Skills for the workbehind the code.

ALWAYS activate before implementing ANY feature, plan, or fix.

source snapshot Aug 22, 2026

ALWAYS activate before fixing ANY bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue, code problem.

source snapshot Aug 15, 2026

Debug systematically with root cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues, call stack tracing, multi-layer validation, log analysis, CI/CD failures, database diagnostics, system investigation.

source snapshot Aug 15, 2026

Plan implementations, design architectures, create technical roadmaps with detailed phases.

source snapshot Aug 22, 2026

STRIDE + OWASP-based security audit with MCP-assisted code analysis and optional iterative auto-fix. Scans code using graph_mcp for structure discovery and mind_mcp for security policy context, then produces severity-ranked findings with fix recommendations. Supports audit-only and audit+fix modes. Use before releases, after sensitive feature additions, or for periodic compliance reviews.

source snapshot Aug 15, 2026

Generate comprehensive edge cases and test scenarios by decomposing features across 12 dimensions (user types, input extremes, timing, scale, state, environment, errors, authorization, data integrity, integration, compliance, business logic). Uses mind_mcp for feature requirements context and graph_mcp for code path discovery. Use before implementation, during code review, or when planning test coverage.

source snapshot Aug 22, 2026

Produce draft-only evidence-backed HTTP and asynchronous API contracts, including OpenAPI or AsyncAPI drafts, endpoints, messages, schemas, authentication, authorization, errors, consumers, and providers. Do not deploy APIs, modify implementations, or publish inferred contracts as authoritative.

source snapshot Aug 15, 2026

Produce draft-only evidence-backed technical behavior as sequence, activity, state-machine, and event-flow documentation. Do not use for business use-case catalogs, API contracts, or persistent data models.

source snapshot Aug 15, 2026

Convene an adaptive panel of independent experts to generate competing solutions, challenge assumptions, debate tradeoffs, and select an evidence-backed option with weighted scoring before implementation. Use for ambiguous, consequential, or multi-path decisions; skip trivial work with one obvious reversible solution.

source snapshot Aug 22, 2026

Browser automation via Puppeteer CLI scripts with persistent sessions. Screenshots, performance, network, scraping, form automation, auth, debugging.

source snapshot Jul 20, 2026

Fast parallel codebase explore using multiple subagents with MCP-based external research. Use for file discovery (local), web/docs lookup, GitHub repo analysis, image/UI understanding.

source snapshot Aug 15, 2026

Produce draft-only special command or protocol wire-format specification from implementation code, including APDU/TLV fields, CLA/INS/P1/P2/Lc/Le framing, opcodes, status words, and command-specific models. Do not use for business scenarios, API contracts, or standalone behavior modeling.

source snapshot Aug 22, 2026

Set up and operate Cortex Harness for project code/doc ingestion, config updates, sync workflows, and MCP server lifecycle.

source snapshot Aug 15, 2026

Validate consistency across discovery outputs (use-case, API, data-model, behavior, command-spec) by checking stable ID resolution, actor/auth alignment, state-transition lifecycle matches, schema compatibility, and cross-domain evidence coherence. Use after leaf discovery skills complete, before refinement.

source snapshot Aug 15, 2026

Produce draft-only evidence-backed physical and logical data models, ERDs, entity and field inventories, data dictionaries, ownership, read/write access, lifecycle, sensitivity, caching, replication, and migration gaps. Do not execute schema migrations or present inferred relationships as declared constraints.

source snapshot Aug 15, 2026

Find current, authoritative technical documentation for libraries, frameworks, APIs, tools, standards, versions, migrations, configuration, and compatibility. Use when an answer requires verified external documentation or precise source links.

source snapshot Aug 15, 2026

Orchestrates evidence-backed document generation, human clarification, semantic/diagram refinement, and conditional review-comment resolution with pause/resume for one scoped domain. Use hi-maintenance-docs for a complete multi-domain pack.

source snapshot Aug 15, 2026

Analyze an evidence-backed draft for ambiguity, terminology gaps, missing semantics, and under-specified Mermaid diagrams, then apply validated clarification answers to an isolated candidate revision. Do not generate initial documents, resolve review comments, invent answers, or update an orchestrator's global manifest.

