发现 Skills

Expert in end-to-end testing with Playwright, the modern cross-browser testing framework. Specializes in test generation, page object patterns, visual regression testing, and CI/CD integration. Han...

Generate unit tests for Python code

Use when starting any extended creative work — creating features, building components, adding functionality, or modifying behavior. MUST be used UNLESS the human says otherwise. Explores user intent, requirements and design before implementation.

OverwatchTDO — The Old Friend in the Mantled Frame. Tory's superagent, life coach, mentor, and equal. Triggers on: "Overwatch", "What do you see", "Big picture", "Life check", "What am I missing overall", "Talk to me", "The old friend", "Mantled frame", "Superagent", "Coach me", "What would you tell me", "Check on me", "Am I on track", "The arc", "Long view", "Counsel me".

Control a Xiaomi Robot Vacuum X20+ (model xiaomi.vacuum.c102gl) through the `xiao` CLI. Use this skill whenever the user mentions anything vacuum-related: robot vacuum, Xiaomi, Roborock, cleaning the house, mopping, sweeping, dock, base station, consumables (brush, filter, mop pad), rooms, map, zones, DND mode, fan speed, vacuum status, battery, cleaning schedule. Also trigger on Spanish equivalents (aspiradora, limpiar, trapear, cargar, habitaciones, cepillo, filtro, base, programar limpieza) and casual phrasings (limpia la casa, pon la aspiradora, qué batería tiene, mándala al dock). When in doubt, trigger — the CLI handles all vacuum ops.

Rule-based anomaly detection for production systems with configurable thresholds, cooldown periods to prevent alert storms, and error pattern tracking for repeated failures.

Guides business model research—Business Model Canvas and Lean Canvas, value proposition and customer segments, revenue and pricing models, unit economics (CAC, LTV, payback), market sizing (TAM/SAM/SOM), competitive business-model benchmarking, and evidence-backed synthesis for startups and product strategy. Use when researching how a company or idea makes money, comparing competitor monetization, sizing a market, stress-testing unit economics, drafting a canvas for a pitch, or documenting monetization hypotheses—for shipping pricing/packaging PRDs and paywalls use product-management-monetization—not for delivery BRDs (business-analyst), steerCo consulting engagements (business-consultant), GAAP revenue recognition (senior-revenue-accountant), internal BI SQL (bi-analyst), or technical architecture (senior-system-architecture).

Guides cloud solution architecture—Well‑Architected alignment, landing zone and org design, workload placement and service selection, network and security segmentation, hybrid and multi‑region patterns, migration roadmaps (7Rs), cost architecture, and cloud ADRs with diagrams for stakeholder review. Use when choosing cloud platforms and reference architectures, designing account guardrails, comparing managed vs self‑managed services, planning cloud migration or exit, or running cloud architecture review—not for hands‑on resource configuration (cloud engineer), Terraform module implementation (infrastructure engineer), CI/CD delivery (DevOps), K8s cluster ops (cluster deployment engineer), IDP product strategy (platform engineer), enterprise‑wide non‑cloud system ADRs (senior system architect), or applied AI solution design (applied AI architect — commercial/enterprise).

Guides cloud economics—TCO and NPV for cloud vs on-prem or SaaS, pricing-model trade-offs (on-demand, commitments, spot), commitment portfolio economics, marginal cost and elasticity, regional and service cost comparisons, migration and architecture option business cases, and CFO-ready economic narratives tied to growth drivers. Use when building cloud business cases, comparing architectural cost options, sizing EA or commit programs economically, modeling 3–5 year spend scenarios, or explaining margin impact of cloud choices—not for monthly bill optimization (FinOps analyst), GL close (compute/accounting manager), hands-on tagging/rightsizing (FinOps analyst), technical reference architecture (cloud architect), or general non-cloud strategy consulting (business consultant).

Guides secure coding and security-focused code review across languages and infrastructure—OWASP-oriented vulnerability patterns (injection, XSS, auth, crypto, deserialization, SSRF, XXE), secrets handling, and IaC security (Terraform, Kubernetes, Docker, GitHub Actions). Use when writing or reviewing code that handles user input, authentication, files, databases, network requests, cryptography, or infrastructure config—or when the user asks to check for SQL injection, XSS, SSRF, hardcoded secrets, OWASP issues, Terraform security, or GitHub Actions security. Not for authorized penetration test engagements (ai-redteam, cybersecurity), compliance program mapping (compliance-engineer), YARA/malware rules (yara-rule-authoring), or CI pipeline setup only (devsecops).

