dtsong
121 verified skills484 total stars
rag-architecture
Use when designing a Retrieval-Augmented Generation pipeline. Covers document processing, chunking strategy, embedding pipeline, vector database selection, retrieval optimization, and context assembly. Do not use for prompt design (use prompt-engineering) or evaluation framework design (use ai-evaluation).
development4
motion-design
Use when designing the motion language for a feature or system. Covers transition specs, micro-interaction definitions, choreography principles, performance constraints, and reduced-motion alternatives. Do not use for visual design critique (use visual-audit) or design token architecture (use design-system-architecture).
testing4
GitHub PR Update
Update PR branch with latest changes from base branch
testing4
a11y-audit
Use when auditing accessibility compliance of a feature or codebase. Covers WCAG 2.2 AA conformance, screen reader compatibility, keyboard navigation, focus management, color contrast, reduced motion, and ARIA usage. Do not use for general UX review (use journey-mapping) or component interaction specs (use interaction-design).
development4
ai-evaluation
Use when designing an evaluation framework for AI/LLM features. Covers golden dataset creation, automated scoring rubrics, hallucination detection, regression testing infrastructure, and production monitoring. Do not use for prompt design (use prompt-engineering) or RAG pipeline architecture (use rag-architecture).
development4
analytics-design
Use when planning measurement strategy for a feature or product area. Covers metrics hierarchy design, event taxonomy, funnel instrumentation, A/B test framework, and data pipeline planning. Do not use for feature prioritization scoring (use impact-estimation) or MVP scope definition (use mvp-scoping).
development4
audit-trail-design
Use when designing audit logging systems for accountability and compliance evidence. Covers event catalogs, log schemas, retention policies, immutability requirements, and compliance reporting. Do not use for regulatory gap analysis (use compliance-review) or data sensitivity classification (use data-classification).
testing4
Git Branch
Create new branches with naming conventions
tools4
changelog-design
Use when preparing release changelogs, migration guides, or breaking change communication for consumers. Covers change categorization, before/after documentation, migration step authoring, semver version strategy, and release communication planning. Do not use for documentation architecture planning (use documentation-plan) or recording architectural decisions (use adr-template).
development4
GitHub PR Request Review
Request reviewers for a pull request
tools4
competitive-analysis
Use when designing features that exist in competing products or analyzing prior art in the market. Covers feature mapping, UX evaluation, technical trade-off assessment, and differentiation opportunity identification. Do not use for evaluating individual libraries (use library-evaluation) or assessing technology maturity (use technology-radar).
development4
compliance-review
Use when reviewing proposed features and data flows against GDPR, CCPA, HIPAA, and other privacy regulations. Covers regulatory applicability, PII data flow mapping, consent mechanism assessment, retention policies, and right-to-deletion compliance. Do not use for data sensitivity tiering (use data-classification) or audit logging design (use audit-trail-design).
testing4
cost-analysis
Use when modeling infrastructure costs, projecting scaling expenses, or identifying optimization opportunities across cloud providers and third-party services. Covers per-unit cost estimation, growth milestone projections, and budget alerting setup. Do not use for deployment strategy design (use deployment-plan) or monitoring architecture (use observability-design).
devops4
data-classification
Use when classifying data elements by sensitivity tier and defining per-tier handling requirements. Covers data inventory, sensitivity classification, PII flow mapping, encryption and masking specifications, and cross-boundary transfer documentation. Do not use for regulatory gap analysis (use compliance-review) or audit logging design (use audit-trail-design).
testing4
Git Delete Branch
Delete local and remote branches with safety checks
testing4
deployment-plan
Use when designing deployment strategies including environment progression, CI/CD pipelines, zero-downtime releases, rollback procedures, and feature flag management. Covers blue-green, rolling, and canary deployment patterns with database migration coordination. Do not use for monitoring or alerting design (use observability-design) or infrastructure cost modeling (use cost-analysis).
testing4
design-system-architecture
Use when designing a token-based design system architecture. Covers primitive, semantic, and component token hierarchy, theming strategy for dark/light mode, and cross-platform implementation planning. Do not use for visual critique of existing interfaces (use visual-audit) or animation specifications (use motion-design).
