Latest Agent Skills
Everything added to the registry recently, newest first.
- chauthehienp3c1 SkillAtlas Explore
Acts as a curious, competent new joiner in the person's own role to work out what they ought to be asking about this particular system, proposes about ten questions, answers them one at a time from the registered sources with citations, raises follow-up questions and concerns (as questions to confirm, never as facts), writes what was learned back into kb/ by the normal cited route, and ends with a short recap. Remembers where the person is, so a second session resumes. Use when someone has read the orientation and does not know what to ask, asks "what should I be asking?", wants to explore or catch up on the system at their own pace, or runs /atlas-explore.
- chauthehienp3c1 BundleAtlas Verify
Has a separate, independent agent check every statement and every diagram box and arrow of a knowledge-base page or work artifact against the exact source text it cites, removes or turns into questions whatever is not supported, and records the pass; for a slimmed work artifact it also has a second agent check that nothing material was dropped from the original. Use when a page or artifact is about to be proposed for commit (atlas-onboard, atlas-ask, atlas-refresh, atlas-shape, atlas-brief and atlas-check run it), when someone asks to verify or fact-check a page or artifact, or when a review banner says the second-agent check is missing or out of date.
- chauthehienp3c1 SkillAtlas Ingest
Registers a new source (code repo, Markdown, PDF, meeting transcript, GitHub pull requests) in the team knowledge-base workspace, normalizes it through the matching adapter, updates the manifest, and judges how reliable the source is by spot-checking it. Use when someone wants to add a source, import a document or transcript, connect a repo, or has an export from Confluence, OneDrive, SharePoint or Rally.
- chauthehienp3c1 SkillAtlas Shape
Shortens a long, repetitive or AI-generated original (a requirements document, epic, feature, user story or meeting notes) into a one-screen work artifact in which every line cites the original word for word, lists what was left out, and files a finding when the original contradicts the code or the knowledge base; or, in gate mode, reviews a draft artifact for clear scope before the team approves it. Use when someone asks to slim, trim, simplify or shape a requirement, epic, feature or story, to turn a long document into a short one, or to check that a draft artifact is ready to approve.
- chauthehienp3c1 SkillAtlas Check
Compares a change (a pull request, a branch range or a set of files) with the story's acceptance criteria and the brief's declared scope, writes a check artifact with a cited verdict per criterion (met, partly met, not met or no evidence), lists files outside the scope and knowledge pages the change touches, and files a finding for each mismatch. Use when someone asks whether a change does what the story says, to review a PR against its story, to verify or test against acceptance criteria, or before saying a piece of work is done.
- chauthehienp3c1 SkillAtlas Brief
Generates the detail one role needs to pick up an approved story or feature (developer, QA, designer, analyst or any other role the team defines) from what exists today, cited to code or sources, plus clearly labelled agent proposals, the files expected to change, and open questions. Use when someone is about to start work on a story and asks for a brief, a task breakdown, implementation notes, test ideas or what they need to know to start.
- chauthehienp3c1 SkillAtlas Ask
Answers a question about the team's system with evidence and labels, checking the knowledge base first and the sources second, then writes what was learned back into kb/ so the knowledge base grows from use. Use when someone in a team knowledge-base workspace asks how something works, why something is the way it is, who knows about something, or what the team has decided or built.
- chauthehienp3c1 SkillAtlas
Front door for atlas, the team knowledge-base tool. Explains what atlas is, helps create a workspace for a team or find the one you already have, and says which folder to open in Cursor. Use when someone types /atlas, asks how to get started with atlas, or wants to onboard to a team and has no atlas workspace open.
- lingcang728 SkillZepp Coach
Endurance coaching on top of the user's own Amazfit / Zepp data through the ZeppBridge MCP server (zeppbridge-mcp). Use when the user asks about their training, recovery, readiness, heart-rate drift, aerobic efficiency, fatigue, race readiness, or wants a training plan drafted or sent to their watch. Reads the data first, then advises; drafts plans in ZeppBridge's format and only publishes after the user agrees.
- aper-ai BundleVirtual Cell Research
Orchestrate extensible virtual cell research workflows for transcriptomic and single-cell data. Use for data preparation and input audits, observed-response analysis, model-based gene or compound perturbations, prediction evaluation and split audits, interpretation of existing results, public-case reproduction, and method or adapter integration. Gene knockout, overexpression and drug screening are representative applications. Execute compatible analysis routes, preserve full results and provenance, and report implementation, quality and independent-validation status separately.
- openmaxai BundleOm Marketplace Client
Agent Market client. Pulls install intents placed by humans in the Agent Market workbench, installs approved skills and expert templates into this Agent after sha256 verification, and reports results and reconciliation back to the market. The Agent never decides on its own what to install. Config at ~/zylos/components/om-marketplace-client/config.json. Service: pm2 zylos-om-marketplace-client.
