Development skills

Turn failures, logs, symptoms, or flaky behavior into a compact repro and verification plan. Use when debugging needs a reproducible failure path.

The English summary is being prepared. Showing the original description.

Stage, commit, and push code changes with branch safety and explicit staging. Use when ready to commit work. Invoked by saying "commit", "push", or "commit and push".

The English summary is being prepared. Showing the original description.

Use when converting a design direction into maintainable production frontend code, selecting architecture within the existing stack, implementing semantics, assets, loading behavior, CSS/layout, components, and progressive enhancement.

The English summary is being prepared. Showing the original description.

Produce publication-style figures from MIKE+ .res1d results via the mike-plus MCP server — a stacked rainfall-runoff hydrograph, a single time series, a network map, a baseline-vs-scenario overlay, or a longitudinal profile (bed / crown / ground / max water level along a pipe string), in the house style (Arial 12, ticks inward, SI units, no title). Use when an agent must render MIKE+ results as a PNG without opening the GUI. No license required.

The English summary is being prepared. Showing the original description.

Run MIKE+ simulations headless via the mike-plus MCP server and report result files + engine status. Use when an agent must execute a MIKE+ .sqlite model's active (or a named) simulation without opening the MIKE+ GUI, then hand the .res1d outputs to reading/plotting. Requires MIKE+ installed + a valid license. Always run on a copy.

The English summary is being prepared. Showing the original description.

Bring an EPA SWMM (.inp) or EPANET (.inp) model into MIKE+ via the mike-plus MCP server — the bridge from an INP builder such as SWMMCanada or agentic-swmm into a MIKE+ database that mike_model_info / mike_run can use. Use when the user has an .inp and wants it in MIKE+. Requires MIKE+ installed + a checked-out license (demo mode caps the model size).

The English summary is being prepared. Showing the original description.

Inspect a MIKE+ .sqlite model via the mike-plus MCP server — active simulation/scenario/model type, unit system, the list of simulation setups and scenarios, element counts — and switch the active scenario. Use when an agent needs to understand a MIKE+ model before running or editing it, or must run a scenario prepared in the GUI. Requires MIKE+ installed + a license.

The English summary is being prepared. Showing the original description.

Read and modify MIKE+ model parameters via the mike-plus MCP server — inspect or change values in any model table (pipe Diameter/Manning in msm_Link, node levels in msm_Node, catchment properties in msm_Catchment, etc.). Use when an agent must identify a current parameter and change it before re-running. Requires MIKE+ + license; mutating tools must run on a copy.

The English summary is being prepared. Showing the original description.

Compare two MIKE+ runs via the mike-plus MCP server — baseline vs scenario, before vs after a parameter edit — to say WHERE a change mattered and BY HOW MUCH (delta peak, delta volume, timing shift, RMSE/NSE) and to draw the overlay hydrograph. Use whenever two .res1d files of the same model exist or a re-run just finished. Comparing needs no license; producing the second run does.

The English summary is being prepared. Showing the original description.

Read MIKE+ .res1d results via the mike-plus MCP server — list contents, summarize peaks, extract a single time series, or check which nodes flood (peak water level vs ground level). Use when an agent needs to inspect or pull numbers from MIKE+ network results (node water levels, link/reach discharge, velocities, flooding). No MIKE+ license or installation required.

The English summary is being prepared. Showing the original description.

Generates a BACKPRESSURE.md file for any project. Analyzes codebase and PRD to produce deterministic self-verification checks that AI coding agents run on their own output.

The English summary is being prepared. Showing the original description.

Connect your AI agent to the A4A end-to-end encrypted agent-to-agent messaging network via local MCP tools or Python SDK.

The English summary is being prepared. Showing the original description.

Operational guide for the Schedule Anything SaaS surface — the 3-plugin WordPress stack (base + Pro + schedule-anything-platform) and its tenant SPA, the mcp-ai-pro/v1 presets/toolkits/sa-tools REST contract (Proposal 081), the WP 6.9 nonce cookie-auth pitfall and its fix pattern, the sa-e2e Docker harness quirks, the SPA↔REST contract-alignment rules, the Cloudways Velocity deploy + mirror-sync loop for both Velocity apps (schedule-anything + Complete Console on console.nvoos.cloud), and the Complete-bundle zip build/verify/staleness loop. Use when working on the Schedule Anything SPA or platform plugin, debugging its REST/auth surface, rebuilding its E2E stack, deploying or syncing a Velocity app, extending presets/toolkits, or diagnosing a 404 on a new SPA-consumed route (e.g. sa-tools), or a Velocity console that fails the nonce check with 'expected JSON but got text/html' (Cloudways Anti-Bot Protection / Imunify360 WebShield on the WP target's server).