testing4
device-integration
Use when designing integration strategies for device hardware APIs including camera, sensors, biometrics, and Bluetooth. Covers permission flows, cross-platform abstraction evaluation, fallback behavior, and power impact analysis. Do not use for platform guideline compliance (use platform-audit) or navigation architecture (use navigation-design).
development4
documentation-plan
Use when designing documentation architecture for a project or team. Covers audience mapping, Diataxis framework classification, onboarding path design, format and location decisions, documentation testing, and maintenance scheduling. Do not use for recording individual architecture decisions (use adr-template) or creating versioned changelogs (use changelog-design).
development4
finops-analysis
Use when analyzing cloud spending, cost attribution, or unit economics. Covers cost allocation tagging, reserved capacity planning, right-sizing, spot/preemptible usage, cost anomaly detection, and showback/chargeback models. Do not use for general infrastructure cost modeling (use cost-analysis) or deployment strategy (use deployment-plan).
testing4
generate-diagram
Use this skill when creating a methodology diagram from research text. Triggers on "make a diagram", "visualize this methodology", "diagram this process", or "generate a figure from this paper". Applies to methodology descriptions, process flows, and research paper sections. Do NOT use for scoring existing diagrams (use evaluate-diagram) or plotting data from CSV/JSON (use generate-plot).
data-ai4
GitHub Activity
Recent repository activity summary
tools4
GitHub Health
Repository health dashboard and status overview
tools4
GitHub PR Respond
View and respond to PR review comments
documentation4
Git Workflows
Local git operations for syncing, branching, merging, and conflict resolution
testing4
GitHub Workflow
GitHub interactions for issues, PRs, releases, and repository management
tools4
invariant-analysis
Use when enumerating security claims from a design, formalizing them as invariants, checking for hidden assumptions, and assessing verification feasibility. Covers safety invariants, temporal properties, and verification tool recommendations. Do not use for writing TLA+ specifications directly (use formal-spec) or implementation-level security review.
tools4
growth-engineering
Use when designing growth infrastructure including onboarding funnels, referral mechanics, A/B test instrumentation, and re-engagement loops. Covers activation metrics, funnel mapping, and experimentation design. Do not use for pricing or paywall architecture (use monetization-design) or product copy and naming (use messaging-strategy).
testing4
helm-generation
Use when creating Helm values.yaml files, converting docker-compose to Helm, or reviewing Helm configurations. Produces minimal-diff values that only override chart defaults. Triggers on 'helm values', 'create values.yaml', 'deploy to kubernetes'.
devops4
hw-security-signoff
Use when a hardware design needs security sign-off before tape-out. Defines the builder-to-auditor handoff contract between Foundry (constructive design) and Forge (security review). Covers security review prerequisites, artifact checklist, sign-off criteria, and conditional approval workflow. Do not use for RTL security review itself (use rtl-security-review) or design flow guidance (use foundry/chip-design-flow).
development4
hw-sw-boundary
Use when reviewing the hardware/software security interface to verify hardware security feature enablement, IOMMU/SMMU DMA protection configuration, and HW/SW trust model coherence. Covers boot chain verification, memory protection, and control flow integrity features. Do not use for kernel configuration audit (use kernel-hardening) or isolation boundary analysis (use isolation-review).
development4
i18n-review
Use when reviewing internationalization readiness of a feature or codebase. Covers locale strategy, RTL layout, string externalization, pluralization, date/number formatting, and cultural UX adaptation. Do not use for general accessibility audits (use interaction-design).
development4
impact-estimation
Use when comparing multiple features or initiatives to determine prioritization order. Covers RICE scoring with quantified reach, impact, confidence, and effort dimensions, tier ranking, and success metric definition. Do not use for MVP scope definition (use mvp-scoping) or analytics instrumentation planning (use analytics-design).
data-ai4
kernel-hardening
Use when auditing kernel security configuration for memory protection, syscall surface reduction, control flow integrity, and integrity mechanisms against local and remote attack vectors. Covers CIS/KSPP benchmarks, KASLR, SMAP/SMEP, seccomp, and secure boot chain. Do not use for isolation boundary analysis (use isolation-review) or HW/SW interface review (use hw-sw-boundary).
