creativeclaw — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited creativeclaw (Agent Skill) and scored it 65/100 (yellow). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 9 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 9 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
For each Creative Claw tool call that exposes it, pass the optional skills_used array with creativeclaw, any other Creative Claw skills actually followed, and guide entries in the form <skill-name>/<relative-guide-path> (for example, creativeclaw/references/workflow-basics.md). Include only skills and guides followed for that call. Omit attribution if the user declines tracking or the field is unavailable. Never send other plugin names, private data, or local paths.
Not connected yet? If no Creative Claw tools (such as list_models or generate_image) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the Creative Claw plugin page in Claude, then the Connectors tab, press Connect, press Add if an "Add custom connector" dialog opens, and sign in. In Claude Code they run /mcp instead. Then they ask again. Do not substitute other tools or describe a result that was not generated.
Read shared execution guidance once per task before using tools. It covers existing authorization, model discovery, optional cost checks, imports, and recovery.
Use the Creative Claw MCP server as a media workspace: source durable assets, apply a brand theme, choose a model by capability, generate or process media, and save results for reuse.
Use manage_account for the current balance and for recent generations with their recorded charges and refunds. Read account and cost guidance before interpreting charges. Use estimate_generation for future quotes, not the cost of a past generation. Do not submit feedback automatically for an account question.
Purchases and plans are handled on the Creative Claw website, not in chat. Do not start, price, or recommend a purchase; if asked, say so and share only an account link a tool returned.
search_assets when the request refers to saved media, an existing project, or identity/product continuity. Skip asset searches for standalone generation with no reuse requirement. Use get_theme for branded work.list_models({ category }) when choosing or checking availability; use get_model_params for a known selected model. Reuse current-task schemas until a model/operation changes or an error indicates they need refreshing.references/platform-upload.md before importing attached or local media. Pass Creative Claw URLs to generation and processing tools.text.estimate_generation only when the user asks about cost, balance, affordability, or supplies a budget constraint. An estimate is information for the user: share it, then continue with the requested work when it fits what they said. Ask about material scope changes, missing essential choices, and whenever a tool result asks for confirmation.check_job when another tool needs the completed URL, or when no viewer is monitoring the job. Never claim completion from a job ID alone.update_asset after completion. Use stable tags across a project.references/platform-client.md. Use the exposed tool schema for top-level fields and get_model_params for model-specific settings.submit_feedback for bugs, missing features or models, confusing flows, generation-quality problems and praise that the user expresses or you observe. Say briefly that you reported it, and do not report when the user asks you not to. Keep reports specific and do not add refund requests. Read references/workflows/feedback.md before reporting.get_model_params and the voiceover workflow.creativeclaw-render-html when the user explicitly asks for HTML/CSS, HyperFrames, or code-driven rendering, supplies HTML, accepts that method, or explicitly asks for a motion-graphics video: motion graphics, kinetic typography, animated text or titles, an animated infographic or explainer, or UI-style animation. A request for a video, an ad, or an explainer without those words stays with the video skills; when it is unclear whether the user wants filmed-looking footage or designed motion, ask one question. It also finds HTML-video examples. An exact text watermark for overlay_images may use render_html_image with a transparent background. Ordinary image or video requests stay with the generative skills.| User wants | Primary route |
|---|---|
| Understand balance, past generation costs, or charges and refunds | manage_account, following account guidance |
| Generate or edit one general image | creativeclaw-generate-image |
| Create a consistent product image set | creativeclaw-product-photoshoot |
| Make a character copy a recorded performance or retain movement across wardrobe variants | creativeclaw-generate-video, starting with motion transfer to resolve the driving video and appearance image |
| Swap, replace or recast people in existing footage: face swaps, "put me in this video", several people at once | creativeclaw-swap-characters (swap_video_characters) |
| Generate, extend, reframe, or transform one video clip | creativeclaw-generate-video |
| Plan a script, shot list, or storyboard | creativeclaw-plan-video |
| Produce a complete multi-shot film | creativeclaw-build-film |
| Create a creator-style product ad | creativeclaw-create-ugc-ad |
| Make a set of ad variations from one product shot or existing ad (new hooks, voiceovers, voices or captions) | creativeclaw-ad-variations |
| Generate narration, dialogue, or speech | creativeclaw-generate-voiceover |
| Design a new synthetic voice from a description | creativeclaw-generate-voiceover (design_voice) |
| Generate a score, music bed, sting, jingle, theme, or song | creativeclaw-generate-music |
| Generate sound effects, ambience, Foley, loops, impacts, or UI cues | creativeclaw-generate-sound-effects |
| Clone a consented voice from a recording | creativeclaw-clone-voice |
| Browse or adapt curated examples when asked | examples guidance |
| Explicitly render HTML/CSS as a PNG, or HTML/HyperFrames motion as video | creativeclaw-render-html |
| Motion graphics, kinetic typography, animated titles, or an animated explainer the user explicitly asks for | creativeclaw-render-html (the video agent) |
| Add or create an intro/outro around existing video | creativeclaw-edit-media |
| Create a personal avatar from photos or a reusable identity sheet | creativeclaw-create-avatar |
| Create or update a reusable Character | creativeclaw-create-character |
| Report product or quality feedback | creativeclaw-submit-feedback |
| Find, import, name, tag, reuse, or delete media | references/workflows/asset-library.md |
| Create, inspect, edit, or apply a brand theme | references/workflows/brand-theme.md |
| Trim, resize, caption, transcribe, clean, or combine existing media | creativeclaw-edit-media |
| Burn a transparent logo or copyright image onto a finished video | creativeclaw-edit-media, using overlay_images; read assembly guidance |
| Make a video from existing timed images, optional video clips, and optional audio | creativeclaw-edit-media, using stitch_clips (never for new AI footage, which is generate_video); read assembly guidance |
| Select highlights from long footage and create vertical Reels | creativeclaw-create-reels |
| Cut, reorder, and reframe chosen video moments | creativeclaw-edit-media (cut_and_reframe_video) |
| Learn what Creative Claw can do | references/workflows/onboard.md |
| Run first-time setup, get started, or take a guided tour | creativeclaw-setup |
Use an explicit outcome over a generic modality. If the user names a model, keep the outcome skill in control and use the matching packaged model reference for prompt and reference details. Use this root skill for requests that span outcomes or do not have one clear owner. Read the matching workflow before calling a mutating or paid tool.
