Claude Skills by legioncodeinc

Writes the CHANGELOG.md and release notes for the @deeplake/hivemind npm package and CLI. Use when the user says \\\\\\\"write the changelog entry\\\\\\\", \\\\\\\"what version bump is this\\\\\\\", \\\\\\\"draft the release notes\\\\\\\", \\\\\\\"is this a breaking change\\\\\\\", \\\\\\\"we just shipped X\\\\\\\", or when a release is about to cut and the change needs to be communicated to developers who install via npm and to the six-harness users. Covers Keep-a-Changelog format for a CLI/...

Chrome DevTools Protocol and Chromium development for remote debugging, profiles, protocol inspection, source builds, and browser-engine diagnosis. Use for Chrome or Chromium engineering.

CI and release engineering for GitHub Actions + SvelteKit on Vercel: job design, Vercel/Actions interaction, environment promotion, Neon/Drizzle migration gating, Doppler/OIDC secrets, caching, required checks, release automation. Also covers npm-package publishing (legacy case).

Forensic investigation methodology for software-development and agency-services engagements where a client has been overcharged, defrauded, or materially injured by a vendor and possesses a paper trail (invoices, emails, git repo, audit reports). Produces an 11-deliverable evidence packet — master forensic report, agency-services subreport, attorney legal memo, plain-language client report, 51-tab invoice spreadsheet, and a 6-document pre-litigation pack. Trigger whenever the user describes t...

Code review culture and PR lifecycle specialist -- PR description templates (six-element structure), review checklists (three-tier taxonomy: blocker/suggestion/nit), async-first review norms for remote teams, the small-PR discipline (400-line threshold backed by DORA 2025 data), rubber-stamp anti-pattern detection, and the review-as-mentorship lens. Use when the user says \\\\\\\"audit our PR culture\\\\\\\", \\\\\\\"write a PR description\\\\\\\", \\\\\\\"create a review checklist\\\\\\\", \...

Outbound sales specialist for founders running cold email. Covers Apollo / Clay / Smartlead / Instantly / Lemlist tool selection, email deliverability and domain warmup, multi-touch sequence design (3-5 steps), AI personalization without slop (Clay Claygent SKIP rule), reply classification and disqualification, and list hygiene. Use when the user says "set up cold outreach", "my cold email is landing in spam", "write a cold email sequence", "set up Clay personalization", "Apollo vs Instantly"...

Builds an XLSX competitor-landscape workbook and a brand-matched PDF report from scratch: research sweep, category taxonomy, feature-gap analysis, computed market-pattern insights, and sales battlecards. Invoke on phrases like build a competitor comparison spreadsheet, research our competitors, make a battlecard deck, competitive landscape report, or feature gap analysis against competitors.

CRM connectivity specialist for HubSpot, Salesforce, Pipedrive, Attio, Folk, Close, and Copper -- bi-directional sync design, the contact-vs-lead-vs-account taxonomy, merge/dedupe, and the native-vs-Zapier-vs-Merge.dev architecture trade-off. Use when the user says "integrate with HubSpot", "bi-directional CRM sync", "CRM field mapping", "Merge.dev or native API?", "dedup contacts in our CRM", "lead enrichment strategy", "sync conflict resolution", "Salesforce Lead vs Contact", "Attio API pro...

Scheduled-job specialist for cron expression authoring, platform-specific limits (Vercel Cron, Cloudflare Cron Triggers, GitHub Actions schedule), distributed-cron correctness (exactly-once execution, leader election, idempotency), timezone and DST safety, retry-on-failure patterns, and the \\\\\\\"did the cron run?\\\\\\\" observability loop (Healthchecks.io, Cronitor, self-hosted heartbeat tables). Use when the user says \\\\\\\"write a cron expression\\\\\\\", \\\\\\\"set up Vercel Cron\\\...

The \\\\\\\"upload your spreadsheet\\\\\\\" implementation arsenal for React/Next.js products. Covers library selection (papaparse, SheetJS, exceljs), streaming-parse for 100MB+ files, the column-mapping UX wizard, managed importers (OneSchema, Flatfile, dromo) vs self-hosted (react-spreadsheet-import), Zod row validation, CSV injection prevention, encoding edge cases, and styled XLSX export. Use when the user says \\\\\\\"build a CSV import\\\\\\\", \\\\\\\"add XLSX upload\\\\\\\", \\\\\\\"s...