testing4
library-evaluation
Use when adding new packages, choosing between dependency alternatives, or auditing existing libraries. Covers popularity metrics, maintenance health, bundle impact, API quality, and license compatibility with weighted scoring. Do not use for evaluating frameworks or platforms (use technology-radar) or comparing competing products (use competitive-analysis).
development4
load-modeling
Use when planning capacity or projecting infrastructure needs under growth. Covers traffic modeling, endpoint heat maps, scaling triggers, benchmark design, and cost-at-scale estimates. Do not use for runtime bottleneck profiling (use performance-audit) or cache architecture design (use caching-strategy).
testing4
Git Merge Main
Merge main branch into current feature branch
data-ai4
messaging-strategy
Use when developing product messaging frameworks including value propositions, feature naming, microcopy guidelines, and CTA strategy. Covers voice and tone definition, conversion copy, and upgrade prompt language. Do not use for pricing architecture or paywall placement (use monetization-design) or onboarding funnels and referral systems (use growth-engineering).
development4
navigation-design
Use when designing navigation architecture for mobile or cross-platform features including screen hierarchy, deep linking schemes, and state preservation strategies. Covers stack navigation, modal flows, universal links, and process death recovery. Do not use for platform guideline compliance (use platform-audit) or hardware API integration (use device-integration).
development4
page-component-mapper
Use when investigating any frontend issue before diagnosis or debugging — maps a Next.js route to its full component tree. Resolves "what components render on this page," "show me the component tree for /dashboard," or "trace imports for this route." Produces a ComponentMap artifact with server/client boundaries, props, hooks, data fetching, and styling metadata consumed by all downstream QA skills. Not for diagnosing bugs, fixing code, or generating tests — those are handled by specialist skills after mapping is complete.
tools4
performance-audit
Use when profiling application performance or diagnosing slow page loads. Covers full-stack bottleneck identification including Core Web Vitals, bundle analysis, database queries, and network waterfall. Do not use for cache architecture design (use caching-strategy) or capacity planning (use load-modeling).
development4
pipeline-design
Use when designing data pipelines for moving, transforming, and delivering data. Covers ETL vs ELT pattern selection, orchestration tool choice, batch vs streaming trade-offs, idempotency guarantees, data quality checkpoints, and lineage tracking. Do not use for schema modeling (use schema-evaluation) or ML workflows (use ml-workflow).
tools4
pqc-readiness
Use when assessing a system's readiness for post-quantum cryptography migration, inventorying classical crypto usage, mapping NIST-standardized PQC replacements, and planning phased migration timelines. Covers key exchange, digital signatures, and hybrid mode needs. Do not use for classical crypto implementation review (use crypto-review) or protocol state machine analysis (use protocol-analysis).
research4
prompt-engineering
Use when designing, evaluating, or versioning system prompts for LLM-powered features. Covers instruction structure, chain-of-thought patterns, output format constraints, few-shot example selection, and prompt versioning strategy. Do not use for RAG pipeline design (use rag-architecture) or AI evaluation frameworks (use ai-evaluation).
development4
python-data-engineering
Use this skill when writing Python code for data pipelines or transformations. Covers Polars, Pandas, PySpark DataFrames, dbt Python models, API extraction scripts, and data validation with Pydantic or Pandera. Common phrases: "Polars vs Pandas", "PySpark DataFrame", "validate this data", "Python extraction script". Do NOT use for SQL-based dbt models (use dbt-transforms) or integration architecture (use data-integration).
development4
qa-coordinator
Use when a user reports a frontend bug, visual defect, or unexpected behavior in a Next.js/TypeScript application. Orchestrates a multi-phase QA pipeline — component mapping, diagnosis, fix, and regression testing — by classifying symptoms and dispatching to the appropriate specialist skill. Does not perform diagnosis or fixes directly; delegates all domain work to specialists. Not for backend-only issues, infrastructure problems, or build/deployment failures.
development4
Git Rebase
Rebase current branch onto main with guidance
data-ai4
regression-test-generator
Use when a verified fix needs a regression test — "write a test for this fix," "generate regression test," or "add test coverage for this bug." Auto-detects project test conventions, routes to Vitest+RTL or Playwright based on component type (sync vs async server), generates targeted tests with anti-brittleness constraints, and annotates coverage boundaries. Not for diagnosing bugs, applying fixes, or writing feature tests — use ui-bug-investigator, component-fix-and-verify, or manual test authoring respectively.
