Claude Skills by bsamiee

Load skill knowledge via skill-summarizer agent

Creates Claude Code agent files (.claude/agents/*.md) with YAML frontmatter, tool permissions, and system prompts. Use when building new agents, configuring agent frontmatter, writing agent system prompts, or setting agent tool permissions.

Use for Bash 5.2+/5.3 scripts, shell CLIs, entrypoints, CI jobs, cron, text-processing pipelines, ShellCheck remediation, and shell reviews. Enforces strict mode, dispatch-table routing, fork-minimal primitives, atomic I/O, signal-safe cleanup, and pragmatic functional shell patterns.

Enforces C# + LanguageExt functional/ROP style, type discipline, runtime-record effects, Scrutor composition, and module organization standards. Use when writing, editing, reviewing, refactoring, or debugging .cs modules, implementing domain models, sealed DU hierarchies, Eff/Fin/Validation pipelines, or configuring .csproj, analyzers, or DI.

Use for PostgreSQL 18 SQL, migrations, DDL, functions, RLS policies, indexes, query plans, extensions, and SQL embedded in TypeScript via @effect/sql-pg. Enforces set-algebraic queries, schema-level invariants, current PostgreSQL features, extension-first design, tenant security, observability, and migration safety.

Enforces Python + expression style, type discipline, error handling, concurrency, and module organization standards. Use when writing, editing, reviewing, refactoring, or debugging .py/.pyi modules, implementing domain models, ROP pipelines, Protocol-driven services, or configuring pyproject.toml, Ruff, or ty.

Enforces TypeScript + Effect functional/ROP style, type discipline, polymorphic surfaces, and module organization standards. Use when writing, editing, reviewing, refactoring, or debugging .ts/.tsx modules, implementing domain models, Effect services, persistence adapters, or boundary handlers, or configuring TypeScript, Effect, or lint/type-check posture.

Generates slash commands with YAML frontmatter, $ARGUMENTS/positional params, and tool permissions. Use when creating .claude/commands/*.md files or fixing command routing.

Queries version-specific library documentation from Context7. Use when fetching API references, code examples, or conceptual guides for npm/PyPI packages. Resolves library IDs, retrieves docs by topic. Not for web search.

Orchestrates two-round parallel agent research with Exa orientation, breadth-first discovery, and depth-focused synthesis. Use when conducting comprehensive research, exploring complex topics requiring multi-source validation, or synthesizing findings from distributed investigation streams.

Generates and validates project documentation: READMEs, ADRs, changelogs, ARCHITECTURE.md, and code documentation. Use when creating, updating, or reviewing any non-code markdown artifact, README file, architecture decision record, ARCHITECTURE document, CHANGELOG entry, or code documentation (docstrings, XML docs, TSDoc). Activates for: (1) scaffolding README, CHANGELOG, ADR, CONTRIBUTING, ARCHITECTURE, or SECURITY files; (2) writing or reviewing doc comments on exported APIs; (3) auditing d...

Generates and validates production-ready multi-stage Dockerfiles and .dockerignore files with BuildKit features, pnpm monorepo support, OCI labels, and security hardening. Use when creating, editing, reviewing, or validating Dockerfiles for Node.js, Python, Go, Java, or Rust.

Executes semantic web search via Exa AI Python CLI. Use when searching for current information, code examples, API documentation, finding similar pages, or generating AI answers with citations. Supports fast/deep/neural search.

Generates and validates GitHub Actions workflows and custom actions (composite/Docker/JavaScript) with SHA-pinned supply chain security, SLSA attestation, OIDC federation, and harden-runner enforcement. Use when creating, editing, reviewing, or validating CI/CD pipelines, reusable workflows, monorepo CI patterns, container build/deploy orchestration, or advanced triggers (workflow_run, dispatch, ChatOps).

Executes GitHub operations via gh CLI 2.62+ Python wrapper for issues, PRs, workflows, projects, releases, cache, labels, discussions, and search. Use when managing repository lifecycle, reviewing code, triggering CI/CD, or querying GitHub API.

Creates Claude Code hooks executing shell commands, prompt evaluations, or multi-turn agents at 15 lifecycle events. Use when building PreToolUse validation, PostToolUse formatting, PermissionRequest auto-approval, Stop/SubagentStop evaluation, TeammateIdle prevention, TaskCompleted gating, Setup provisioning, SessionStart context injection, or deterministic agent control via blocking/non-blocking hooks.

Executes Hostinger API operations managing VPS instances, Docker Compose, DNS, domains, billing, firewalls, SSH keys, snapshots. Use when controlling virtual machines, containers, domain configuration, or hosting infrastructure.

Generates and validates production-ready Pulumi K8s TypeScript resources following deploy.ts patterns, and diagnoses runtime cluster issues. Use when creating Deployments, Services, Ingress, Gateway API, HPA, ConfigMaps, Secrets, PVCs, DaemonSets, NetworkPolicies, PDBs, ValidatingAdmissionPolicies, ComponentResources, validating existing infra code, or debugging deployed K8s/EKS workloads.

