Checks requirements.txt, pyproject.toml, and package.json dependency manifests for surface-level direct-dependency footguns: standard-library shadowing pins, abandoned backports, unpinned dependencies, and obvious intra-manifest conflicts, plus opt-in PyPI yanked releases. Use when the user asks to check a manifest for dependency problems, asks why dependencies won't install or whether anything is wrong with their dependencies, wants a dependency autopsy, or suspects dependency manifest rot. Runs offline by default as a local tool for the user's own project, not repository CI.

Creates reusable Convex components with defineComponent, a clean client wrapper, their own schema, and an npm publish setup. Use when extracting a feature into a package, building something for the Convex component directory, or when a component's functions are not showing up in the parent app.

Integrate, build and debug Tiptap editors in applications. Use for Tiptap setup, installing or creating extensions, collaboration, comments, AI features, and document conversion. Excludes contributions to the Tiptap monorepo or unrelated application work.

Audits a project's dependencies for supply-chain risk: version-matched advisories for direct dependencies and the full lockfile tree, abandoned or archived upstreams, npm publisher concentration, and install-time script execution. Use when asked to audit dependencies, assess supply-chain or third-party package risk, or review a dependency tree before an engagement.

Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings ledger, escalation when fixes stop converging, and a mechanical scope guard. Reviews are performed by the plugin-dev skill-reviewer agent. Use to fix skill quality issues, iteratively refine a skill, or resume a loop after an escalation ('fix my skill', 'improve this skill until it passes review', 'skill improvement loop'). NOT for a one-time review — use the plugin-dev skill-reviewer agent directly.

Keep Stave's Claude and Codex provider runtimes in sync when editing one of them. Use when a change touches `electron/providers/claude-sdk-runtime.ts`, `electron/providers/codex-app-server-runtime.ts`, executable lookup, env construction, CLI session launch env, tooling status probes, or any provider-agnostic behavior. Trigger on phrases like "provider runtime", "claude adapter", "codex adapter", "sibling adapter", "PATH env", "CLAUDE_CONFIG_DIR", "CODEX_HOME", "tooling status", "어댑터 대칭", "양쪽 프로바이더 확인".

Use when a large body of work (a version milestone, an epic, a roadmap, a set of PRDs/design docs) needs to be broken into parallel workstreams and executed with the shep CLI. Triggers include "break this down", "split into workstreams", "plan V6", "what should we build first", "run these in parallel", "dependency graph", "merge order", "worktree split", or any request to turn planning docs into running shep features. Produces a workstream plan first, then drives `shep feat new` / `shep feat start` wave by wave. Part of the Shep autonomous SDLC platform — https://shep.bot

Create a new RediSearch public release branch from master or prepare branch-out changes. Use when branching a version line such as 8.10 from master, setting initial version.h, copying GitHub branch protection, adapting release-branch CI gates, triggering validation, or documenting follow-up master-to-release sync policy.

Systematically bisect an end-to-end performance regression between two refs (tags/branches/commits) down to the exact offending commit(s). Use this when CI/customer benchmarks show one version is measurably slower than another and you need to attribute the cost to specific PRs.

Build GraalVM native images using the native-maven-plugin (org.graalvm.buildtools). Use this skill to build Java applications with Maven, configure pom.xml native image settings, run native tests, collect metadata, or resolve build or runtime issues.

Transforms images on demand via Netlify Image CDN's /.netlify/images endpoint with query parameters for resizing/cropping/format/quality. Use when adding image optimization or responsive images, converting formats (WebP/AVIF/PNG), generating thumbnails or blur placeholders, serving remote/third-party images through the CDN, allowlisting remote domains in netlify.toml, setting up image redirects or cache headers, building user-uploaded image pipelines, or debugging a 404 on /.netlify/images. Also covers framework image handling for Angular/Astro/Gatsby/Next.js/Nuxt.

Migrate Terraform provider resources and data sources from Plugin SDKv2 to the Plugin Framework: muxing both plugins in one provider (terraform-plugin-mux, tf5to6server), per-resource migration workflow, SDKv2-to-Framework schema mapping (ForceNew, ValidateFunc, DiffSuppressFunc, Default, Timeouts, blocks), null-vs-zero-value behavioral traps, and state-compatibility verification. Use when converting or translating SDKv2 resources to the Framework, setting up a muxed provider server, deciding whether a resource should be migrated at all, or debugging plan diffs and state errors that appeared after a migration.

Set up a local Grove environment for running code example tests. Use when the user asks to "set up Grove", "configure the test suite", "get started with Grove", "set up my environment", "I need to run Grove tests", or is working with Grove for the first time and needs prerequisites configured. Checks for required tools, installs dependencies, guides .env file setup, verifies MongoDB connectivity, and checks sample data availability.

Create a new Mattermost plugin from the starter template in the current directory. Use when creating a new plugin from scratch, scaffolding a Mattermost plugin, or bootstrapping a plugin project.

This skill should be used when the user asks to "run the outcome eval", "paired bare vs protocol", "which decisions did the protocol surface", "count what the AI asked or presented", "does /inquire surface what the request left out", or wants to see, from transcripts, which decisions reached the user as a question or something to recognize instead of having to be written into the opening prompt. Project-local contributor tooling.

Generate custom favicons from logos, text, or brand colours. Produces favicon.svg, favicon.ico, apple-touch-icon.png, icon-192/512.png, and web manifest. Use whenever the user wants a favicon, mentions replacing a CMS default favicon, converting a logo into a favicon, creating branded initials icons, or troubleshooting favicon not displaying / iOS black square / missing manifest.

Use when writing a Vitest test for a react-router useBlocker unsaved-changes guard in this repo — specifically an intentional-navigation handler (Edit / Submit / Cancel) that uses flushSync(() => setIsNavigating(true)) before navigate() to bypass the blocker. A test that reads the blocker predicate after act() passes even when flushSync is removed, so it does not guard the fix. Trigger on any test touching isNavigating, useBlocker, flushSync, or a *.hooks.js navigation-blocker handler.

Run, monitor, and fix frontend Cypress E2E tests. Handles local execution, CI monitoring, failure diagnosis, flaky test detection, and accessibility regression checks. Use this skill whenever the user mentions Cypress, E2E tests, end-to-end tests, test failures, CI failures, "CI is red", flaky tests, accessibility testing, or wants to run/debug/fix any frontend integration test — even if they don't say "e2e" explicitly.

Add a SLSA Generation step (YAML type: provenance) to an existing Harness pipeline to generate SLSA provenance and optionally attest with Cosign (keyless, key-based, or Vault). Supports container images (Docker, ECR, GCR, GAR, ACR, HAR) and Harness Local Stage artifacts. Place after image build/push; run sequentially after SBOM steps, not in parallel. Only works with existing pipelines. Use when asked to generate SLSA, add SLSA provenance, SLSA Generation step, attest SLSA, or configure SLSA Level 3 provenance in a pipeline. Trigger phrases: generate SLSA, SLSA generation, add SLSA step, SLSA provenance, attest SLSA, SlsaGeneration, provenance step, SLSA attestation, add provenance step.

Create or update component documentation in Sentry's MDX stories format. Use when asked to "document a component", "add stories", "write component docs", "create an mdx file", "add a stories.mdx", or document a design system component. Generates structured MDX with live demos, accessibility guidance, and auto-generated API docs from TypeScript types.