Software Development AI Skills

Drupal debugging techniques — Devel module, Drush watchdog, Twig debug, XDebug, error logging, and common troubleshooting patterns.

Use when you need to add, remove, edit, list, or change the boot default of an nvpmodel power mode on a Jetson/Tegra (Orin, Thor) target. Triggers: edit power mode, tune frequency caps.

Perform code review with actionable feedback and suggestions.

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building…

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis…

Write correct Sarvam text translation code (sarvam-translate:v1, mayura:v1) — mode/script/numeral options and silent parameter failures. Use this skill when building text translation or localization…

Establishes idempotency, self-containment, immutable artifacts, self-healing, zero-downtime, and zero-knowledge security for CI/CD pipelines, including delivery-strategy choice, evidence-gated…

Map opportunities using Teresa Torres' Opportunity Solution Trees. Use when asked to identify opportunities, find product gaps, explore new areas, map the solution space, or connect business outcomes…

One MCP, 30+ image and video models. Use this skill when the user wants to generate images or videos via Higgsfield (Seedance 2.0, Sora 2, Veo, Kling, Nano Banana Pro, GPT Image 2, Flux, Hailuo, Soul,…

Runs autonomous loop fetching stories from GitHub Issues. Implements and closes issues as done. Triggers on "loop through my PRDs", "work on my issues", "start the autonomous loop", "implement my…

Design REST/GraphQL APIs, module interfaces, and type contracts when creating endpoints or changing public boundaries.

AI/ML supply chain attacks — model poisoning, Pickle RCE, Hugging Face / Ollama registry compromise, LangChain plugin backdoors, OpenClaw / ClawHub ecosystem threats. Distinguishes from…

Catalyst serverless functions — all 7 types (Basic I/O, Advanced I/O, Event, Cron, Job, Integration, Browser Logic), handler signatures, catalyst-config.json, Security Rules, API Gateway routing, file…

Design and author Hermes Workflows with typed inputs/outputs, agent/bash/ask/parallel/pipeline/goal primitives, Review Queue gates, artifacts, and verification receipts. Use when creating or modifying…

Expert guidance for designing LangGraph state machines and multi-agent workflows. Use when building workflows, connecting agents, or implementing complex control flow in LangConfig.

Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js…

This skill should be used when the user asks to "plan chunks", "break this down", "plan the implementation", or when a story has status planning and needs implementation details before building.…

Turns a raw Qualtrics conjoint export into analysis-ready long-format data: implementation identification, reshaping, choice-profile alignment, reference categories, and pilot exclusion. Use when a…

Analyze upstream specs (agentskills.io, Claude Code plugin/marketplace format, OpenAI Codex plugins/marketplace, OpenClaw, MCP and MCP Registry, CodeRabbit, APM) for changes, identify gaps in…

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill. For evaluating, benchmarking, or optimizing an…

Turn a conference attendee or speaker list plus the user's goals into a working conference plan — a tiered, prioritized target list with why-them one-liners, pre-conference outreach drafts, per-day…

Opt-in recreation of the Bun + TypeScript framework used to build Vapi's landing-page voice agents from a ROUGH_DRAFT.md spec, including a scenario registry, language stacks, prompt composer,…

Create and push reusable skills to SkillNote when repeated instructions are detected or user says "create a skill", "save this pattern", "push a skill". Guides drafting, review, collection selection,…

Use when implementing any feature or bugfix, before writing implementation code

Use when an app's layout must adapt to a window that changes size while the app runs, or when an app must support more than one window. That includes being asked to make an app resizable or support a…

harness 路径约定：`{HARNESS_DIR}`/`{PLAN_DIR}`/`{SDD_DIR}`/`{ITERATION_DIR}`/`{KNOWLEDGE_DIR}`/`{SPECS_DIR}`/`{REVIEW_DIR}` 等符号的发现与初始化、docs 与 harness 子树边界、Spec 分支模型。读写 `.mstar/` 或开 plan 前必读。

Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports.

