atretyak1985
UserThe craft of agent swarms — a vendor-neutral, multi-project Claude Code agent framework (plugin marketplace): one shared core + opt-in domain packs.
Categories
Indexed Skills (54)
api-contract
Verify field-level alignment between the ORM schema, Zod validation schemas, and route handler response shapes in the main app (project.json -> mainApp), or check that SQL migrations match the ORM table definitions. Don't use it for writing new API routes (use api-integration), reviewing code style or naming (use code-standards), or auditing function length and complexity (use code-quality).
api-integration
Implement REST route handlers, ORM queries, WebSocket telemetry connections, or SSE streaming endpoints in the main web app (project.json -> mainApp), or consume those APIs from client components. Do not use for schema-only changes, deployment/infrastructure config work, or device firmware development.
automation
Convert a repeatable operational runbook for the project's infrastructure (pod restarts, cache flushes, scaling) into a parameterized, idempotent script with safety gates, or design a chaos experiment to test system resilience. Do not use for CI/CD pipeline changes, deployment-manifest authoring, application code changes, or ad-hoc debugging.
browser-verification
Use this skill when an agent needs to verify UI behavior in a live browser via Playwright MCP tools (browser_navigate, browser_snapshot, screenshots, console/network capture) against localdev or the project's staging environment (project.json -> cloud.envAlias). Covers the target-confirmation step, the observe/interact loop, and safety guardrails. NOT for full domain E2E lifecycle flows (use the domain pack's E2E skill if the project ships one) and never against production.
c4-architecture-docs
Use this skill to document the architecture of a big issue / epic / feature with the C4 model (c4model.com) -- producing system context, container, component, and dynamic diagrams as Mermaid .mmd plus a narrative doc. Trigger phrases: 'C4 model', 'architecture diagram', 'system context / container / component diagram', 'document the architecture of this epic', 'draw the containers for this feature'. Don't use it for: rendering an existing .mmd to HTML (use the project's Mermaid viewer/renderer, or the `mmdc` CLI); FigJam whiteboard diagrams (use figma:figma-generate-diagram); a pure decision record with no diagrams (use the ADR template — `.claude/templates/adr-template.md`, falling back to core's `templates/adr-template.md`).
code-quality
Use this skill for QUANTITATIVE structural metrics on TypeScript or Python source -- function length, cyclomatic complexity, nesting depth, duplication, code smells -- producing a scored report. NOT for conventions, naming, or `any`-type checks (use code-standards), API contract alignment (use api-contract), or deployment config (use deployment).
code-search
Select the right search tool (Grep, Glob, codebase-retrieval) to locate existing code, symbols, or files across the project's monorepo. Don't use it for creating new files, implementing features, or reviewing code quality.
code-standards
Use this skill when reviewing TypeScript, Python, or infrastructure/service-config code against the project's CONVENTIONS -- type safety (`any` detection), naming, import ordering, Next.js patterns, and 12-factor build rules. NOT for quantitative complexity metrics -- function length, cyclomatic complexity, nesting depth belong to code-quality. NOT for API field alignment (use api-contract).
deps-check
Use this skill when auditing dependency versions, checking for outdated packages, or scanning for security vulnerabilities across the project's repos. Don't use it for upgrading packages (that requires a separate implementation task) or for deployment config template issues (use deployment).
env-check
Use this skill when a task involves adding, removing, or renaming environment variables across the project's repos OR verifying env var documentation before a release. Don't use it for runtime env introspection in a live cluster (that requires exec access to the running service).
functional-design
EXECUTES refactors of TypeScript business logic in the main app toward pure functions, immutability, and data-flow pipelines -- edits files directly via Edit. NOT for planning-only refactors with no code changes (use refactor-plan). NOT for cloud service config, I/O-heavy route handlers, or Python/firmware paths in the device/edge repo (project.json → device).
git-commit
Generate conventional commit messages when staging files for commit in any of the project's repos. Do not use for git tag messages, merge commit messages, changelog entries, or automated version bump commits.