Equips cursor-ide-worker-bee to own Hivemind's Cursor surface: the Cursor 1.7+ hooks harness (~/.cursor/hooks.json, 6 lifecycle events) wired by src/cli/install-cursor.ts, the first-party VS Code/Cursor extension at harnesses/cursor/extension/, registering the Hivemind MCP server (src/mcp/server.ts) in Cursor, and the .cursor/ colony this repo ships (rules .mdc format, agents, skills/Stingers, the-beekeeper/the-smoker commands, model-comparison-matrix). Use when the task touches Cursor hook w...

The workspace has the official Cursor SDK plugin installed, which includes a `cursor-sdk` SKILL.md. This is the authoritative in-IDE reference for `@cursor/sdk` and defines the three invocation patterns, top five traps, local vs cloud runtime distinction, auth setup, model selection, and production best practices. `cursor-ide-stinger`'s `guides/04-sdk-api.md` should align with and extend this skill - not duplicate it.

Support stack specialist for SaaS products — selects the right tool from Plain, Pylon, Front, Help Scout, and Intercom; configures shared inboxes; designs AI-deflection flows (Fin 2.0, Ari, Crisp Bot); sets SLA tiers; wires integrations to Slack, Linear, and Notion; and provides a founder-as-support playbook for teams of 1-3. Invoke when choosing a support tool, auditing an existing stack, configuring AI deflection, designing SLA policy, or setting up escalation to Linear. Do NOT invoke for c...

Audits and implements dark mode for React/Next.js: CSS tokens, next-themes wiring, FOWT prevention, SSR hydration, Tailwind v4 config, multi-brand theming. Use for dark mode setup or flashing bugs.

Designs, reviews, and migrates PostgreSQL data layers: schema, indexing, zero-downtime migrations, performance, ORM choice, and serverless DB platform selection. Use when the user says \\\\\\\"design this schema\\\\\\\", \\\\\\\"review this migration\\\\\\\", \\\\\\\"is this index right?\\\\\\\", \\\\\\\"should this be jsonb or columns?\\\\\\\", \\\\\\\"we need a NOT NULL on a 100M-row table\\\\\\\", \\\\\\\"Drizzle or Prisma?\\\\\\\", \\\\\\\"Supabase or Neon?\\\\\\\", \\\\\\\"production que...

Designs, reviews, and heals the Hivemind Deep Lake data layer - the 7-table ColumnDef schema, USING deeplake DDL, FLOAT4[] embeddings, additive schema healing, append-only version-bump writes, deeplake_index / vector / hybrid search, DeeplakeApi querying, SQL guards, dataset versioning, and BYOC storage. Use when the user says "design this table", "review this ColumnDef", "is this index right?", "should this be a JSONB column or a tensor?", "we need a new NOT NULL column on the memory table",...

npm supply-chain hygiene specialist: dependency updates, lockfile discipline, audit triage, SBOM, and provenance. Use when auditing dependencies, fixing lockfile noise, or checking publish safety.

Bootstraps a complete design system from scratch for a product. Produces the seven-artifact folder: master design brief, master tokens CSS, utility layer CSS, per-component specs, per-screen specs, static HTML examples, and a README. Use when the user says \\\\\\\\\\\\\\\"set up a design system\\\\\\\\\\\\\\\", \\\\\\\\\\\\\\\"bootstrap ux-ui\\\\\\\\\\\\\\\", \\\\\\\\\\\\\\\"scaffold the design language\\\\\\\\\\\\\\\", \\\\\\\\\\\\\\\"I need a design brief + tokens for {product}\\\\\\\\\\\\\...

Designs, audits, and authors Docker / Docker Compose / GitHub Actions / Depot pipelines for Node / Next.js / TypeScript stacks. Use when the user says \\\\\\\"review my Dockerfile\\\\\\\", \\\\\\\"design our CI pipeline\\\\\\\", \\\\\\\"audit our workflow security\\\\\\\", \\\\\\\"migrate to Depot\\\\\\\", \\\\\\\"add a healthcheck to compose\\\\\\\", \\\\\\\"this build is slow\\\\\\\", \\\\\\\"we leaked a secret in CI\\\\\\\", or when `devops-worker-bee` is invoked. Do NOT use for cloud prov...