Document exported Nim modules and APIs with doc comments that `nim doc` actually picks up, including module docs, proc and type docs, field docs, and runnable examples. Use when writing documentation…

Search Cloudflare documentation and get migration guides via CLI. Use when user needs to look up Workers, Pages, R2, D1, KV, Zero Trust, CDN, DNS, or any Cloudflare product/feature documentation.

Use when writing, refactoring, or debugging Lean proofs and you need a stable translation from mathematical reasoning into explicit tactics, controlled rewriting, or maintainable proof structure.

Découper un PRD en phases indépendamment livrables par tranches verticales (tracer bullets), puis produire ou étendre `docs/PLAN.md` selon un template fixe (décisions architecturales + phases avec…

Use this skill when a Biome change may affect users and you must decide whether it needs a changeset, choose the release level, or create and edit `.changeset/*.md` release-note text. Do not use for…

Design-to-code visual restoration loop: diffs the running page against a Figma link or baseline image via real screenshots (DOM geometry + pixel diff/heatmap + zoomed inspection), drives tiered fix…

High-precision semantic search and content retrieval via Exa API. Use when: (1) Deep research requiring semantic understanding, (2) Code documentation and examples lookup, (3) Company/professional…

Reconstruct what a Claude Code or Codex agent actually did during one exact session, including goals, decisions, actions, file and git changes, tests, failures, recoveries, final state, and open work.…

Turn a completed BioDSH task, or an existing analysis procedure someone else wrote (script, notebook, Snakefile/Nextflow, methods text), into a reproducible, re-runnable workflow through a guided plan…

Convert stored Tapestry artifacts into higher-level synthesis. Use when a user wants interpretation, consolidation, research notes, or analysis built on top of an already-ingested URL or note.

Opens the running app in a browser and verifies recent UI changes actually work. Use whenever the user wants a quick smoke test or sanity check of recent work, or says "go", "open in browser", "check…

Enforces which Dart 3 construct each declaration earns — sealed class + exhaustive switch with no `default:`/`case _:`, the three class modifiers (`sealed`/`final`/`abstract interface class`) and skip…

查询e互动。接口：GET /api/v2/market/data/ashare-interactions。所有请求必须设置 FTSHARE_API_KEY。

Search DrugBank comprehensive drug database with natural language queries. Drug mechanisms, interactions, and safety data powered by Valyu.

Design or refine springs, gestures, and interruptible motion when physical continuity or direct manipulation matters.

Coordinate parallel work in Jujutsu workspaces: choose jj or a git-worktree fallback, split reviewable slices, create and dispatch isolated workspaces, monitor safely, and integrate. Use when planning…

Record a Chrome browser tab to video via CLI. Use when the user wants to capture a screen recording of a browser tab. Supports list, start, stop, caption, and status subcommands. No debug mode…

Profile, diagnose, and optimize C++ performance bottlenecks with measurable evidence. Use when analyzing CPU/memory hotspots, benchmarking before/after changes, triaging regressions from benchmark…

Look up World of Warcraft UI escape sequences — pipe-character sequences embedded in text strings to produce colors, inline textures, atlas icons, grammar inflections, word-wrap hints, Kstrings, and…

Use when a backpressured code-review subagent is judging whether a diff uses the type system to make illegal states unrepresentable — i.e. the diff touches data models, function signatures, or domain…

Handle PR review feedback - understand reviewer comments, research their concerns, and help the user address them. The LLM explains what reviewers want and why; the user decides how to respond and…

Expert guidance on Swift Concurrency best practices, patterns, and implementation. Use when developers mention: (1) Swift Concurrency, async/await, actors, or tasks, (2) modern concurrency patterns or…

Generate project documentation from an existing codebase. This documentation shall serve Agents and Humans. Creates a project overview, module documentation, and feature documentation with explicit…

Review Odoo addon code for correctness, security, performance, migrations, tests, and official Odoo coding guidelines. Use when reviewing Odoo modules, diffs, pull requests, or changed files involving…