html-reporting
Use this skill when an agent must render a self-contained HTML report or dashboard — task summaries (Phase 8), code/operational audits (Phase 5), or any shareable artifact viewed outside the terminal. It provides one canonical dark-terminal shell so every report looks consistent. Don't use it for markdown-only output, for measuring metrics (it only formats numbers you supply), or for the mermaid viewer (use mermaid-viewer).
mermaid-viewer
Use this skill when the user has a Mermaid source file (.mmd) and wants to view it in a browser -- asking to convert mermaid to html, render this diagram, make an HTML viewer, or make the schema explorable. Don't use it for generating new diagrams from scratch or exporting to PNG/PDF.
migration-check
Validate SQL migration safety, check ORM-to-migration schema alignment, review new migration SQL files, or detect schema drift between the database and application Zod/DTO types. Do not use for deployment config validation (use deployment), identity-provider database issues (use the auth-domain skill), or IaC drift detection (use infrastructure-as-code).
refactor-plan
PRODUCES a refactoring plan ONLY -- impact analysis, step ordering, risk assessment, rollback strategy -- with NO code changes made. NOT for executing refactors: pure-function/immutability refactoring is executed by functional-design. NOT for deployment rollback (use release-promotion) or dependency upgrades (use deps-check).
security-audit
Use this skill when a task involves reviewing or scanning application code for security vulnerabilities, evaluating OWASP Top 10 compliance for the project's apps, device/edge repo, or cloud service config, or scanning for hardcoded secrets. Don't use it for CI/CD pipeline hardening or SBOM generation (use supply-chain-security instead).
summary-templates
Use this skill when a task involves summarizing completed work, writing a feature summary, documenting what changed, or creating a completion report for a task, feature, bug fix, or refactoring. Don't use it for writing documentation, changelogs, or postmortems.
test-coverage
FIND test coverage gaps ONLY -- map source files to test files, identify untested modules with risk levels, and suggest what needs tests across the project's repos (project.json -> repos). Read-only analysis. NOT for writing, running, or debugging tests (use testing), and NOT for measuring actual coverage percentages (run the test suite with --coverage directly).
testing
WRITE, RUN, or DEBUG tests for the project's code -- pytest (Python), Jest/RTL (TypeScript), Playwright (E2E), and deployment config testing. NOT for finding coverage gaps or untested modules -- that read-only gap analysis belongs to test-coverage. NOT for CI pipeline configuration (use deployment).
keycloak
Configure Keycloak realm/client settings, integrate Auth.js v5 OIDC in the web portal (project.json → mainApp), set Keycloak Helm values (init/full stage), recover bootstrap admin, or debug KC_HOSTNAME/issuer mismatches. Do not use for Helm chart templating (use helm-chart-expert), GCP firewall rules (use kubernetes-deployment), or database migrations (use migration-check).
embedded-systems
Use this skill when writing or reviewing Python code for Raspberry Pi 5 edge devices -- UART hardware drivers, camera streaming via picamera2, GPIO control, systemd services, or resource monitoring. Don't use it for MAVLink protocol parsing (use mavlink-integration), web portal server code, or Helm work.
mavlink-integration
Use this skill when a task involves MAVLink protocol communication via pymavlink, UART/UDP/TCP drone connections, ArduPilot SITL simulation, or telemetry message parsing in the edge service. Don't use it for raw UART hardware driver code without MAVLink framing (use embedded-systems), WebSocket transport to the web portal (use api-integration), or Docker builds (use docker-build).
run-plan
EXECUTES an existing plan produced by @implementation-planner or @task-planner -- parses the phase DAG, routes sequential phases through a per-phase implementer+review loop and parallel groups through concurrent isolated dispatches, preserving ASK gates and durable progress. NOT for creating plans (use @task-planner / @implementation-planner), NOT for ad-hoc single-file fixes (no plan needed), NOT usable from inside a subagent (subagents cannot spawn subagents -- this playbook runs in the main session only).
docker-build
Use this skill when building or pushing Docker images for the project's services (the main app, the device service) to the cloud container registry. Don't use it for deploys (use deployment) or Dockerfile template editing without a build (use code-quality).