testing4
schema-design
Use when designing or modifying database schemas with migration plans. Covers entity definition, relationship mapping, normalization trade-offs, indexing strategies, and RLS policies. Do not use for API endpoint contracts (use api-design) or codebase analysis (use codebase-context).
development4
SUITE_NAME
TRIGGER_DESCRIPTION. Use when USER_CONTEXT. Routes to specialists for CAPABILITIES.
testing4
soc-integration
Use when planning SoC integration including bus fabric architecture, memory map allocation, IP qualification, interrupt routing, and design-for-test strategy. Covers AMBA/AXI protocols, register map design, DFT insertion, and production test planning. Do not use for RTL design flow (use chip-design-flow) or block-level verification (use verification-methodology).
testing4
Git Squash
Squash commits non-interactively for cleaner history
tools4
Git Switch
Switch branches safely with uncommitted change handling
tools4
technology-radar
Use when evaluating frameworks, tools, or platforms for adoption, migration, or stack decisions. Covers maturity assessment, ecosystem health, team readiness, migration cost, and long-term viability with radar quadrant placement. Do not use for comparing individual libraries (use library-evaluation) or analyzing competing products (use competitive-analysis).
tools4
testing-strategy
Use when designing test plans for new features or improving existing test coverage. Covers test pyramid design, coverage targets, quality gates, and test file specifications. Do not use for codebase pattern audits or convention enforcement (use pattern-analysis).
development4
threat-model
Use when applying STRIDE threat modeling to identify security risks in proposed features. Covers trust boundary mapping, data flow analysis, threat rating, mitigation proposals, and residual risk documentation. Do not use for failure scenario discovery (use failure-mode-analysis) or boundary value testing (use edge-case-enumeration).
development4
ui-bug-investigator
Use when a user reports a non-CSS UI bug in a Next.js App Router application — "blank page," "data not loading," "click does nothing," "hydration mismatch," "flicker on navigation," or "state not updating." Runs symptom-targeted diagnostic checks against a component map to identify rendering, state, event handling, and data flow issues. Not for CSS layout, styling, or visual design problems — route those to css-layout-debugger.
tools4
visual-audit
Use when performing structured visual design critique of an interface. Covers hierarchy, contrast, spacing, typography, color, and component consistency with actionable fix recommendations. Do not use for design token architecture (use design-system-architecture) or animation specifications (use motion-design).
testing4
caching-strategy
Use when designing or auditing a caching architecture. Covers multi-layer cache hierarchy, key schema, TTL policies, invalidation flows, and warming strategies. Do not use for runtime performance profiling (use performance-audit) or capacity planning (use load-modeling).
testing4
GitHub PR Status
Check PR status, CI results, and merge readiness
testing4
codebase-context
Use when analyzing an existing codebase for architecture, tech stack, conventions, and infrastructure. Covers project structure mapping, data model discovery, integration point cataloging, and constraint identification. Do not use for schema changes (use schema-design) or API contract definition (use api-design).
development4
distributed-patterns
Use when designing distributed systems or evaluating distributed architecture patterns. Covers CAP theorem trade-offs, consensus protocols (Raft, Paxos), saga orchestration, CRDTs, event sourcing, partition handling, distributed transactions, and failure detectors. Do not use for general API design (use api-design) or database schema design (use schema-design).
development4
interaction-design
Use when designing component interaction specs with visual states, transitions, and accessibility requirements. Covers state matrices, responsive behavior, ARIA compliance, and content constraints. Do not use for multi-step user journey mapping (use journey-mapping).
data-ai4
SPECIALIST_NAME
SPECIALIST_TRIGGER. Use when SPECIALIST_CONTEXT.
testing4
journey-mapping
Use when mapping complete user journeys through multi-step flows, onboarding sequences, or feature workflows. Covers entry points, happy paths, alternate paths, error states, friction analysis, and delight opportunities. Do not use for individual component interaction specs (use interaction-design).