Generates LogQL queries for Grafana Loki 3.0-3.6 log aggregation and metric extraction. Use when building Loki queries, dashboards, alerts, or optimizing pipeline performance with bloom filters, structured metadata, pattern matching, and approx_topk aggregations.

Generates Mermaid v11+ diagrams with YAML frontmatter, ELK layout, and Dracula theming across 22 types: flowcharts, sequence diagrams, state machines, ER diagrams, class diagrams, mindmaps, block diagrams, journey maps, requirement diagrams, pie charts, quadrant charts, sankey diagrams, XY charts, radar charts, gantt charts, treemaps, C4 architecture, architecture-beta, packet-beta, timelines, gitgraph, and kanban boards. Use when visualizing logic flows, system architecture, state transition...

Generates production-ready n8n 2.0+ workflow JSON with nodes, connections, AI agents, RAG pipelines, Task Runners, MCP clients, and validation. Use when building workflow automations, scaffolding LangChain agents with tools/memory, implementing RAG retrieval systems, or converting requirements to n8n JSON.

Queries Nx monorepo metadata via Python CLI: workspace projects, affected detection, dependency graphs, project.json configs, generator schemas. Use when analyzing monorepo structure, optimizing CI via affected projects, or inspecting workspace topology.

Generates Pulumi TypeScript observability infrastructure for Grafana Alloy 1.13, Prometheus 3.5+, Grafana 12.3 across K8s/Docker. Use when deploying metrics stacks, provisioning alert rules/dashboards, or migrating cloud↔selfhosted observability.

Creates structured output formats (JSON/YAML/Markdown-KV/XML) and response style scope configurations via accuracy-token tradeoff analysis. Use when defining agent schemas, building CLAUDE.md output sections, configuring hierarchy overrides, or standardizing serialization patterns across agents/commands.

Orchestrates concurrent workstreams via Task tool, decomposing non-trivial requests into 3-10 parallel agents with independent scopes. Use when multiple investigative paths, validation layers, research/analysis/debugging exceed trivial scope, or implementation planning requires facet exploration.

Queries Perplexity AI via sonar/sonar-pro/sonar-deep-research/sonar-reasoning-pro models. Use when conducting cited web research, deep technical reports, or complex reasoning problems requiring up-to-date sources.

Generates and validates PromQL queries with RED/USE/SLO patterns, native histograms, recording rules, and alerting expressions. Use when creating, reviewing, or validating PromQL queries, recording rules, or alerting expressions.

Executes SonarCloud API operations for quality gates, issues, metrics, analysis history, and security hotspots. Use when checking code quality, inspecting bugs/vulnerabilities, retrieving coverage/complexity metrics, or viewing project security status.

Enforces LLM-optimized style compliance for documentation and code. Use when creating/modifying markdown (headers, lists, Dictums, separators), code organization (comments, dividers, naming), or validating voice (grammar, tone, imperative phrasing) and formatting against taxonomy/whitespace standards.

Executes Tavily AI search, extraction, crawling, mapping, and deep research via Python CLI. Use when web search, URL content extraction, site crawling, or multi-step research needed.

Generates dense law-driven test suites for Effect modules via algebraic PBT using Vitest, @effect/vitest, fast-check. Enforces 175 LOC cap, 95% per-file coverage, mutation kill-ratio via Stryker. Use when writing/reviewing spec files, adding coverage, generating property tests, debugging flakes, or scaffolding unit/integration/E2E tests from templates.

Parallel divergent ideation for coding agents. Spawns N isolated branches under different cognitive frames (regulator, biology, speedrunner, 10-year-old, $0 budget), scores, clusters, prunes traps, and deepens top survivors. Use on /adhd, "ADHD mode", brainstorm/ideate intents, or open-ended design, architecture, naming, API/SDK surface, and fuzzy-debugging decisions. Skip for syntax, lookups, bugs with known root cause, or closed phrasing ("quick", "standard", "canonical", "textbook").

Structural code work on ast-grep — outline maps before reading source, AST search through the MCP tools with inline rules, durable rule folders enforcing project quality, and syntax-tree rewrites. Use when reading, editing, or searching any code/source file, when authoring or organizing a project's ast-grep rules, and when applying structural rewrites.

Owns the local review cycle over three engines — CodeRabbit, Greptile, and Macroscope (`.coderabbit.yaml`, `.greptile/`, `.macroscope/`). Use on any request to review, and whenever those config files are read, edited, or authored — this skill owns their schemas and rule grammar.

Scripted actions in macOS — an app's scripting dictionary, Apple Event wire ABI under it, and the Objective-C bridge opening Cocoa and Foundation to JXA. Drives native machine and app state and data, resolves terminology via installed dictionary, provides capability as an agent-callable tool returning a typed JSON envelope, embeds OSA in a Cocoa host, runs unattended via launchd, ships packaged applets, and authors sdef that makes an app scriptable. Use whenever interacting with macOS applica...

Authors, hardens, reviews, and debugs Bash and shell scripts. Use whenever creating, editing, or reading any .sh/.bash file, and ShellCheck remediation.