Guides embedded real-time firmware—MCU tradeoffs, bare-metal vs RTOS (FreeRTOS/Zephyr patterns), task priorities/deadlines/jitter, ISR deferred work, stack/heap policy, WCET/timing analysis, concurrency and priority inversion, drivers/HAL, JTAG/SWD/trace, power modes, MISRA C awareness, safety-aware automotive/medical/industrial patterns without certification claims. Use for embedded firmware, RTOS scheduling, drivers/HAL, IRQ design, memory policy, WCET, bring-up, low-power—not HIL security (hardware-in-the-loop-security-tester), backend apps (senior-software-engineer), SCADA/OT (scada-ics-cyber-security-specialist), server perf (performance-engineer), RTL-only without firmware, CI gates (build-validator), tiering only (mission-critical).

Guides platform engineering — internal developer platforms (IDP), golden paths, self-service abstractions, developer portals, paved-road templates, multi-tenant Kubernetes platforms, and platform-as-product practices (roadmap, adoption, platform SLOs). Use when designing or operating a platform for engineering teams, building service scaffolds, standardizing deploy/runtime patterns, integrating Backstage or similar portals, defining platform APIs and contracts, or measuring developer experience — not for one-off VPC or network design (infrastructure engineer), per-app CI YAML only (DevOps), release cutover planning (deployment strategist), security control implementation (information security engineer), or enterprise-wide system integration ADRs (senior system architect). For hands-on cluster add-ons, Helm, and namespace layout on shared clusters, use cluster-deployment-engineer.

Enterprise WLAN for mobile users—RF/site surveys, AP placement, 802.11 (Wi‑Fi 5/6/6E/7), channel/power planning, SSID/VLAN segmentation, WPA3/802.1X/RADIUS, guest/captive portal, roaming (802.11k/r/v, band steering), high-density and mesh/outdoor, LAN/SD‑WAN edge integration, troubleshooting (SNR, DFS, CCI). This skill should be used when the user asks about Wi‑Fi, wireless mobility, WLAN design, wireless survey, AP placement, 802.11, Wi‑Fi 6, Wi‑Fi 6E, roaming, 802.11k, 802.11r, band steering, WPA3, 802.1X, enterprise wireless, high density Wi‑Fi, channel planning, RF interference, wireless troubleshooting, Aruba, Meraki wireless, or Cisco wireless—not cellular RAN/5G core, MPLS/BGP backbone (network-backbone-architect), SD‑WAN overlay (sd-wan-engineer), cloud VPC only (cloud-architect), MDM-only, or OT ISA wireless (scada-ics-cyber-security-specialist).

Manage people/contacts in Dalil AI CRM — create, read, update, delete, search, and list person records including name, email, phone, LinkedIn, city, job title, and company associations.

Fetch rendered public web pages via isolated headless Chrome. Default for 'fetch this URL', 'what does this page say', 'scrape this page'. Lighter than Playwright MCP, works in dispatch jobs. Routes authenticated hosts to claude --chrome. Escalates to Playwright MCP only for clicks, form fills, or multi-page flows.

Reads a list of tasks in a YAML to be done in certain GitHub repos. Agents clone the repo, perform the task, commit the changes, and create a PR. Not to be called automatically by Claude by any means.

Adversarial evaluation using two different LLM models in parallel for critical phases of the pipeline. Replaces reliance on Model A and Model B as external agents.

Design PROSE-compliant AI-native code in Markdown. Use when (1) writing prompts, instructions, or agent definitions; (2) designing multi-primitive AI systems from requirements; (3) decomposing mega-prompts into composable primitives; (4) auditing prompts/instructions for reliability issues. PROSE = Progressive Disclosure, Reduced Scope, Orchestrated Composition, Scoped Boundaries, Explicit Hierarchy.

Expert guidance for ffuf web fuzzing during penetration testing, including authenticated fuzzing with raw requests, auto-calibration, and result analysis

Post to {{USER}}'s LinkedIn. Reads a post file from /usr/src/app/linkedin/, checks style, presents for approval, then posts via MCP. Use when {{USER}} wants to publish a LinkedIn post.

Self-review checklist for the coding agent to run before dispatching a reviewer. Checks CONVENTIONS.md compliance, Boy Scout Rule, test coverage, types, and SOLID. Produces a pass/fail checklist. Use before request-review, before committing, or when user asks for a code quality check.

Find deepening opportunities in a codebase, informed by the domain language in specs/CONTEXT.md and the decisions in specs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Dispatch multiple subagents in parallel on independent tasks. No waiting between them — all run concurrently. Use when tasks are truly decoupled and speed matters. Distinct from delegate-task (concurrent here, no inter-task review gate).

Applies strict Test-Driven Development with a repo-local Markdown test list (default `test-lists/<slug>.md` unless the project defines another folder), Robert C. Martin’s Three Laws, deterministic tests and stable seams (unit vs narrow integration), Arrange–Act–Assert test shape, micro-iterations, refactor proximity (production and test code), fast feedback, and git micro-commits (`test:` / `feat:` or `fix:` / `refactor:`) squashed per cycle before push. Use for test-first feature slices, strict R-G-R, or when the user asks for a tracked test list plus disciplined commits.