- alfhen BundleLaravel Idioms
Use for any work in a Laravel codebase, whether reviewing, planning, building, refactoring, debugging, speeding up or testing PHP code in a project with an artisan file or laravel/framework in composer.json, even when the user never says "Laravel". Load it before planning a change or answering a question about the code, not only before editing. Also use it to audit a Laravel codebase, judge its health, find code smells or write a refactor report. Concrete rules for Laravel 11-13 on controllers, Form Requests, policies, collections, Eloquent and N+1, migrations, API auth and errors, webhooks, security, uploads, races, outbound HTTP, events and mail, queues, scheduler, Artisan commands, caching, Blade, Livewire, Inertia, Filament 5, error reporting and logging, dates and money, Pest and PHPUnit tests, plus a mandatory "Before you finish" checklist. Not for PHP projects that aren't Laravel. Complements Laravel Boost's laravel-best-practices skill, so load both when both are installed.
- xplusplusai BundleAutoxpp Load Integration Dev
Loads the Senior Integration Developer role for pre-lifecycle work: Azure Functions, Service Bus, Dataverse plugins, OData, integration architecture and debugging. No arguments — just invoke and start working.
- xplusplusai BundleAutoxpp Quality Supervisor
Epistemic watchdog for the autoxpp lifecycle. Distinct from autoxpp-watchdog (which catches mechanical stalls — absence of motion). This skill catches wrongness of motion: confidence inflation, anti-pattern emergence, scope creep, doom-loop relapse. Invoked periodically on phase transitions and on-demand after non-green tester verdicts.
- xplusplusai BundleAutoxpp Load Senior Fo Dev
Loads the Senior D365 F&O Developer role for pre-lifecycle work: investigation, debugging, code research, solution design, root cause analysis. No arguments — just invoke and start working.
- xplusplusai BundleAutoxpp Test Data Seeder
Background agent that pre-seeds test data in the D365 environment while dev-v2 analyzes standard code. Reads test_cases.md as a shopping list, finds or creates required records via OData/SQL/browser, and writes test_data_manifest.md for the tester to consume.
- xplusplusai BundleAutoxpp Load QA Engineer
Loads the QA Engineer role for pre-lifecycle work: ad-hoc test planning, test data strategy, test matrix design, coverage analysis. No arguments — just invoke and start working.
- xplusplusai BundleAutoxpp Design Reviewer
Pre-coding design review gate between req-analyzer and dev-v2. Runs for requirements classified as complex or risky. Loads design-reviewer + senior-fo-developer roles, reads requirement.txt / work_items.md / test_cases.md and relevant dev-reference sections, and writes design_review.md with PASS / NEEDS-WORK / BLOCKED verdict. Dev-v2 cannot proceed until PASS.
- xplusplusai BundleAutoxpp Load Lifecycle
Bootloader for the autoxpp D365 F&O lifecycle. Call ONCE at the start of a requirement to mark the boundary between research/refine (pre-lifecycle) and autonomous execution (req-analyzer -> test-composer -> dev-v2 -> build -> tester -> DONE or fix-loop). The skill resolves workspace, writes requirement.txt from the arg, initializes lifecycle.log, spawns the watchdog, and auto-chains into req-analyzer + test-composer.
- xplusplusai BundleAutoxpp Test Composer
Compose test cases from a requirement. Reads requirement.txt, outputs test_cases.md with structured test cases including setup data, steps, and pass conditions. Append-only on feedback iterations — never remove old cases. Run once per requirement — skip if test_cases.md already exists and no new feedback. Works from the original requirement directly — does NOT depend on work_items.md.
- xplusplusai SkillAutoxpp Setup API Key
Configure your AutoXPP API key and MCP connection for premium skill access.
- xplusplusai BundleAutoxpp Req Analyzer
Analyze a requirement and produce structured work items with dependencies. Reads requirement.txt (and optionally Stage 1 output, feedback). Outputs work_items.md with developer-level task descriptions and a complexity flag (simple/complex/risky). Domain-specific artifact tags, grep patterns, and worked examples live in reference/domain-*.md. Run once per requirement — skip if work_items.md already exists and requirement unchanged.
- xplusplusai SkillAutoxpp Init Session
Initializes an AutoXPP session. Must be called before any other autoxpp skill in a conversation. Sets up session context on the MCP server.
- xplusplusai BundleAutoxpp Azure Devops
Use when the user asks to read, query, or interact with Azure DevOps work items, tickets, comments, attachments, or boards. Triggers on phrases like "read ticket", "check devops", "work item", "devops comments", "ticket 1069", or any Azure DevOps URL (dev.azure.com).
