. DO NOT USE FOR: OpenAPI schemas; generic Markdown documentation with no OKF bundle; knowledge graphs that do not use OKF files; runtime packaging or serving protocols not defined by OKF.
NetFabric/intelligentium
Create polished Python terminal user interfaces and skill scripts with Textual and Rich. Use when: building TUI apps; adding interactive terminal workflows; designing tabs, progress bars, checkboxes, radio buttons, tables, charts, forms, status views, keyboard navigation, color, or responsive terminal layouts; making Python scripts visually appealing and informative. Every skill script defaults to a TUI on an interactive terminal and provides --no-tui for deterministic stream output. DO NOT USE FOR: browser GUIs; desktop-native GUIs; plain shell commands with no interactive workflow; non-Python applications.
NetFabric/intelligentium
Open specification (ARD v0.9) for publishing, discovering, and verifying AI capabilities (MCP servers, A2A agents, skills, APIs) across federated networks. USE FOR: creating ai-catalog.json manifests; catalog entry schema; URN identifier format (urn:air:<publisher>:<namespace>:<name>); hosting at /.well-known/ai-catalog.json; DNS discovery (TXT/SRV records); Agentmap robots.txt directive; POST /search API; POST /explore API; GET /agents list API; federation modes (auto, referrals, none); trustManifest with SPIFFE/DID/attestations; representativeQueries for semantic search; building ARD registry clients; querying discovery services at runtime. DO NOT USE FOR: implementing MCP server tools (use MCP docs); implementing A2A agent cards (use A2A spec); OAuth/OIDC authentication.
NetFabric/intelligentium
Manage APM packages as a consumer: install, update, remove agent context (skills, prompts, agents, instructions, MCP/LSP servers). Use when: apm init; apm install packages; apm update / outdated; apm uninstall / prune; private or org packages; local bundles; authentication (GITHUB_APM_PAT); apm run scripts; apm audit; drift detection; governance ramp; apm doctor; troubleshooting install failures; managing apm.yml dependencies; lockfile (apm.lock.yaml) semantics; MCP server wiring; LSP server config. Covers: targets (copilot, claude, cursor, codex, gemini, windsurf, kiro), harness auto-detection, what to commit. DO NOT USE FOR: authoring or publishing packages (use apm-producer); writing apm-policy.yml.
NetFabric/intelligentium
Design, implement, migrate, debug, review, and test ReactiveUI 24+ applications. USE FOR: ReactiveObject; WhenAnyValue; ObservableAsPropertyHelper/ToProperty; ReactiveCommand; WhenActivated; Bind/OneWayBind/BindCommand; Interaction; routing and view location; RxAppBuilder; source generators; ReactiveUI.Primitives vs *.Reactive distributions; schedulers; DynamicData; validation; WPF, Avalonia, MAUI, WinUI, WinForms, Blazor. DO NOT USE FOR: generic Rx.NET pipelines without MVVM (use dotnet-rx); unrelated MVVM frameworks; visual UI design.
NetFabric/intelligentium
Modern .NET and C# best practices for code quality, performance, and correctness. USE FOR: choosing struct/class/record/readonly-record-struct; nullable reference types; pattern matching; primary constructors; collection expressions; required members; init-only properties; file-scoped namespaces; global usings; async/await patterns; ConfigureAwait; ValueTask vs Task; CancellationToken propagation; IAsyncEnumerable; Span<T>/Memory<T> usage; avoiding boxing; readonly struct; ArrayPool<T>; FrozenDictionary/FrozenSet; LINQ vs loops in hot paths; ArgumentNullException.ThrowIfNull; ThrowIfNegative; ThrowIfZero; IReadOnlyList return types; error handling patterns; GeneratedRegex; LoggerMessage; source generators for regex and logging; avoiding Math/MathF in favor of static methods on the numeric type. DO NOT USE FOR: generic math interfaces (use dotnet-generic-math); ASP.NET Core middleware; EF Core modeling.
NetFabric/intelligentium
Build, run, and publish .NET applications from a single C# file without a .csproj, using .NET 10 SDK file-based apps. USE FOR: dotnet run file.cs; dotnet run --file; shebang/shell-executable C# scripts; colon-prefixed directives (sdk, package, project, property, include); converting a file-based app to a project with dotnet project convert; publishing file-based apps with native AOT; packaging a file-based app as a .NET tool (PackAsTool); user secrets for file-based apps; flat *.run.json launch profiles; dotnet build/clean/publish/pack/restore on a .cs file; build caching behavior and dotnet clean file-based-apps; folder layout to avoid project-file cone conflicts. DO NOT USE FOR: traditional .csproj solution scaffolding (use dotnet-solution-setup); C# language idioms unrelated to the SDK/CLI (use csharp-best-practices); benchmarking (use dotnet-benchmarking).
NetFabric/intelligentium
Design, implement, debug, test, and review in-process producer-consumer pipelines with System.Threading.Channels. USE FOR: Channel<T>, ChannelReader<T>, ChannelWriter<T>, bounded/unbounded queues, BoundedChannelFullMode, backpressure, TryWrite, WriteAsync, ReadAsync, ReadAllAsync, completion, cancellation, concurrent producers/consumers, BackgroundService workers, in-memory event queues, overload protection, and channel performance. DO NOT USE FOR: durable or cross-process messaging, distributed pub/sub, broker delivery guarantees, Rx.NET stream composition, task-parallel dataflow blocks, or simple thread-safe collections with no asynchronous producer-consumer requirement.