content-media4
GitHub Triage
Batch label and prioritize GitHub issues
tools4
GitHub Release
Create a GitHub release with changelog
documentation4
Git Push
Push commits to remote with upstream handling
tools4
Git Sync
Fetch and show remote changes without modifying local branch
tools4
Git Pull
Pull remote changes with merge or rebase strategy
tools4
css-layout-debugger
Use when a user reports CSS, layout, or styling issues in a Next.js application — "element overlapping," "spacing is wrong," "responsive layout broken," "dark mode not working," "Tailwind classes not applying," or "alignment off." Diagnoses through a 6-phase pipeline that mirrors browser evaluation order, covering token resolution, cascade conflicts, layout models, stacking contexts, and viewport responsiveness. Handles Tailwind, CSS Modules, styled-components, and vanilla CSS. Not for JavaScript logic bugs, data fetching issues, or server-side rendering errors — route those to ui-bug-investigator.
development4
git-status
Quick git queries - status, diff, log, blame. Triggers on "git status", "what changed", "show diff", "recent commits".
tools4
isolation-review
Use when mapping isolation boundaries, enumerating crossing points, verifying enforcement mechanisms, and testing for bypass paths across trust domains. Covers containers, VMs, enclaves, namespaces, seccomp, and network segmentation. Do not use for kernel configuration audit (use kernel-hardening) or HW/SW security interface review (use hw-sw-boundary).
development4
platform-audit
Use when auditing a feature or implementation against platform-specific guidelines such as iOS HIG, Material Design 3, and WCAG. Covers compliance scoring, violation identification, remediation steps, and App Store risk assessment. Do not use for navigation architecture (use navigation-design) or hardware API integration (use device-integration).
development4
microarch-analysis
Use when analyzing microarchitectural attack surfaces by mapping shared hardware structures, identifying speculative execution vectors, quantifying speculative windows, and proposing countermeasures. Covers cache timing, transient execution, and contention channels. Do not use for RTL-level design review (use rtl-security-review) or physical implementation analysis (use physical-design-security).
testing4
rtl-security-review
Use when reviewing RTL designs for security vulnerabilities including access control gate bypasses, insecure FSM transitions, timing-dependent information leakage, and unintended data paths. Covers Verilog, SystemVerilog, and VHDL modules with security-critical functions. Do not use for physical implementation review (use physical-design-security) or microarchitectural attack analysis (use microarch-analysis).
development4
protocol-analysis
Use when analyzing cryptographic protocol security by modeling state machines, enumerating transitions, and identifying desynchronization, replay, downgrade, and session binding vulnerabilities. Covers protocol handshakes, session management, and negotiation integrity. Do not use for implementation-level crypto review (use crypto-review) or post-quantum assessment (use pqc-readiness).
development4
adr-template
Use when recording significant architectural or design decisions that affect the system. Covers decision framing, context documentation, options analysis with tradeoff evaluation, consequence mapping, and review trigger definition. Do not use for documentation strategy planning (use documentation-plan) or release changelog creation (use changelog-design).
testing4
web-security-hardening
Security audit checklist for web applications. Use when reviewing, auditing, or hardening a web app's security posture. Covers rate limiting, auth headers, IP blocking, CORS, security middleware, input validation, file upload limits, ORM usage, and password hashing. Triggers on requests like "review security", "harden this app", "security audit", "check for vulnerabilities", or when building/reviewing API endpoints.
development4
Prompt Wizard
Interactive wizard to craft effective prompts using Claude Code best practices
development4
chip-design-flow
Use when guiding RTL-to-GDSII chip design flow including RTL coding style, synthesis constraints, place-and-route strategy, timing closure, and tape-out checklist. Do not use for verification methodology (use verification-methodology) or SoC integration (use soc-integration).
testing4
cicd-generation
Use when creating GitHub Actions workflows, adding CI/CD to a project, or reviewing pipeline security. Produces fail-fast, security-hardened workflows with OIDC auth and SHA-pinned actions. Triggers on 'add CI', 'create workflow', 'github actions'.
testing4
code-search
Fast codebase searches using grep/glob. Triggers on "find", "search", "where is", "grep for".
development4
api-design
Use when designing REST or RPC endpoint contracts with request/response types and error handling. Covers endpoint specification, TypeScript type definitions, authentication requirements, pagination, and caching strategies. Do not use for database schema changes (use schema-design) or codebase analysis (use codebase-context).