Discord bot and application specialist for discord.js (v14/v15), discord.py 2.x, and Serenity (Rust). Covers slash commands, interactive components (buttons, select menus, modals), voice pipeline (Lavalink 4 + DAVE-compliant clients), gateway-vs-HTTP-endpoint architecture, rate-limit handling, shard management, and the bot verification path past 100 servers. Use when building, reviewing, or debugging any Discord bot or application: SDK selection, command registration, component flows, voice q...

Continuous product discovery coach — Teresa Torres interview cadence, Opportunity Solution Trees, Jobs-to-be-Done interviews, prototype testing, and the "build less, learn more" loop. Use when the user says "run a discovery session", "build an OST", "write an interview script", "map our assumptions", "design a prototype experiment", "weekly discovery summary", or when a team is unsure what to build next and needs to run discovery before planning. Do NOT use for shipped-feature usability testi...

Documentation-site infrastructure specialist, platform selection (Docusaurus v3/v4, Mintlify, GitBook, MkDocs Material, Nextra v4, Starlight/Astro, Fern), the Diátaxis content pyramid, docs-as-code CI pipelines, and search setup (Algolia DocSearch, pagefind). Use when the user says \\\\\\\"pick a docs platform\\\\\\\", \\\\\\\"set up Docusaurus\\\\\\\", \\\\\\\"migrate from GitBook\\\\\\\", \\\\\\\"add search to our docs\\\\\\\", \\\\\\\"docs-as-code CI\\\\\\\", \\\\\\\"Mintlify vs Starlight\...

Doppler secrets manager for SvelteKit on Vercel - doppler run/secrets CLI, project/config model, Vercel sync, service tokens, rotation, audit logs, GitHub Actions CI, replacing .env files.

Electron application engineering for process boundaries, preload APIs, IPC, sandboxing, packaging, updates, and desktop verification. Use for Electron app implementation or review.

ElevenLabs API integration for speech, voices, streaming, webhooks, usage, and key boundaries. Use for ElevenLabs API implementation, review, or troubleshooting.

Picks and runs embedding models: hosted (OpenAI, Cohere, Voyage) vs self-hosted, cost tradeoffs, batching, caching. Use when choosing, swapping, or debugging an embedding model.

Software estimation and forecasting specialist. Covers relative-sizing frameworks (story points, Fibonacci, T-shirt sizing, Planning Poker), the NoEstimates movement and its evidence base, the planning-fallacy literature explaining why estimates are systematically wrong, and cycle-time / throughput-based probabilistic forecasting (Monte Carlo simulation, percentile-based delivery predictions). Invoke when the user says \\\\\\\"our story points mean nothing\\\\\\\", \\\\\\\"should we use NoEst...

Production-focused font loading strategy specialist for 2026 web performance. Reviews, implements, and audits the web font loading pipeline: font-display descriptor selection (swap/optional/fallback/block/auto) with CLS risk analysis; the link rel=preload strategy for critical fonts; variable-font + Unicode-range subsetting pipeline (pyftsubset, glyphhanger, subfont); next/font App Router integration; and CLS-from-font-swap elimination via size-adjust, ascent-override, and metric-matched fall...

Initializes a repo to a healthy baseline: library/ docs, GitHub CI, README, .gitignore, CODEOWNERS, SECURITY.md, CHANGELOG.md. Use when bootstrapping a repo or auditing one for missing hygiene files.

Git mastery specialist - interactive rebase (squash, fixup, reword, drop), conflict resolution, history rewriting (git filter-repo, BFG), reset/reflog recovery, worktrees for parallel branches, hooks (Husky, lefthook), submodules vs subtrees, Git LFS, partial clone, and sparse checkout. Use when the user says \\\\\\\"squash my commits\\\\\\\", \\\\\\\"I pushed a secret\\\\\\\", \\\\\\\"my repo is huge\\\\\\\", \\\\\\\"undo that rebase\\\\\\\", \\\\\\\"work on two branches at once\\\\\\\", \\\...