jira-tasks
Read-only Jira access for the project's tracker — answer 'what am I assigned', list open tickets, check <PROJECT-KEY>-<n> status, pull the jira backlog, or link a workspace task to a ticket. Triggers: my tickets, open tickets, what am I assigned, jira backlog, link task to ticket, ticket status, recently updated tickets, tickets by label. NOT for creating, transitioning, commenting on, or logging work against tickets — those are write ops the user must explicitly request each time, never as a side effect. NOT for Confluence (pages, spaces, comments).
monitoring
Use this skill for Prometheus metrics, Grafana dashboards, alert rules, and ServiceMonitor wiring ONLY -- including instrumenting an endpoint with Prometheus counters or histograms. NOT for logs or traces: structured logging, OpenTelemetry spans, and log-trace correlation belong to observability. NOT for Helm liveness/readiness probes (the project's deployment workflow / infra-pack skills when enabled).
monorepo-coordination
Coordinate changes that span two or more repos of a multi-repo workspace, or two or more apps/packages of a monorepo (read project.json → repos / monorepo for the project's shape). Produces merge-order plans, MR/PR templates, CI probes for operator gates, and post-merge validation checklists. Not for changes confined to a single repo or package, even large ones.
observability
Use this skill for structured logging and OpenTelemetry distributed tracing ONLY -- including log-trace-metric correlation in the project's service code. NOT for metrics or dashboards: Prometheus counters/histograms, Grafana dashboards, and alert rules belong to monitoring. NOT for Helm health probes (the project's deployment workflow / infra-pack skills when enabled).
troubleshooting
Use this skill when debugging a specific failure, investigating an incident, analyzing error logs, or diagnosing connectivity problems on the project's platform. Don't use it for proactive instrumentation (use monitoring or observability), writing tests (use testing), CI pipeline config (use deployment), or staging-environment-specific pod debugging (use the staging operations skill).
aws-cicd-auth
Configure and review AWS auth for GitHub Actions CI/CD — OIDC role assumption, ECR push perms, ECS deploy perms, least-privilege IAM. Not for application IAM/Cognito, not for GCP.
deployment
Use this skill for a Helm-upgrade deploy of an app service (the web portal or the edge service) to an EXISTING Kubernetes cluster, plus post-deploy verification. NOT for cluster-level ops -- Minikube/k3s lifecycle, GCP firewall, tunnels, bootstrap secrets (use kubernetes-deployment); NOT for cross-environment promotion (use release-promotion).
gcp-cicd-auth
Configure and review GCP authentication for GitLab CI/CD pipelines: Workload Identity Federation, Artifact Registry push, Secret Manager access, and least-privilege service accounts. Not for Keycloak IAM, AWS/Azure auth, or runtime pod identity.
github-actions-cicd
Design, review, or debug GitHub Actions workflows — CI jobs (type-check, lint, test, build, security, summary), AWS ECR/ECS deploys, and a standardized per-repo workflow set. NOT for cloud-auth role/OIDC trust details (use aws-cicd-auth) or Dockerfile/image-build mechanics (use docker-build).
gitlab-ci-cd
Design, review, or debug .gitlab-ci.yml pipelines for the project's repos. Covers stage ordering, job configuration, artifact flow, deploy safety flags, and the 8-stage model. Not for GitHub Actions, Jenkins, GitOps controllers, or GCP auth stanzas.
gitops-promotion
Use this skill when the project uses a pull-based GitOps controller (Wave B) for cluster reconciliation via a version-pinning repo's desired state. Don't use it during Wave A imperative GitLab deploys (use gitlab-ci-cd) or for CI pipeline structure (use gitlab-ci-cd).
helm-chart-expert
Use this skill when a task involves Helm chart templating, values file structure, subchart dependency management, or chart validation (lint/template/dry-run) for the project's charts. Don't use it for Helm deploy orchestration (use deployment), Keycloak config (use keycloak), IaC drift (use infrastructure-as-code), or Docker builds (use docker-build).
