Find the open-source solution that fits.

Apply the review layer to an HTML or Markdown artifact, select the exact phrase or element that is wrong, and add a note in place. Markup Mode compiles those comments into Markdown with quotes and locators so an agent can edit the intended spot without guessing. It runs entirely in the browser, changes only a generated copy, and declines client-rendered SPA shells by default.

Ultimate Meta Ads Skill turns Claude Code into a structured Facebook and Instagram advertising strategist. It combines evergreen strategy, copy, creative, funnel, scaling, and troubleshooting frameworks with a dated supplement that updates tracking, objectives, budgets, attribution, learning phases, and creative specifications for recent Meta behavior. Checklists and templates support launch and optimization. Because ad mechanics change quickly, the project recommends verifying current details against Meta’s official documentation and the advertiser’s own data; results are not guaranteed.

Pine Script v6 skill helps Claude Code write, debug, review, and migrate TradingView indicator code without inventing function signatures or confusing v5 with v6. A lookup script queries the offline reference for built-ins, typed arguments, return values, examples, and common v6 gotchas, while migration notes cover frequent version changes. The skill still treats the live compiler as the final check and requires Node.js 18+; its reference data is fetched on demand from a pinned upstream revision and integrity-checked.

rednote-writing-skill turns links, screenshots, notes, or rough ideas into finished Xiaohongshu posts, and can also critique an existing draft. Collage, Co-create, and Review modes preserve the author’s judgment and voice without inventing facts. After the body is written, a mechanical pass checks punctuation, automated-writing tells, and platform-risk terms, followed by a fresh human-sounding pass; titles and cover lines come last. The voice is tuned to one account through its real post examples, so another account needs new examples and positioning.

Use this Claude Code skill to turn a brand brief or an existing site into a detailed website design system covering typography, color, spacing, motion, and optional WebGL direction. Its hub-and-spoke knowledge base loads only the guidance needed for the task and produces four deliverables: a design specification, DTCG tokens, a motion specification, and an implementation plan. Building the site remains a separate stage.

Enterprise Architecture Team helps an organization establish and run an enterprise architecture function, from its charter and target-state vision to principles, standards, stakeholder engagement, maturity assessment, portfolio rationalization, and decision records. It is aligned with TOGAF while remaining vendor-neutral and can route a request to one artifact or a complete operating blueprint. A matching GitHub Copilot prompt file keeps the workflow available outside Claude.

UGC Video Skill writes prompts for short videos that feel filmed by a real person on a phone, with handheld movement, natural light, believable skin, and casual dialogue rather than polished advertising. Its renderer targets official APIs for Seedance, Kling, Veo, Sora, and Hailuo, adapting reference images and native audio where supported. Provider credentials come from environment variables, and each model has different parameters, input rules, and dependencies.

Augur turns a geopolitical, institutional, or social question into a resolution contract, gathers tagged material across several analytical lanes, maps incentives and structural pressure, and keeps only analogies whose mechanisms transfer. It produces a three-to-five-path scenario tree with probability bands, early indicators, and disconfirmers, then stores forecasts for Brier scoring after resolution. Forecasts are inherently uncertain and are intended for analysis and education, not investment, legal, financial, or security decisions.

Spoiler-Free Replay finds an official full-match football replay on Xiaohongshu, opens it from kickoff in fullscreen, and blocks score-bearing highlights, titles, comments, and other visible spoilers. The workflow first confirms that the match has ended without telling the user the result, then checks the player view before handing it over. It depends on Claude in Chrome and a logged-in Xiaohongshu web session, and its controls are currently platform-specific.

claude-guard scans Claude Code skills, hooks, MCP configurations, and settings for prompt-injection lures, download-and-execute commands, plaintext endpoints, broad permissions, hidden bidirectional characters, and committed secrets. It redacts secret values, groups findings by severity, and exits with a failure code when a High finding exists, making JSON output suitable for CI. The zero-dependency scanner is offline and heuristic; a clean result is not a sandbox or formal proof of safety.

Use this Claude Code skill to turn scripts into single-voice narration or multi-speaker podcast audio through ElevenLabs, including character-level timing for karaoke-style subtitles. Its cookbook focuses on practical Chinese pronunciation, pacing, emotion tags, chunking, MP3 merging, and browser synchronization issues. An ElevenLabs account and API key are required, and ffmpeg is needed for dialogue assembly and multi-chunk merging.

Use this Claude Code skill to scan a Plex library, find promising titles that are not yet owned, and explain each recommendation through movies already on the shelf. It publishes recommendation cards and an interactive proximity map, preserves earlier rounds, and updates the taste profile when suggested titles are later added. Plex is required; Tautulli adds per-user views, while Overseerr or Jellyseerr adds availability and request actions.

Surgical Fix guides a coding agent to reproduce one defect, map what may and must not change, capture a baseline, keep the patch within an explicit boundary, and verify both the corrected behavior and preserved behavior. Its lean edition relies on a five-step written workflow, while the guarded edition adds risk tiers, file claims, checkpoints, drift checks, and resumable evidence. These controls structure the work but do not prove semantic correctness or provide a sandbox.

Provide a visual mood and music direction, and the skill finds a track, detects strong beats, plans short shots, generates frames with Seedream, animates them with Kling, and assembles the result with ffmpeg. It is designed for roughly 20–30 second, 3:4 atmospheric vertical videos rather than dialogue-heavy or performance-driven scenes. The current workflow requires macOS and paid Seedream and Kling API access.

CareerProof organizes resumes, project notes, papers, slides, and other career records into a structured evidence vault, then maps that evidence to a target job description. It can produce tailored resume outlines, bullet candidates, gap analysis, and interview talking points while flagging unsupported claims and confidentiality limits. The system is designed for truthful application materials rather than automated job submission.

Suno Craft — LV wraps KIE.ai’s asynchronous Suno API in a resumable submit, wait, status, and fetch workflow. Beyond making songs, it supports sound effects, extensions, covers, stem separation, WAV and MIDI extraction, personas, voice cloning, video, cover art, and word-level lyrics timing, plus a field guide to music craft. A cost-tier gate asks before expensive batches, the API key stays in a local file, and generated files must be downloaded before temporary URLs expire. Users remain responsible for service terms, rights, and AI disclosure.

Point Track Coach at an audio bounce and optionally an Ableton project to inspect structure, tonal balance, stems, masking, rhythm, automation, and version-to-version changes. It produces an interactive local HTML report where charts, observations, and recommendations link back to audible moments. The full workflow is currently aimed at macOS and relies on tools such as ffmpeg, Python, librosa, and Demucs.

Use this Claude Code skill to make minified, bundled, or obfuscated JavaScript easier to inspect. The model proposes meaningful names while Babel applies each rename through the AST and scope graph, reducing the risk of collisions or broken shadowing. It also supports large webpack bundles, export identifiers, TypeScript class IIFEs, and iterative cleanup, with Node.js and Babel dependencies required.