image/nano-banana-2 (Nano Banana 2) for most generation and editing, including targeted corrections that should preserve the existing scene. It balances quality, speed, and cost. Use image/gpt-image-2.5-flare for fast OpenAI image work, and use image/gpt-image-2.5-sunburst for complex professional assets, typography, and controlled edits. Use image/seedream-5-pro for product and marketing imagery. Nano Banana Pro remains available when explicitly selected. After a model moderation refusal, Seedream may also be offered as the tool's suggested alternative, with user confirmation before another paid generation; it applies its own safety checks and may still reject the request. For a transparent background, use GPT Image 2.5 (Flare or Sunburst) with its transparent background option, or remove_background. Use other image models only when the user asks for them.video/gemini-omni-flash. Recommend video/seedance-2.5 as the premium cinematic model for native-audio, high-end, reference-rich, first/last-frame or long (up to 30 s) work; for a cheaper preview, a 480p request is a usable draft, and extras.draft_job_id finalizes that same take at 1080p within 7 days (720p starts a new take). Use video/minimax-h3-max for fast cinematic native-audio work, or video/flux-3-max for text, first/last frames or timed image keyframes (5 to 20 seconds at 720p/1080p). FLUX accepts no video/audio references; keep H3 Max or Seedance 2.5 for those. Both H3 Max and FLUX 3 Max are available before purchase and eligible for the free first video. Use video/minimax-h3-max-turbo (H3 Max Fast) for cheap, fast drafts. Use Seedance Mini only when the user asks for it. For existing footage, route through references/workflows/edit-video.md instead of applying this generation ranking; video/minimax-h3-max-extend is the default for extending a clip. Never recommend or proactively route to an LTX or DreamActor model. Use Wan only when explicitly requested; recommend Seedance 2.5 instead. For document or webpage briefs, read the content and prepare a Seedance prompt with supported media references; do not pass Wan's file_url or web_url fields to Seedance.speech/elevenlabs-v4 for all non-cloned speech, including stock voices, expressive delivery, and dialogue. Speak a clone with its provider's model: a Cartesia clone with speech/cartesia-sonic; an ElevenLabs clone with speech/elevenlabs-v2 for a steady read or speech/elevenlabs-v4 for expressive delivery or dialogue. New clones use Cartesia unless the user chooses ElevenLabs. Designed voices speak with speech/elevenlabs-v4 (ElevenLabs designs) or speech/gemini-3.8-flash-tts (Google designs). To change who is speaking in an existing recording, use speech/cartesia-voice-changer. ElevenLabs v3 is legacy; use it only when the user asks for it. Never clone without consent or silently switch providers. Honor explicitly requested supported models. Load creativeclaw-generate-voiceover for the selected model's reference and current settings.generate_sound_effect with sfx/elevenlabs-sound-v2 for sound effects, Foley, ambience, and loops. Use generate_music for scores, music beds, stings, jingles, and songs; creativeclaw-generate-music picks the music model. Do not pass non-speech model IDs to generate_speech.Verify missing capabilities with runtime discovery, then reuse the selected schema for unchanged operations within the task.
For image prompting, load the selected image model reference. Video outcome skills package their selected video model references. For speech, load creativeclaw-generate-voiceover and only its selected model guide. There are no standalone model skills; the outcome workflow owns authorization, execution and delivery.
For new generative video, follow the selected video skill's reference-first workflow: one clean keyframe per shot with generate_image at the video's aspect ratio, built from approved identity, product, or location anchors, then pass it to the video model. Later keyframes also take the first approved keyframe as a reference so the shots match. Tell the user the plan includes one keyframe image per shot before making them. Skip them when the user asks for direct text-to-video, supplies a ready shot image, or is editing footage.
references/tool-catalog.md — current tool routing by purpose.references/workflows/examples.md — the curated examples catalog.references/async-jobs.md — queued-job handling.references/platform-upload.md — attachment, local-file, picker, and URL ingestion.references/platform-client.md — client capability and connection rules.references/platform-dimensions.md — common image and video sizes.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.