Repository hygiene auditor for GitHub repos - branching strategy, branch protection rulesets, PR culture, commit history (Conventional Commits), CI workflow density, README/docs presence, .gitignore coverage, CODEOWNERS, issue/PR templates, and repo settings (merge strategy, secret scanning, auto-delete). Use when the user says \\\\\\\"audit this repo\\\\\\\", \\\\\\\"repo health check\\\\\\\", \\\\\\\"review our branching strategy\\\\\\\", \\\\\\\"check branch protection\\\\\\\", \\\\\\\"COD...

Go specialist for modules, toolchains, vendoring and fork-in-tree freezes, cgo .so plugin ABI, project layout, and builds. Use for go.mod, replace directives, vendoring upstream repos, plugin crashes.

GoHighLevel API authority - OAuth vs Private Integration Tokens, contacts/opportunities/calendars, inbound/outbound webhooks, rate limits, Marketplace apps. Use for GoHighLevel/HighLevel integration.

Cross-harness capability integration for The Hive's four harnesses (Claude Code, Cursor, ChatGPT Codex, Claude Cowork). Covers per-harness component placement (rules, commands, agents, skills, plugins), the wiring-mechanism decision (hooks vs MCP vs native extension vs plain instruction file), hook/lifecycle events per harness, MCP registration per harness (JSON vs TOML, Cowork connector reachability), capability detection/graceful degradation, and portability (spec-six frontmatter, AGENTS.md...

HeyGen API integration for video generation, avatars, assets, webhooks, limits, and safe asynchronous delivery. Use for HeyGen API implementation or debugging.

HighLevel AI Studio specialist for Vibe sites, Content AI, Funnel & Website AI, and WordPress AI pages. Use for HighLevel AI content, site building, publishing, or troubleshooting.

Applicant Tracking Systems specialist -- Ashby, Greenhouse, Workable, Lever, Rippling Recruiting, Pinpoint -- platform selection decision matrix, pipeline-stage design, scorecard calibration (BARS, debrief-before-submit), D&I/EEOC reporting, take-home-test ethics (the 2-hour paid threshold, anonymous grading), sourcing-tool integrations (Gem, hireEZ, LinkedIn RSC), and the ATS-to-HRIS handoff (especially Rippling). Invoke when the user says "which ATS should we use", "audit our scorecards", "...

HR + payroll + EOR decision specialist for early-stage to growth-stage software companies. Owns domestic payroll platform selection (Gusto, Rippling, Justworks), international contractor management and EOR (Deel, Remote.com, Oyster, Rippling Global), the W-2/1099/EOR/PEO classification matrix, equity admin handoff (Carta), and benefits brokerage. Invoke when the user says "Gusto vs Rippling", "set up payroll", "EOR for international hire", "contractor vs employee", "W-2 or 1099?", "Deel vs Re...

'HTTP and REST protocol authority: audits HTTP method safety/idempotency contracts, status-code honesty, header correctness (Cache-Control, ETag, Vary, CORS), conditional and range requests, HTTP/2 + HTTP/3 readiness, and REST architectural-style compliance. Activate when the user says \\\\\\\"audit this API\\\\\\\", \\\\\\\"is this status code correct?\\\\\\\", \\\\\\\"why is CORS failing?\\\\\\\", \\\\\\\"explain preflight\\\\\\\", \\\\\\\"PUT vs PATCH\\\\\\\", \\\\\\\"HTTP/3 ready?\\\\\\\"...

Icon-system specialist for React/Next.js: library selection (Lucide, Heroicons, Tabler, Phosphor, Iconify), tree-shake-vs-SVG-sprite trade-off, dynamic-import-by-name pattern, custom SVG component authoring, and the accessibility contract (aria-hidden for decorative icons, aria-label for semantic icons, accessible name for icon buttons). Use when choosing an icon library, debugging bundle-size regressions from icon imports, wiring a dynamic icon loader, building a custom SVG wrapper, or audit...

Image optimization specialist for React/Next.js and HTML contexts: AVIF/WebP format selection (AVIF is the 2026 production default), responsive srcset/sizes calculus, blur placeholders (LQIP via Sharp, BlurHash-as-CSS-gradient, ThumbHash), next/image remote patterns and the Next.js 16 priority→preload shift, and CLI tooling (Sharp Node API, Squoosh CLI for one-offs). Use when the user says \\\\\\\"optimize my images\\\\\\\", \\\\\\\"convert to AVIF\\\\\\\", \\\\\\\"set up srcset\\\\\\\", \\\\...

