lock-project-stack
Detect a project's manifest (pyproject.toml / package.json / go.mod / Cargo.toml), pin its library set into wet-mcp's Cabinets project_context, then route subsequent docs queries to the locked versions automatically.
hunt-analytics-generation
Generate query-agnostic analytics that model adversary behavior by translating hunt investigative intent into analytic definitions grounded in schema semantics. This skill is used to define how behavior should manifest in data before query execution or validation, and works best when informed by system internals, adversary tradecraft, a structured hunt focus, and suggested data sources.
argocd-helm
ArgoCD and Helm expert skill. Use when deploying applications with ArgoCD, creating or reviewing Helm charts, designing GitOps workflows, managing ApplicationSets, multi-cluster deployments, progressive delivery with Argo Rollouts, troubleshooting sync issues, secrets management (SOPS, External Secrets Operator), and Kubernetes manifest management. Covers ArgoCD 3.x and Helm 3.x best practices.
rembric-plugin-development
Apply when creating, modifying, or reviewing any Rembric agent plugin. Triggers on changes under `apps/plugin/`, on new clients added alongside Claude Code / Codex CLI / Hermes Agent / opencode, on edits to `apps/plugin/bin/rembric-bridge.mjs` or `apps/plugin/bin/rembric-dotenv.mjs`, on per-client manifest changes, or on plugin install/uninstall scripts. End-to-end validation against `pnpm run dev:docker:up` is mandatory whenever local testing is feasible.
pwa-review
Comprehensive 185-point PWA audit beyond Lighthouse - analyzes manifest, service worker, offline capabilities, security, iOS compatibility, and advanced PWA features
android-cli
Reference for the AndroidSdk.Tool CLI (`android` command) - a .NET global tool for Android SDK automation. Use when: (1) Managing Android SDK packages (list, install, uninstall, download), (2) Working with AVDs/emulators (create, delete, start, list), (3) Interacting with connected devices via ADB (list devices, get properties, install/uninstall APKs), (4) Locating or configuring JDK for Android development, (5) Setting up CI/CD for Android or .NET MAUI development, (6) Reading APK manifest information, (7) Accepting SDK licenses non-interactively.
Crewship Artifacts
Create and revise Crewship Project, Dashboard and Slides artifacts with complete manifests, data version checks, anchored agent feedback and restorable code versions, and edit selected Design canvases. Use for these artifacts, not native Craft documents or website deployment.
bedframe
Work in a Bedframe browser extension project. Use when the repository contains AGENTS.md, src/_config/bedframe.config.ts, src/manifests/*, or the task involves the Bedframe CLI, @bedframe/core, browser manifests, extension pages, Vite config, or release flow.
enapter-blueprint
Enapter Blueprint skill covering Lua script, manifest, profiles, publishing to Marketplace. Use for any Enapter Blueprint development task.
curator-evolution
Use when interpreting Hermes Curator Evolver evidence reports, historical session backfill, proposals, verifier results, candidate search, auto-run output, timer installs, or guarded apply manifests.
dbt_ingest
Map dbt `schema.yml` / `properties.yml` models and sources into KTX semantic-layer overlays and column notes. Covers `sources:` vs `models:`, column `data_tests` (not_null, unique, accepted_values, relationships), and how bundle-time writes complement manifest backfill from git sync. Load when the WorkUnit's `skillNames` includes `dbt_ingest` or when raw files are dbt YAML under `models/` / `sources/`.
generate-mdl
Generate a Wren MDL manifest from a database using ibis-server metadata endpoints. Use when a user wants to create or set up a new Wren MDL, scaffold a manifest from an existing database, or onboard a new data source without installing any database drivers locally.
assessment-design
Evidence-based assessment design with rubrics, feedback strategies, and formative checkpoints. Aligns each assessment to learning objectives using Bloom's taxonomy. Applies Nicol's 7 principles of good feedback practice. Reads from /learning-objectives manifest and extends it with assessment specs. (idstack)
browser-extension
Master specialized skill for building 2025/2026-grade browser extensions. Deep expertise in Manifest v3, Service Worker persistence (Alarms, Offscreen API), Side Panel API, and Cross-Browser compatibility.
orchardcore-module-creator
Creates new OrchardCore modules with proper structure, manifest, startup, and patterns. Use when the user needs to create a new module, add content parts, fields, drivers, handlers, or admin functionality.
manifest-status
Show current Manifest plugin configuration as a diagnostic table. Use when the user says "/manifest-status", "manifest status", "show manifest config", "manifest settings", "is manifest installed", "check manifest plugin", or wants to see the current state of the Manifest OpenClaw plugin configuration. Outputs a table and nothing else.
arch-check
Run the charter architecture fitness check â Checkpoint 7 (Light Verify), alongside `crap-analyzer`. Turns the charter's architectural vision from prose into an objective gate: `dae_arch.py` reads the manifest's `architecture:` rules and reports violations.
Chrome Extension Development (Manifest V3)
This skill covers everything needed to build, debug, and publish Chrome extensions with MV3. It is organized as a routing document: read this file first to understand the architecture and decision points, then load the relevant reference file for implementation details.
uemcp-manifest-type-hints
Fix silent tool registration failures in UEMCP when Python function parameters use modern union syntax (str | None) instead of Optional[str]. Use when: (1) MCP tools silently lose optional parameters in their JSON schema, (2) new ops module parameters all show as required when they should be optional, (3) manifest generator falls through to string type for Optional parameters. The manifest generator's get_origin() check only matches typing.Union, not types.UnionType from Python 3.10+ pipe syntax.
kubernetes-skill
Prevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, and cluster policies.
kinocut-repurpose
Use the current Kinocut tools to turn one local video path into a short platform-ready clip package with manifests, review artifacts, and human approval gates.
cleanup-quarantine-manager
Classify cleanup candidates and apply conservative quarantine moves with reversible manifests.
minectl
Use this skill for every message containing the word "minectl". Claude has zero built-in knowledge of minectl â it is an obscure, third-party CLI for deploying Minecraft servers to cloud providers. Without this skill, any response about minectl will be fabricated. This covers all minectl topics: manifests, create/delete/update commands, RCON troubleshooting, authentication errors, cloud provider selection, instance sizing, budget optimization, TPS tuning, plugin uploads, and edition choice. Do NOT trigger for Minecraft servers managed via Docker, Kubernetes, Ansible, Terraform, or Pulumi â only for minectl-based workflows.