infrastructure-as-code
Use this skill when a task involves detecting config drift between live cluster state and code, capturing manual kubectl/psql/gcloud fixes into Helm values or Terraform, preparing populated values files, or verifying a fresh deploy would succeed from code alone. Don't use it for Helm template authoring (use helm-chart-expert) or migration safety checks (use migration-check).
kubernetes-deployment
Use this skill for CLUSTER-LEVEL Kubernetes operations: Minikube/k3s lifecycle, GCP firewall rules, minikube tunnel debugging, and bootstrap-secret patterns. NOT for app-service Helm deploys or upgrade orchestration (use deployment) or Helm chart template authoring (use helm-chart-expert).
release-promotion
Use this skill when promoting an image or chart version across environments (dev -> staging -> production), rolling back a promotion, or updating the version-pinning repo's digests. Don't use it for single-environment Helm deploys (use deployment) or code-level rollback (use refactor-plan).
mission-creation
Use this skill to create and drive a UAV mission end-to-end through the web UI with the Playwright MCP browser tools on LOCALDEV (https://<localdev-host>) — rebuild/redeploy, Keycloak login, the multi-step BY_ROUTE/REALTIME mission wizard, pre-flight, the Start-Mission FSM, AND the full per-drone flight-command lifecycle (arm → take-off → hover → start/fly → stop → observation divert → resume → home/land/disarm), per-tab verification, and cleanup. Use it for E2E UI verification (incl. verifying a controlbox/FSM change against real SITL), demos, or reproducing mission-flow bugs. Do NOT use it against staging or production (shared/real environments), for API-only or DB-seeded mission creation (no browser), or when localdev is not running.
auditing-agent-architecture
Use when designing or reviewing Claude-based agent systems — agentic loops and stop_reason handling, multi-agent orchestration, coordinators, subagent invocation and context passing, workflow enforcement, Agent SDK hooks (PreToolUse/PostToolUse), task decomposition, or session state and resumption. Also when an agent terminates prematurely, loops forever, repeats work, or subagents return inconsistent or incomplete results.
configuring-claude-code
Use when setting up or auditing Claude Code in a repository — CLAUDE.md hierarchy and imports, .claude/rules, custom slash commands and skills, path-specific rules, plan mode vs direct execution, iterative refinement workflow, or CI/CD integration with headless -p mode. Also when instructions get ignored, conventions load in the wrong scope, CLAUDE.md has grown bloated, or a CI pipeline needs non-interactive Claude runs.
engineering-prompts-and-output
Use when writing or reviewing system prompts, few-shot examples, structured output via tool use, JSON schema validation with retry loops, Message Batches API processing, or multi-instance/multi-pass review pipelines such as automated PR reviewers. Also when outputs are inconsistent between runs, JSON fails validation, false positives erode reviewer trust, hallucinated fields appear, or self-review keeps missing defects.
managing-context-reliability
Use when reviewing long-running or multi-agent Claude systems for reliability — context window management and summarisation, escalation and ambiguity resolution, error propagation between agents, codebase exploration and context degradation, human review and confidence calibration, or information provenance and multi-source synthesis. Also when quality degrades over long sessions, agents silently swallow failures, mid-context details get lost, or synthesised answers lose attribution.
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
architecture-map
Generate or refresh the repo-wide architecture map — architecture-out/architecture-map.json (machine contract with named flows) + architecture-map.html (self-contained viewer). Use when the user asks for an architecture map, repo map, "/architecture-map", or when an agent needs a fresh machine-readable architecture overview. NOT for per-epic C4 deep-dives (use c4-architecture-docs) and NOT for building the knowledge graph itself (use /graphify).
gitnexus-cli
Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"
gitnexus-debugging
Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug"
gitnexus-exploring
Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow"
gitnexus-guide
Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?"
gitnexus-impact-analysis
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?"
gitnexus-refactoring
Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file"
designing-tools-and-mcp
Use when creating or reviewing tool definitions for Claude — tool names, descriptions, input schemas, structured error responses, tool_choice configuration, MCP server setup and scoping, or built-in tool usage (Grep, Glob, Read, Edit). Also when Claude picks the wrong tool, confuses similar tools, retries hopeless failures, treats empty results as errors, or degrades because too many tools are exposed.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.