By ameenaliu
AI-driven product-video generation + multilingual localisation for social media. Brand-agnostic — each project supplies its own brand kit (collected per-workspace into <ProductVideos>/brand/brand.json). Four user-invocable skills: init-video-workspace (one-time setup + brand kit collection), generate (5-phase pipeline + Phase 0 brief drafting + 3 human approval gates + V8 animation-pacing + V9 callout-alignment vision review), translate (re-render captions + re-synthesise voiceover; ElevenLabs for en + 31 other languages; 9jaLingo for yo/ha/ig/pcm; captions-only fallback otherwise), update-brand-kit (refresh colors/logo/tagline/fonts/personas anytime). Pipeline: optionally extracts frames from a sample via ffmpeg + Claude vision; selects from 6 markdown script templates; composes Remotion .tsx that renders to 9:16 + 1:1 + 16:9 in one pass; generates voiceover + ambient bed via ElevenLabs (Starter $5/mo, commercial-licensed); muxes audio + video via ffmpeg into 3 final MP4s. 5 specialised agents (analyzer, scriptwriter, compositor, narrator, reviewer). 4 hooks (secrets-guard for sk_ + nl- + .env protection, large-media-guard, render-quality-check, pii-pattern-guard). 18 skills total (4 user-invocable + 3 conventions + brand-collection + 9jalingo-voices + 9 supporting). Credentials live in <ProductVideos>/.env (gitignored, hook-protected). The ProductVideos workspace is a local folder, optionally backed by a GitHub repo you supply. Works with Claude Code and OpenAI Codex.
[HARNESS INTERNAL — do not invoke directly] Phase 1 of the platform-product-video-harness `generate` workflow. Extracts frames from a reference video (`sample.mp4`) via ffmpeg, reads each PNG via Claude vision, produces a structured JSON outline (scene count, pacing, palette, suggested template) cached at `projects/<slug>/_cache/analysis.json`. Silent — no human gate; output feeds Phase 2 (scriptwriter). Never invoke outside the harness — use /platform-product-video-harness:generate.
[HARNESS INTERNAL — do not invoke directly] Phase 3 of the platform-product-video-harness `generate` workflow. Generates `compositions/<slug>.tsx` from the approved script.md, wires asset references via Remotion `staticFile()`, then runs `npx remotion render` three times (9:16, 1:1, 16:9) to produce silent preview MP4s in `_preview/`. Hosts GATE #2 for human visual approval before Phase 4. Never invoke outside the harness.
[HARNESS INTERNAL — do not invoke directly] Phase 4 of the platform-product-video-harness `generate` workflow. Loads ELEVENLABS_API_KEY from <ProductVideos>/.env (refuses to proceed and prints the remediation block if missing — never auto-writes .env). Calls ElevenLabs TTS per scene + Sound Effects API for an ambient BGM bed. Muxes audio + video via ffmpeg into 3 final MP4s in projects/<slug>/out/. Never invoke outside the harness.
[HARNESS INTERNAL — do not invoke directly] Phase 5 of the platform-product-video-harness `generate` workflow. Read-only verifier. Runs ffprobe on each of the 3 final MP4s to verify aspect ratio, duration (±2s of script target), audio levels (-16 LUFS voiceover, -28 LUFS BGM), no clipped frames, no missing captions, no hardcoded brand colors in the composition. Hosts GATE #3 for final human approval. Never writes any file. Never invoke outside the harness.
[HARNESS INTERNAL — do not invoke directly] Phase 2 of the platform-product-video-harness `generate` workflow. Picks the closest template from skills/script-templates/ based on the analyzer's outline + the user's `brief.md`, fills template variables, drafts `script.md` with scene shot list + voiceover lines + on-screen captions + per-scene durations. Hosts GATE #1 for human approval before Phase 3. Never invoke outside the harness.
9jaLingo TTS API — the secondary voice provider, used by /platform-product-video-harness:translate for Yoruba (yo), Hausa (ha), Igbo (ig), and Nigerian Pidgin (pcm). Covers all four launch-set languages with a single OpenAI-compatible endpoint. Credentials live in <ProductVideos>/.env as NAIJALINGO_API_KEY. ElevenLabs handles English + 28 other languages; 9jaLingo handles the four Nigerian languages; anything else falls back to captions-only.
How to render the same Remotion composition into 9:16, 1:1, and 16:9 in one render pass. The compositor registers 3 <Composition>s per video — same React component, different width/height — and a shared <SafeArea> + scene components adapt to the active aspect ratio at render time via useVideoConfig().
Canonical Q&A protocol for collecting brand kit inputs (name, colors, logo, tagline, fonts) and writing brand/brand.json + brand/logo.svg. Used by /init-video-workspace (Step 4.5, first-time setup) AND by /update-brand-kit (any-time update). Single source of truth so both paths use the same prompts, the same defaults, and the same random palette algorithm.
Pointer to the per-project brand kit canonical source at <ProductVideos>/brand/brand.json. Used by the scriptwriter (personas, banned phrases, tone of voice), compositor (colors, fonts, logo placement), and reviewer (verifies brand tokens are used, not hardcoded). The harness encodes process rules + a neutral starter brand.json template here; the brand itself lives in the ProductVideos repo and evolves with the brand.