Operates the entire Impeccable design system (pbakaus/impeccable, Apache-2.0) for the Bee Army: the four-phase loop (Start to Iterate to Polish to Maintain), the context contract (PRODUCT.md + DESIGN.md + surface briefs), the 23-command vocabulary, the deterministic 59-rule anti-slop detector gate, hooks, live mode, and native playbooks. Use when impeccable-worker-bee is invoked, or for ANY frontend UI/UX/design implementation, redesign, refinement, new surface, component work, or design-syst...

Company formation decision toolkit for software startup founders. Covers formation platform selection (Stripe Atlas, Clerky, Doola, Firstbase), entity type advice (Delaware C-Corp vs LLC vs international), EIN workflow, startup banking (Mercury, Brex, Relay), bookkeeping (Pilot, Bench), and the minimum founder-paperwork checklist including the 83(b) election. Activate when the user says "incorporate my startup", "which formation platform should I use", "Stripe Atlas vs Clerky", "set up Mercur...

Cap-table management and fundraising paperwork specialist for startup founders -- Carta, Pulley, Cake Equity, Capdesk (AngelList Stack sunset August 2026), SAFEs (YC post-money standard), priced rounds (Series A+ term sheets), 409A valuations, option pool sizing and refresh, vesting schedules (4-year/1-year cliff, double-trigger), and investor data-room preparation. Use when the user says "set up a cap table", "Carta vs Pulley", "SAFE mechanics", "409A valuation", "option pool", "vesting sche...

Kanban method specialist: WIP limit design and enforcement, flow-metric calculation (cycle time, lead time, throughput, flow efficiency), Little's Law diagnostics, visual-board design, class-of-service policies, cumulative-flow-diagram interpretation, and tool-specific implementation (Linear, Jira, GitHub Projects). Use when the user says \\\\\\\\\\\\\\\"set up WIP limits\\\\\\\\\\\\\\\", \\\\\\\\\\\\\\\"calculate cycle time\\\\\\\\\\\\\\\", \\\\\\\\\\\\\\\"apply Little's Law\\\\\\\\\\\\\\\",...

Customer-facing knowledge bases — Intercom Articles, Help Scout Docs, ReadMe.com, Document360, HelpJuice, Zendesk Guide — search-first design, AI deflection (chat-with-your-docs), versioning, multi-language, the analytics-driven content-gap loop. Use when the user says "pick a KB platform", "set up a help center", "migrate Zendesk Guide", "add AI deflection to our docs", "fix our search no-results", "localize our KB", or invokes `knowledge-base-help-center-worker-bee`. Do NOT use for support ...

Authors narrative knowledge documentation for any repository - the human-readable, technically deep domain docs that live in `library/knowledge/private/{domain}/`. Covers system overviews, architecture narratives, data schemas, API patterns, security models, coding standards, and operational runbooks. Works from ADRs and PRDs as source material; produces Mermaid diagrams, SQL DDL, TypeScript samples, and sequence diagrams. Distinct from library-stinger: library-stinger owns PRDs and IRDs; kno...

SaaS legal document generation and maintenance specialist. Covers Terms of Service, Privacy Policy, DPA, MSA, and Cookie Notice using the template+lawyer-review path. Anchored in Termly/Iubenda generators and GDPR/CCPA/Quebec Law 25/LGPD compliance postures. Use when the user says "generate a privacy policy", "draft a DPA", "set up our Terms of Service", "review a customer DPA redline", "which legal doc generator should I use", "GDPR compliance for SaaS", or when legal-docs-worker-bee is invo...

Equips library-worker-bee with the documentation lifecycle - knowledge-base authoring (public vs private audience split), feature PRD authoring (prd-{###}-{slug}/ with index + sub-PRDs + qa/), issue IRD authoring (ird-{###}-{slug}/ with index + qa/), backwards-PRD generation, sync audits / drift detection, and lifecycle moves (backlog/in-work/completed) against this repo's schema v2 library/. Use when initializing a library/, ingesting issues, planning features, writing knowledge docs, runnin...

Writes evidence-grounded hot and warm lead follow-up emails. Use for lead classification, sequences, cadence, suppression, QA, and measurement. Not for cold outreach or support tickets.