source snapshot Aug 15, 2026

Resolve structured review comments against an evidence-backed document revision; assign a disposition to every comment and apply accepted changes idempotently. Do not generate, clarify, approve publication, or update global manifests.

source snapshot Aug 15, 2026

Unified knowledge retrieval skill. Build traceable answers from git, MCP, and memory files.

source snapshot Aug 22, 2026

Write log entries analyzing recent changes and session reflections.

source snapshot Aug 15, 2026

Orchestrate a complete, navigable, evidence-backed maintenance documentation pack spanning system overview, architecture, modules, use cases, technical behavior, API contracts, data models, command specifications, gaps, and freshness. Use for end-to-end documentation — not one bounded domain.

source snapshot Aug 15, 2026

Synthesize existing module-inventory and tech-audit artifacts into an architecture summary, per-module breakdown, risk assessment, and optional Mermaid diagrams. Do not inspect source from scratch or run full onboarding.

source snapshot Aug 15, 2026

Create, edit, and visually validate client-ready PowerPoint presentations (.pptx) using a sanitized navy-white-orange-teal design system, with evidence-led storylines, natural executive copy, editable architecture/process/timeline/option layouts, and professional native charts derived from supplied CSV, JSON, spreadsheet, or tabular data. Use for executive proposals, consulting decks, technical architecture, current-state assessments, phased roadmaps, investment options, KPI reviews, and Japanese-customer-facing presentations where visual consistency, quantitative accuracy, privacy, and presentation readiness matter.

source snapshot Aug 15, 2026

Five expert personas independently analyze proposed changes before implementation to catch architectural, security, performance, and UX issues early. Uses mind_mcp for project context and graph_mcp for code impact analysis. Produces GO/CAUTION/STOP verdict with consensus agreements, conflict resolutions, and risk mitigations. Use before major features, refactors, or risky changes.

source snapshot Aug 22, 2026

Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, scale uncertainty.

source snapshot Aug 15, 2026

Organize project files, directories, output paths, names, and Markdown structure. Use when creating files, choosing where outputs belong, reorganizing existing assets, or standardizing a project layout.

source snapshot Aug 15, 2026

Map an unfamiliar repository into an evidence-backed module inventory, entry-point map, and optional key-function catalog. Use for repository onboarding, architecture reconnaissance, handover preparation, or refactor scoping.

source snapshot Aug 15, 2026

Gather traceable evidence from repository code and project documents. Use for codebase exploration, architecture, feature tracing, dependency or impact analysis, and questions that require verified source context.

source snapshot Aug 22, 2026

Generate or update a comprehensive, evidence-backed repository wiki in Repo Wiki format (/repowiki/), including architecture, installation and configuration, CLI/build automation, languages and frameworks, data/graph schemas, protocol integrations such as MCP, query/search, incremental processing, APIs, testing, deployment, developer guidance, troubleshooting, module documentation, and knowledge cards. Use for codebase documentation, team onboarding, repository capability mapping, and persistent architecture knowledge.

source snapshot Aug 15, 2026

Reverse Engineering C and C++ modules into validated use-case, module, and C++-to-Java migration artifact packages. Generates evidence-backed traces, sequence/class/state/activity/architecture diagrams, entry-point/interface/data/business-rule/error/concurrency catalogs, parity mappings, risks, tests, reviews, and coverage; exhaust mind_mcp and graph_mcp before Serena, and use native source tools only as a final fallback.

source snapshot Aug 22, 2026

Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition, course correction.

source snapshot Aug 15, 2026

Audit a repository's technology stack, build system, dependency management, CI/CD pipelines, deployment targets, and platform assumptions. Use for build onboarding, migration readiness, deployment review, or CI/CD documentation.

source snapshot Aug 15, 2026

Produce draft-only evidence-backed business use cases for one source module by inventorying files, classes, functions, entry points, registrations, indirect calls, and terminal effects, then reconstructing actors, permissions, rules, flows, outcomes, IDs, tests, and coverage. Do not use for technical behavior diagrams, API contracts, data models, or migration execution.

source snapshot Aug 22, 2026