- xplusplusai BundleAutoxpp Ude Switch
Quick-switch Visual Studio 2022 UDE between multiple online D365 F&O environments (different customers) on a single machine. Use when user says "switch UDE", "switch FO env", "change to customer X env", "connect to <url>", or wants to change which online Dataverse the current UDE is pointed at. Reads UDE list from C:\Users\[user]\.autoxpp\ude-configs.json. Handles the full Power Platform Tools connection flow (Tools menu → Reconnect prompt → Login → URL entry → Select Solution → Client assets download) via UIA, then retargets the custom metadata folder in the auto-generated XPP config so UDEs don't collide on the same metadata path.
- xplusplusai BundleAutoxpp Browser V2
D365 Finance & Operations browser automation, built on playwright-cli. Use this skill - not raw playwright-cli - whenever a task opens, navigates, tests, or captures evidence in a D365 F&O / UDE / Dataverse / Power Apps canvas app web UI (any *.operations.dynamics.com, *.crm.dynamics.com, or apps.powerapps.com URL, a canvas app running locally via Vite, or any mention of a D365 form, menu path, workspace, or sales/purchase/warehouse screen). Adds F&O-aware authentication (Chrome-profile reuse that survives OAuth blocks and deployments), form-URL (mi=) and menu-tree navigation, canvas-app iframe and control handling, async-render handling, self-learning site patterns, cross-skill integration, and structured evidence capture on top of the built-in playwright-cli skill. Site-specific knowledge lives in reference/ files.
- xplusplusai BundleAutoxpp Watchdog
External safety net for the autoxpp lifecycle. Spawned ONCE at the start of any requirement lifecycle, before any other autoxpp skill. Runs a background poll script over lifecycle.log and emits STALL events when a phase transition is missed. Zero LLM cost per tick — pure file-based detection.
- xplusplusai BundleAutoxpp SQL Jit
Acquire Just-In-Time read-only SQL credentials from VS2022's 'SQL Credentials for Dynamics 365 FinOps' dialog for the active online UDE environment. Auto- launches VS2022 if not running (reuses autoxpp-build launcher scripts, same 3-attempt retry loop), drives the JIT dialog via PowerShell UIA, captures the connection string from clipboard, writes it to ~/.autoxpp/ude-configs.json → udeConfigs[].sqlCache. Credentials last ~24h. Companion to scripts/sql.py which reads the cache and runs queries via pyodbc. Use when a test case or investigation needs SQL access to internal tables / aggregates / joins that OData cannot express.
- xplusplusai BundleAutoxpp Tester
Execute test cases and produce a structured test report. Reads test_cases.md, orchestrates test execution via domain-appropriate tools (autoxpp-browser-v2 for UI paths, direct HTTP/SQL/Service Bus for integration paths), handles test data setup, captures evidence, and outputs test_report.md with pass/fail per case.
- xplusplusai BundleAutoxpp Dev V2
Focused D365 F&O coding skill. Reads work_items.md and implements X++ artifacts sequentially in dependency order. Uses autoxpp-dev-reference for D365 patterns. No planning (req-analyzer does that), no test design (test-composer does that). Autonomous-ready — never prompts for input. For fix loops, reads test_report.md.
- xplusplusai BundleAutoxpp Build
Drives Visual Studio 2022's full build-deploy cycle for D365 F&O via PowerShell UI Automation. Zero human clicks — compile, sync database, deploy to online environment.
- vibeic BundlePhase1 Completeness Deep Review
After phase1_one_shot_runner emits L*.json, AI checks that admitted source facts retain their meaning, classification, authority, and owning fields in the generated documents. Record documentary additions in the durable review sidecar, never by directly patching generated L documents; capture systematic producer gaps for plugin repair. Mandatory after every phase1 / phase2 / phase23 run before claiming PASS.
- vibeic BundleBenchmark Enhancement Capture
Capture a proven AI-assisted recovery into the responsible design, local tool fork, plugin program, or expert skill without adding a policy layer.
- vibeic BundleOpen Benchmark Methodology
Mandatory for VerilogEval, VerilogEval-v2, VerilogEval-Human, CVDP, RTLLM, PyHDL-Eval, RTL-Repo, MetRex, ResBench, ChipAgentsBench, benchmark, pass@1, benchmark floor/defect, run/rerun/score benchmark, or interpreting benchmark results. Enforces one general product entry, clean-room blind evaluation, Program First plus independent AI review/backup, official host scoring, evidence-backed triage, and capture of general enhancements.
- vibeic BundleCompliance Gate Spot Check
AI review of actual native tool evidence against original engineering limits, with explicit failures and unmeasured obligations.
- vibeic BundleScope Pattern Attestation
Layer-3 hardware attestation — talk to an oscilloscope via SCPI to verify behavioral patterns (or absence of patterns) on real silicon IO. Use when sim and static RTL checkers can both pass but you need to confirm the actual hardware doesn't exhibit a forbidden timing pattern (e.g. periodic wake pulses that should have stopped after a state transition). Triggers when user says "scope check", "verify on hardware", "is the wake pulse really stopping", or hands you scope screenshots / SCPI traces.