Owns PostgreSQL work: schema and DDL, migrations and lock levels, set-algebraic queries, functions and PL/pgSQL, indexes, RLS and tenant isolation, extensions (pgvector, PostGIS, TimescaleDB, pg_partman, pg_cron, pg_duckdb), logical replication and CDC, server tuning (vacuum, WAL, parallel query, JIT), EXPLAIN plans, wait-event and lock-contention diagnosis, and SQL embedded in TypeScript through @effect/sql-pg. Use when authoring, reviewing, migrating, or debugging any .sql file or SQL strin...

Infrastructure custody pass — dispatches infra-custodian over a scope (TEND) or the working diff (REVIEW, the bare default); returns its typed receipt. Use after landing edits to constitutions, RULINGS, routers, laws, standards, or .claude/ definitions, and on "check the infra", "did we miss a ruling".

Gemini dispatch via Antigravity: image generation and Nano Banana, visual judgment of images, visual artifacts, screenshots, diagrams, and second-model critique returning taste and quality related findings. Use for "generate an image", "make a mockup", "visually confirm", for competing-design synthesis, visual validation, counterexample hunts, and on any mention of Gemini, Antigravity, or Nano Banana.

Owns codex usage end to end, dispatch through the supervised delegate script, the codex prompt contract, model and effort choice, and session resume. Use as a write delegated sub-agent when work is well defined and explicit, use as a read delegate for exploration, research, and navigation, writing a durable report when a stronger model is needed for deep investigation with cheap usage expense, and a second perspective on any plan or diff. Use when writing or repairing a codex prompt, or codex...

Owns all prose, markdown files and the comments inside source files and fences through a voice law, an anti-anchoring rule against rosters, counts, and freezes, a named defect catalog, file-kind templates, and a deterministic gate and fixer. Use when authoring, editing, or reviewing markdown of any kind and comments in source files; when designing a document schema or marker vocabulary; when pruning code comments; or on "clean up this doc", "tighten the prose", "this doc is stale".

Builds Claude Code and Codex hooks — enforcement, where a rule the model keeps ignoring becomes a deterministic exit-2 block, one body serving both providers. Use for PreToolUse gates, PostToolUse formatting/redaction, PermissionRequest auto-approval, SessionStart injection, Stop/SubagentStop continuation, PreCompact extraction, async guardrails, and Codex hooks.json/config.toml adapters.

Owns Hostinger account work and the transport that carries it — `hostinger` MCP tools, REST under `HOSTINGER_API_TOKEN`, or SSH on the box — with the safety law over irreversible acts: snapshot first, firewall sync, async polling, hPanel-only escapes. Reaches domains, DNS zones, WHOIS; VPS lifecycle, firewalls, SSH keys, recovery; Docker Compose deploy and rollback; shared hosting, WordPress, databases; ecommerce stores; Reach deliverability and segments; the billing catalog `item_id` every p...

Authors, validates, and repairs Mermaid diagrams: type selection, graph logic, layout-engine config, an archetype template per diagram kind, and a bundled validator proving each fence renders, reads legibly, and holds its graph logic. Committed fences carry structural payload only; theming rides one optional reference for a deliverable that explicitly wants a styled render. Use when writing, fixing, or embedding a mermaid fence in markdown or a single-file HTML page, exporting one to SVG or P...

Owns Pulumi infrastructure-as-code: creating, inspecting, and destroying cloud and SaaS resources on any Pulumi-registry provider — `pulumi do` one-offs, projects and stacks, ComponentResource design and packaging, Automation API, ESC environments, policy packs, drift schedules. Use when reviewing or refactoring Pulumi code, debugging a failed `up` or `preview`, chasing an unexpected replace or delete in a preview, adopting resources via `pulumi import`, converting Terraform, CloudFormation, ...

Drives a live Rhino session: on-demand slot spawn or adoption of a user-started Rhino, slot lifecycle, RhinoCommon scripting in C# and Python, `.3dm` open/save, scene and selection queries, layer materials, camera framing, cost-bounded viewport capture, and Grasshopper2 canvas authoring. Use when working within Rhino for code development, or dedicated Rhino session work, creating Grasshopper scripts and layouts, or when its MCP tools are absent — "work in Rhino", "work in Grasshopper', "show ...

External-package truth: any signature, member, or capability of an imported library resolves through Context7 over memory or a guessed git tag. Load before the first lookup. Fires on any Context7 mention, doc or API lookup, a new import, "how does <lib> do X", and before coding against an uninstalled member. Un-indexed sources belong to search-tavily.

Owns live-web retrieval through Tavily CLI (`tvly`), search, extract, map, crawl, research, on the cheapest verb that answers: relevance resolved server-side, not post-filtered locally, and bulk page content routed to disk, never the context window. Beats blind single-URL fetching, which ranks and scopes nothing. Any current-web question routes here.

Owns secret custody over 1Password and Doppler — op the permanent local store and SSH-key custodian, Doppler the runtime backend. Use when creating a secret, token, or env key or when one fails to resolve, creating and managing them, the op agent key, a tool or code logic needs a scoped token, or a config file needs secret material. Minting tokens and creating projects, configs, or scopes is Pulumi topology in Parametric_Forge/services/topology.ts — the pulumi skill.