NetFabric/intelligentium
Abstract math for trigonometric functions: definitions, domains, ranges, key identities, and inverse functions. USE FOR: implementing sin/cos/tan/cot/sec/csc; implementing arcsin/arccos/arctan/atan2/acot/asec/acsc; validating input domains for inverse trig; applying Pythagorean and angle-sum identities; choosing atan vs atan2; precision near domain boundaries. DO NOT USE FOR: angle unit conversions (use angles-and-circular-arithmetic); coordinate system conversions (use coordinate-system-conversions); rotation representations (use 3d-rotation-theory).
NetFabric/intelligentium
Build, maintain, debug, and review Visual Studio Code extensions. Use when: extension manifest, activation, commands, views, tree views, webviews, notifications, settings, language providers, tasks, debuggers, custom editors, authentication, Accounts, sign-in, account management, session lifecycle, Workspace Trust, desktop or web compatibility, testing, CI, packaging, Marketplace publishing. DO NOT USE FOR: general web applications or Copilot agent customization; use the relevant web-development or agent-authoring guidance.
NetFabric/intelligentium
Local web search and page fetching for AI agents via SearXNG and Firecrawl. Use when you need to search the web, fetch page content as markdown, or gather information from URLs. No API keys required.
BumpyClock/agent-templates
Protect and use focused time: choosing work that deserves deep focus, focus patterns from daily blocks to focus days and sprints, booking and defending calendar blocks, team norms and urgent routes, interruption reduction, a start ritual, handling attention residue, message batching and weekly focus-hour reviews. Use whenever someone cannot focus, has a fragmented day, keeps getting interrupted, needs deep work time for writing, analysis or coding, wants fewer notifications or wants team focus hours.
afeezadebayo/planning-task-management-skills
Set personal, career or small-team goals that get reached: one to three objectives, measurable key results with baselines and targets, committed, stretch, learning and habit goal types, initiatives and habits per key result, if-then plans, a capacity check, weekly confidence check-ins and fair 0 to 1 scoring. Use whenever someone wants to set goals or OKRs, plan a year or quarter, make vague goals measurable, connect weekly work to bigger aims, set team objectives or score last period's goals.
afeezadebayo/planning-task-management-skills
Design habits and routines that last: one or two habits linked to goals, tiny versions for hard days, cues from existing routines, environment design, if-then obstacle plans, light tracking and weekly reviews, plus morning, shutdown, weekly reset and focus routines and a method for breaking unwanted habits. Use whenever someone wants to build or break a habit, design a morning, evening or shutdown routine, stay consistent, restart routines after disruption or connect daily behaviour to goals.
afeezadebayo/planning-task-management-skills
Choose what matters now: goals first, then the right method (top three, Eisenhower matrix, impact and effort, MoSCoW, weighted scoring, 1-3-5), hard constraints, a capacity check against real free hours, a not-now list with draft messages and short lists for today and this week. Use whenever someone has too much to do, conflicting priorities, needs to explain trade-offs to a manager, wants to cut a backlog, or asks what to work on today or this week.
afeezadebayo/planning-task-management-skills
Audit how a person or small team plans and gets work done: capture, clarify, prioritise, plan, focus, review, goals, energy, tools and team requests scored 0 to 3, the biggest leaks, a minimal one-source-of-truth system, daily and weekly rhythms, a gradual rollout and handoffs to specialist skills. Use whenever someone feels busy but behind, keeps missing deadlines, has too many productivity tools, starts a new role or wants to set up an AI-assisted planning system.
afeezadebayo/planning-task-management-skills
Turn any outcome into a plan someone can start today: a definition of done, scope, milestones, tasks small enough for one sitting, dependencies and owners, estimates with 20 to 30% buffer against the planning fallacy, a pre-mortem, a schedule and the first next action. Use whenever someone has a big project that keeps stalling, needs a project plan, wants to break down a goal or task, has a deadline to plan backwards from or asks where to start.
afeezadebayo/planning-task-management-skills
Run a quarterly review and plan for a person or small team: goal scores with evidence, wins, misses and root causes, an agent-prepared time and energy audit, keep, stop, shrink and start decisions, next quarter's objectives, a 13-week plan with milestones, a capacity check, calendar protection and risks. Use whenever someone wants a quarterly review, to plan the next quarter or 12 weeks, to reflect on what worked, to reset after a busy period or to set team quarterly priorities.
afeezadebayo/planning-task-management-skills
Collect commitments from email, chat, meetings, documents, calls and ideas into one inbox, then process each item with the Getting Things Done decisions: delete, do now under two minutes, delegate, defer to the calendar, create a project or file as reference, extracting actions, owners and dates from notes and threads. Use whenever someone wants a brain dump, to process their inbox or to-do list, to turn meeting notes, email threads or chat into tasks, or feels overwhelmed by loose commitments.
afeezadebayo/planning-task-management-skills
Set up a plain-text task system a person and their AI agent share: a TASKS.md file with Today, This week, Waiting for, Later, Projects and Done, a MEMORY.md glossary that decodes shorthand, people and codenames, next-action rewrites, update rules and morning, after-meeting and weekly sync routines. Use whenever someone wants an AI agent to manage their to-do list, set up TASKS.md, consolidate scattered tasks, teach an agent their shorthand or sync tasks from meetings, email and chat.
afeezadebayo/planning-task-management-skills
Run a 30 to 45-minute weekly review with an AI agent: an agent-prepared brief, empty inboxes, last week's results, stale task decisions, chased waiting items, a next action for every project, the next two weeks of calendar, a goals check, three to five priorities, focus blocks and a weekly lesson log. Use whenever someone wants to do a weekly review, plan next week, clean up an out-of-control task list, restart after a holiday or keep their productivity system trusted.
afeezadebayo/planning-task-management-skills
Agent skill for agent - invoke with $agent-agent
shivamchopra7/claude-skill-directory
Agent skill for app-store - invoke with $agent-app-store
shivamchopra7/claude-skill-directory