How the scriptwriter derives burned-in captions from voiceover lines, syncs them to scene frame ranges, and respects per-platform caption constraints. Captions are mandatory for every voiceover line — Reels / Feed / LinkedIn / Shorts all default to muted playback.
A GitHub-native Claude Code + Codex plugin marketplace, designed to be installed once and shared across projects. It ships two plugins:
platform-sdlc-harness — a multi-agent SDLC workflow (orchestrator → planner / developer / reviewer / tester) with 3 human approval gates and 3 holistic review phases, driven by GitHub Issues + sub-issues + Projects (v2) and the gh CLI (no MCP server). Lifecycle: Epic → Feature → Story → Task; two-tier branching; Conventional Commits; gh PRs.platform-product-video-harness — Remotion + ElevenLabs product-video generation + multilingual localisation for social media, with a per-project brand kit.Both are stack-flexible (defaults: .NET 8 service/ + React 19 Turbo web/ + Expo mobile/) and configured per-repo by /init-workspace into .claude/context/.
Works with two AI coding tools. The plugins are the canonical source; running the relevant init scaffolds the equivalent setup for OpenAI Codex as well as Claude Code, so a team runs the same workflow + conventions whichever tool they use. A data-policy layer (hooks in Claude; AGENTS.md rules + optional pre-commit/CI guards elsewhere) keeps PII, customer data, and credentials away from the model.
The marketplace lives on GitHub at ameenaliu/harness-platform.
.claude/settings.jsonCommit this to a project repo's .claude/settings.json so every teammate gets the marketplace auto-registered and the plugins enabled when they open the repo in Claude Code (one-time trust prompt):
{
"extraKnownMarketplaces": {
"harness-platform": {
"source": { "source": "github", "repo": "ameenaliu/harness-platform" },
"autoUpdate": true
}
},
"enabledPlugins": {
"platform-sdlc-harness@harness-platform": true,
"platform-product-video-harness@harness-platform": true
}
}
/plugin marketplace add ameenaliu/harness-platform
/plugin install platform-sdlc-harness@harness-platform
/plugin install platform-product-video-harness@harness-platform
/init-workspace
type:*, surface:*, status:*) and the org Project (v2) board exist;.claude/context/platform-context.md + .claude/settings.local.json;AGENTS.md, .codex/agents/*.toml, .agents/skills/platform-*-workflow/ — so Codex runs the same workflow.| Requirement | Notes |
|---|---|
gh CLI | Authed (gh auth status) with scopes repo, project, read:org, workflow. |
| Stack toolchains | Per adopted surface: .NET 8 SDK (service), Node 20+/Yarn 4 (web), Expo/Node (mobile). |
| ffmpeg + ElevenLabs key | Only for the product-video plugin. |
harness-platform/
.claude-plugin/marketplace.json # 2 plugins
plugins/
platform-sdlc-harness/ # SDLC pipeline (GitHub Issues + Projects + gh)
platform-product-video-harness/ # Remotion + ElevenLabs videos (per-project brand)
scripts/ # marketplace maintenance (validate, conflicts, context-bloat)
README.md AGENTS.md LICENSE
See each plugin's README.md and CLAUDE.md for the full rules and workflows.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimExecutes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI-driven SDLC pipeline on GitHub — Issues + sub-issues + Projects (v2) on a service/web/mobile monorepo. Four-workflow pipeline: discovery-workflow (idea → Epic/Feature/Story/Task tree with hierarchical numbering E1/F1.1/S1.1.1 + Markdown issue bodies + native sub-issue Parent links + native Blocked-by issue dependencies + Project (v2) board membership) → backlog-workflow (refine a Story with issue/body edits, preserves numbering, manages dependencies) → dev-workflow (10-phase build with 3 gates + 3 holistic reviews + Phase 8 architecture/rules reconciliation, two-tier branching, gh PRs) → pr-review (post-PR holistic comments via gh). 4 specialized agents (planner with 5 modes, developer, reviewer with 5 modes incl. gh PR commenting, tester). 7 hooks (4 data-policy + 3 stack quality-check; the secret-scan + pii guards are covered by a hook behavior test suite + GitHub Actions CI). 30 skills total (adds github-rendering canonical structures + sub-issue/dependency protocol, plus capability/quality/security skills the dev/test/review roles drive — auto-installed by /init-workspace: agent-device + maestro-e2e + react-doctor + expo-doctor mobile/web verification, security-scan (Semgrep/Gitleaks/OSV-Scanner), dead-code-analysis (Knip/madge), dotnet-code-quality (Roslynator), bundle-budget (size-limit), migration-safety (EF Core), api-contract-check (oasdiff), observability (Serilog/OTel/Sentry); all advisory). Uses the gh CLI (no MCP server). Works with Claude Code and OpenAI Codex.
npx claudepluginhub ameenaliu/harness-platform --plugin platform-product-video-harnessComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.