development4
pattern-analysis
Use when auditing codebase patterns or evaluating proposed changes for convention consistency. Covers file naming, component patterns, data fetching, state management, and type conventions. Do not use for test plan design or coverage targets (use testing-strategy).
development4
crypto-review
Use when reviewing cryptographic implementations for algorithm choice correctness, key management soundness, side-channel resistance, and crypto agility readiness. Covers symmetric and asymmetric operations, key lifecycle, and construction safety. Do not use for protocol-level analysis (use protocol-analysis) or post-quantum migration planning (use pqc-readiness).
development4
e2e-testing
Use when designing end-to-end test suites, visual regression testing, or cross-browser test strategies. Covers Playwright/Cypress test architecture, page object patterns, test data management, visual snapshot comparison, cross-browser matrix, and CI integration. Do not use for unit/integration test strategy (use testing-strategy) or code pattern audit (use pattern-analysis).
development4
verilator-simulation
Use when planning or reviewing Verilator-based simulation workflows for SystemVerilog designs. Covers lint analysis, simulation setup, trace/waveform debugging, coverage-driven verification, and C++ co-simulation. Do not use for commercial EDA tools (use verification-methodology) or RTL design flow (use chip-design-flow).
tools4
monetization-design
Use when designing monetization architecture including pricing tiers, paywall placement, subscription infrastructure, and upgrade flows. Covers freemium models, billing integration, and retention mechanics. Do not use for product copy or naming conventions (use messaging-strategy) or onboarding funnels and A/B tests (use growth-engineering).
testing4
verification-methodology
Use when designing verification environments, planning coverage-driven closure, or architecting UVM testbenches. Covers constrained-random stimulus, functional coverage models, assertion-based verification, formal property checking, and coverage closure planning. Do not use for RTL design flow (use chip-design-flow) or SoC integration (use soc-integration).
testing4
formal-spec
Use when writing formal specifications in TLA+ to verify system properties, defining state variables, configuring TLC model checker, and documenting assumptions and limitations. Covers safety and liveness properties for protocols and concurrent systems. Do not use for security claim enumeration without specification intent (use invariant-analysis).
testing4
embedded-architecture
Use when designing firmware architecture for embedded or IoT devices. Covers RTOS selection, memory layout, power state machine, task decomposition, and watchdog recovery design. Do not use for wireless protocol selection (use protocol-design) or fleet-scale device management (use fleet-management).
development4
fleet-management
Use when designing fleet management infrastructure for IoT device fleets. Covers device provisioning, OTA firmware update strategy, telemetry pipeline design, fleet monitoring, remote management, and scaling projections. Do not use for firmware architecture (use embedded-architecture) or wireless protocol selection (use protocol-design).
development4
protocol-design
Use when selecting and designing communication protocol stacks for IoT or embedded systems. Covers physical layer selection, transport and application protocols, security layers, message format design, and error resilience. Do not use for firmware architecture (use embedded-architecture) or fleet-scale operations (use fleet-management).
development4
mvp-scoping
Use when defining minimum viable scope for a product or feature launch. Covers MoSCoW prioritization, value-effort matrix analysis, MVP cut-line definition, and phased roadmap planning. Do not use for quantified feature comparison (use impact-estimation) or measurement instrumentation (use analytics-design).
data-ai4
evaluate-diagram
Use this skill when scoring or comparing a generated diagram against a human reference. Triggers on "score this diagram", "evaluate my diagram", "compare to reference", or "how accurate is this". Applies when both a generated diagram and a reference image exist and quality assessment is needed. Do NOT use for creating new diagrams (use generate-diagram) or plotting data (use generate-plot).
testing4
dbt-skill
Use when working with dbt (data build tool) - creating models, writing tests, CI/CD pipelines, materializations, sources, staging/intermediate/marts layers, Snowflake/BigQuery warehouse configuration, incremental strategies, Jinja macros, data quality, semantic layer, or making analytics engineering decisions
tools4
dockerfile-generation
Use when creating Dockerfiles, optimizing container images, or reviewing Docker configurations. Produces multi-stage, security-hardened builds with proper layer caching. Triggers on 'create Dockerfile', 'dockerize', 'optimize container'.