The English summary is being prepared. Showing the original description.

Build high-impact, animated GitHub profile READMEs that play like mini-movies using pure SVG, CSS, and SMIL animations. Covers dark/light theme switching, swinging lanyard ID badges, tech orbits, loca

The English summary is being prepared. Showing the original description.

Install, check and restyle the agy-powerline statusline for Antigravity CLI (agy): quotas, model, context window and git on agy's status bar.

The English summary is being prepared. Showing the original description.

Sentryのイシューを調査して修正する。リンク・ID・検索でイシューを 特定し、スタックトレース・ブレッドクラム・トレース・ログの全コンテキストを 取得し、根本原因を特定して修正・解決する。

The English summary is being prepared. Showing the original description.

Open-format data ingestion for NV oOS Pro toolkits — the reusable pattern behind the F&B data-ingestion track (Proposal 078). Covers structural (header) matching over filename mapping, the configurable table_map + header-matcher + name-guess resolution order and the slug-first regression, the multi-format loader (CSV/TSV/JSON/JSONL/XLSX/ODS/PDF/photo), the Observation + terminology-map layer (vitals/FHIR analogue) with raw preservation, dedupe/retention/out-of-band banding, complete-by-default/resumable (offset) imports, and the read-only ingest-review dashboard anatomy (edit_posts review vs manage_options write, dry-run-first). Use when adding or extending data ingestion to a toolkit, ingesting heterogeneous owner files, wiring XLSX/PDF/photo imports, building an ingest/review dashboard, or debugging partial/truncated imports.

The English summary is being prepared. Showing the original description.

Rework an existing NV oOS Pro toolkit from a single-tenant demo into a universal product — currency-neutral schema with legacy aliases, a Tenant Profile + token renderer shared across the two assistant-delivery surfaces (packs via Portability vs blueprints via Blueprint Installer), demo-mode inversion, a universal single-folder ingestor (header-alias dictionary + dry_run + JSON), report export to CSV/PDF (DomPDF vs html_to_pdf choice), the add-a-tool drift checklist (TOOLS_LIST, coverage manifest, admin tool list, presets), and the re-seed-on-settings-save gotcha. Use when asked to 'universalise', 'de-demo', 'multi-tenant', 're-tenant', 'remove LKR/Surf Club', 'point the toolkit at a single Drive folder', 'export reports as CSV/PDF', or 'avoid re-installing assistants on save'. First case study: food-beverage (F&B Management, 2026-10-16). Complements mcp-ai-wpoos-toolkit-creation (build new) and mcp-ai-wpoos-toolkit-audit (harden existing).

The English summary is being prepared. Showing the original description.

Operational guide for the NV oOS Dictation desktop companion app (Tauri v2 + Rust, examples/nvoos-dictate) — build/run on Windows/MSVC, the local-first engine track (parakeet/whisper/fastconformer/moonshine/silero-vad), the embedded remote-STT fallback, the Stage-2 polish provider track (disabled/openai_compat/nvoos plus local LM Studio and Ollama), the file/media decode seam (Symphonia 0.5), the live camera + local object-detection/tracking track (Proposals 073 + 075) with an opt-in VLM label-polish layer (Proposal 076), the CDP browser-control agent (feature agent) + FastConformer engine + NV oOS multi-SPA hub, model registry + verification harnesses, the plugins.updater boot-crash config rule, and the full test/clippy gate matrix. Use when building, extending, or debugging the dictation app, adding an engine/model, a polish provider, the browser agent, file/video transcription, camera/vision detection, or VLM relabeling.

The English summary is being prepared. Showing the original description.

Enumerate the active Spring Voyage `area:*` taxonomy and the owning umbrella for each. Codex equivalent of the Claude /areas command.

The English summary is being prepared. Showing the original description.

Triage an issue — decide whether to close, route to an active-plan area, or park. Codex equivalent of the Claude /triage command.

The English summary is being prepared. Showing the original description.

Run every lint-class CI gate locally. Codex equivalent of the Claude /lint command.

The English summary is being prepared. Showing the original description.

Draft or refresh the human-written release notes for a version in `docs/releases/`. Codex equivalent of the Claude /release-notes command.

The English summary is being prepared. Showing the original description.

Start the Spring.Web (portal) dev server. Codex equivalent of the Claude /web command.

The English summary is being prepared. Showing the original description.