All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 307,718
- 12,822
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse ai & agents skills
Showing 3,049–3,072 of 307,718 skills
- DiarioSave or enrich this session's note in the Obsidian vault of the current workspace (`<workspace>/claude/diario`) — a summary of what was done and decided, links to artifacts/PRs/cards/planning files, open items and how to resume the session. Use when the user asks to save the session to Obsidian ("salva no obsidian", "registra essa sessão") or when wrapping up significant work.Votes: 0GitHub stars: 2
- Build Pcf ControlDesign and build Power Apps Component Framework (PCF) code components end to end - deciding first whether PCF is even the right tool, then producing a build plan and working control verified against Microsoft Learn, with checkpoints where PCF actually breaks. Trigger whenever the user says "build a PCF control", "PCF component", "code component", "custom control", "field control", "dataset control", "virtual control", "pac pcf", "component framework", "spec a control", or describes a bespoke ...Votes: 0GitHub stars: 4
- Setup WorkstationTake a machine from nothing to fully equipped for building Power Platform solutions with AI agents - installs the CLIs, SDKs, runtimes, Microsoft and Powercademy plugin marketplaces, workload plugins and recommended MCP servers, signs in, verifies everything works, and ends with a readiness card. The first thing to run on any new machine. Trigger whenever the user says "set up my machine", "set up my workstation", "setup workstation", "new laptop", "new machine", "first-time setup", "get me s...Votes: 0GitHub stars: 4
- Check SetupDiagnose and repair an existing Power Platform development toolchain - CLIs, auth profiles, agent runtimes, plugins, MCP wiring - finding what's broken, outdated or misconfigured, repairing it with consent, and ending with a readiness card. Trigger whenever the user says "check my setup", "is my setup ok", "something's broken", "doctor", "my auth is a mess", "which account am I signed in as", "why isn't pac working", "wrong tenant", "is anything out of date", "my plugins aren't loading", or h...Votes: 0GitHub stars: 4
- Writing SkillsThis skill holds the Powercademy Skills house standard and the lint-enforced constraints that CI rejects violations of - dual-runtime portability rules, description limits, path conventions, the mechanics quarantine, redaction policy. Reviewing or authoring a marketplace skill without loading it will miss enforced constraints and fail CI. Trigger whenever the user says "write a skill", "new skill", "create a plugin", "add a skill to the marketplace", "review this SKILL.md", "review my skill",...Votes: 0GitHub stars: 4
- Flow ConventionsApply Powercademy's Power Automate lessons before building, editing or debugging a cloud flow - whichever tool does the building - so known traps are avoided rather than rediscovered. This skill holds the accumulated flow gotchas log: editing flows that already run (renames, child-flow contracts, blast radius, regression checks), designer quirks (255-character descriptions, nesting), expressions, Parse JSON, HTTP and Microsoft Graph permissions, child flow patterns, environment variables and ...Votes: 0GitHub stars: 4
- Dataverse ConventionsApply Powercademy's Dataverse and Power Platform conventions before creating or changing schema - tables, columns, choices, record status, relationships, solutions, publishers - so established judgement is applied and known mistakes are not repeated. Trigger before any Dataverse schema work: "create a table", "add a column", "new choice column", "status field", "statecode", "status reason", "set up a solution", "which publisher", "add to solution", "import failed", "missing dependency", or an...Votes: 0GitHub stars: 4
- Plan Canvas AppMake the decisions that determine whether a Power Apps canvas app survives contact with real data - delegation strategy, data architecture, screen and navigation design, performance conventions - and produce a build plan Microsoft's canvas authoring tooling can then execute. Trigger whenever the user says "canvas app", "plan a canvas app", "build a canvas app", "design an app", "app screens", "gallery", "Power Fx", "delegation", "delegation warning", "which data source should I use", or descr...Votes: 0GitHub stars: 4
- Promote SolutionRun a Power Platform solution promotion end to end with checkpoints - pre-flight the source and target, export the right solution as managed, move it, import, then verify with evidence - stopping before anything irreversible. Trigger whenever the user says "deploy this solution", "promote to test", "deploy to production", "ship this", "release this", "move this to UAT", "export the solution", "import the solution", "run the deployment", "publish my changes to another environment", or names tw...Votes: 0GitHub stars: 4
- Design Alm ProcessDesign the delivery process for a Power Platform solution - environment strategy, solution segmentation, publisher and naming, promotion path, environment-variable and connection-reference handling, and who approves what - producing a written ALM process the team can actually follow. Trigger whenever the user says "set up ALM", "ALM process", "environment strategy", "how many environments do I need", "dev test prod", "solution strategy", "how do I move this to production", "deployment process...Votes: 0GitHub stars: 4
- WellspringGenerate alternatives for frontend state and interaction models using ownership, time, and representation shifts. Use when the model is awkward, not for a mandatory state audit.Votes: 0GitHub stars: 2
- TrialsBuild frontend regression tests that observe real user behaviour and survive implementation refactors. Use for interaction, integration, and critical journey coverage.Votes: 0GitHub stars: 2
- SeaworthyHarden a selected frontend journey across async states, recovery, accessibility, and performance constraints. Use for implementation readiness, not a universal visual-style audit.Votes: 0GitHub stars: 2
- PilotRoute surface work to an execution SOP, a creative heuristic, or a direct answer. Use when the needed kind of help is unclear; do not impose a suite-wide pipeline.Votes: 0GitHub stars: 2
- LookoutEstablish delivery observation and decision-linked frontend telemetry for a chosen release. Use for preview, measurement, and post-release checks with privacy and rollback boundaries.Votes: 0GitHub stars: 2
- LiveryExplore coherent visual directions across colour, type, space, form, imagery, and motion. Use to invent a visual character, not to certify polish or run every atelier lens.Votes: 0GitHub stars: 2
- KeelBuild a walking skeleton for one selected frontend journey across real integration seams. Use to establish an end-to-end path, not for ordinary CSS questions or speculative architecture.Votes: 0GitHub stars: 2
- BulwarkMaintain frontend module boundaries and reusable design artifacts with demonstrable checks. Use for architecture erosion, stale abstractions, and design-system integration.Votes: 0GitHub stars: 2
- BearingsExplore frontend architecture by reframing journeys, ownership, and the experience of time. Use before committing a product direction, not as a compulsory frontend architecture checklist.Votes: 0GitHub stars: 2
- TouchstoneEvaluate a specific software project for a stated use using source, maintenance, compatibility, and trial evidence. This is a repository-assessment skill, not the root A/B experiment platform.Votes: 0GitHub stars: 2
- ForageFind and capture a bounded shortlist of software projects for a concrete need. Use for repository discovery, with dated sources and an explicit search stopping point.Votes: 0GitHub stars: 2
- ReckoningAnalyse research results against the recorded plan, inspect failure patterns, and bound the claims. Use for evidence review before writing or making a research decision.Votes: 0GitHub stars: 2
- ProspectFind research possibilities by connecting tensions, absences, and neighbouring fields. Use for open-ended question generation rather than literature scoring or forced project selection.Votes: 0GitHub stars: 2
- LedgerWrite a reproducible experimental plan for a chosen research question. Use after direction selection to define comparisons, data boundaries, metrics, and resource limits.Votes: 0GitHub stars: 2