development4
Git Branches
List and visualize branch status
tools4
Git Conflicts
Guided conflict resolution for merge and rebase conflicts
documentation4
GitHub Issue
Create, link, and manage GitHub issues with templates
tools4
GitHub Tag
Create semantic version tags
tools4
schema-evaluation
Use when evaluating or designing data warehouse schemas for analytical workloads. Covers star schemas, snowflake schemas, data vault, OBT patterns, grain definition, SCD strategies, normalization trade-offs, and data contracts between producers and consumers. Do not use for pipeline orchestration or ETL flow design (use pipeline-design).
devops4
observability-design
Use when designing monitoring, alerting, logging, tracing, and SLI/SLO strategies for services or systems. Covers metric collection, structured logging, distributed tracing, dashboard design, and error budget management. Do not use for deployment pipeline design (use deployment-plan) or infrastructure cost modeling (use cost-analysis).
testing4
failure-mode-analysis
Use when systematically identifying failure scenarios for proposed features and infrastructure changes. Covers component enumeration, failure mode discovery, cascade analysis, mitigation design, monitoring signals, and rollback planning. Do not use for security threat modeling (use threat-model) or input boundary testing (use edge-case-enumeration).
testing4
generate-plot
Use this skill when creating a statistical plot or chart from a data file. Triggers on "plot this data", "make a chart", "graph this CSV", or "visualize these results". Applies to CSV, JSON, or tabular data needing bar charts, scatter plots, line graphs, or similar visualizations. Do NOT use for methodology diagrams from text (use generate-diagram) or diagram scoring (use evaluate-diagram).
data-ai4
Git Abort
Abort failed merge, rebase, or cherry-pick operations
data-ai4
Git Stash
Stash management - save, pop, list, and drop stashed changes
tools4
GitHub Changelog
Generate changelog from merged PRs and commits
documentation4
workflow
Use when planning implementation steps, deciding commit format, or structuring development approach. Provides brainstorm-plan-implement flow with conventional commits. Triggers on 'how should I approach this', 'commit format'.
development4
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
development4
language-conventions
Language and project convention references for Python, TypeScript, and Terraform. Use when setting up new projects, reviewing code conventions, or ensuring consistency. Covers tooling, configs, patterns, testing, and project structure.
tools4
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
development4
GitHub PR Merge
Merge a pull request with strategy selection
tools4
component-fix-and-verify
Use when a diagnosed fix needs to be applied and verified against a Next.js component — "apply this fix," "fix and run tests," or "verify this change." Applies a single diagnosed fix with mandatory diff preview, then runs scoped and broad verification (tsc, lint, tests) with atomic safety and revert capability. Not for diagnosing bugs (use ui-bug-investigator or css-layout-debugger) or generating regression tests (use regression-test-generator).
development4
GitHub Mine
Show my assigned and mentioned GitHub items
tools4
edge-case-enumeration
Use when systematically discovering edge cases for proposed features using structured enumeration techniques. Covers input boundary analysis, state combinations, concurrency scenarios, temporal edge cases, and permission edge cases. Do not use for security threat analysis (use threat-model) or infrastructure failure discovery (use failure-mode-analysis).
testing4
ml-workflow
Use when designing end-to-end ML workflows. Covers experiment tracking, feature engineering and storage, model training pipelines, serving and deployment, A/B testing, and drift monitoring. Do not use for data warehouse schema design (use schema-evaluation) or ETL pipeline architecture (use pipeline-design).
testing4
ai-data-integration
Use this skill when connecting AI or LLMs to data platforms. Covers MCP servers for warehouses, natural-language-to-SQL, embeddings for data discovery, LLM-powered enrichment, and AI agent data access patterns. Common phrases: "text-to-SQL", "MCP server for Snowflake", "LLM data enrichment", "AI agent access". Do NOT use for general data integration (use data-integration) or dbt modeling (use dbt-transforms).
tools4
SKILL_NAME
TRIGGER_DESCRIPTION. Use when USER_CONTEXT. Covers CAPABILITIES.
tools4
physical-design-security
Use when reviewing physical implementation security for power domain coupling, timing-related leakage, clock domain crossing issues, and layout-level information exposure. Covers DPA/SPA resistance, EM emanation, fault injection countermeasures, and probing defenses. Do not use for RTL logic review (use rtl-security-review) or microarchitectural attack analysis (use microarch-analysis).
development4