- name
SKILL.md
スキルファイルは公開元のリポジトリに置かれたままです。
コピーしたコマンドをターミナルに貼り付けてください。この SKILL.md がそのエージェントにインストールされます。
npx skills add wiltodelta/remove-ai-watermarks --skill provider-oracles -a cursor -yコピーしたコマンドをターミナルに貼り付けてください。この SKILL.md がそのエージェントにインストールされます。
npx skills add wiltodelta/remove-ai-watermarks --skill provider-oracles -a claude-code -yコピーしたコマンドをターミナルに貼り付けてください。この SKILL.md がそのエージェントにインストールされます。
npx skills add wiltodelta/remove-ai-watermarks --skill provider-oracles -a codex -yコピーしたコマンドをターミナルに貼り付けてください。この SKILL.md がそのエージェントにインストールされます。
npx skills add wiltodelta/remove-ai-watermarks --skill provider-oracles -a grok -yコピーしたメッセージを Grok Bot のチャットで送信してください。Bot がこの SKILL.md を GitHub から取得し、すべての Bot が共有するスキルに追加します。
Install this skill: https://github.com/wiltodelta/remove-ai-watermarks/tree/HEAD/.claude/skills/provider-oracles公開元より
Read docs/provider-oracles.md for surface keys, slot schema, preparation, and
recording commands. Use scripts/provider_oracles.py for surface discovery, slot
validation, upload preparation, result recording, and integrity verification.
Named slots live in the gitignored repository-local
.oracle-slots.json. Never commit that file. Pass --slot NAME to use it;
pass --slots PATH only to override the local path.
Never substitute one provider's negative verdict for another provider's signal. Do not optimize candidates adaptively against an external oracle. Keep each submitted artifact frozen inside its own batch and bind the result to that artifact's hash. Do not erase failures.
Anyone doing the task may run the configured checks. Do not ask who is allowed to use the oracle, and do not ask for confirmation before moving to the next surface, slot, or route.
Walk plan PROVIDER. That command only prints the order. The order itself stays:
openai-api. Microsoft is
microsoft-api.openai-web and Microsoft is
microsoft-web, both through isolated Playwright. Meta is meta-web
through isolated Playwright. Google is gemini-web on the user's existing
real Chrome, then synthid-web at https://synthid.com/ through isolated
Playwright. Meta and Google have no API surface, so their first Web oracle is
the first row.When the current surface, slot, or route is exhausted by a refusal, quota response, transport error, or indeterminate verdict, record the exact response and run the next item as its own command. One adapter call still makes one request.
Before starting, identify the finite set of configured slots and prepare one
immutable batch per slot. After a quota refusal or service failure, record the
exact response, leave that slot's remaining rows unsubmitted, and continue
through the remaining slots in the order above. Exception: when gemini-web
returns an explicit modality-level quota refusal (such as the video modality quota has been exceeded) or an active modality quota-hold record (status: "active") exists for that video or audio modality, halt same-modality
gemini-web account rotation rather than switching /u/N/ Google accounts to
evade the hold; keep prepared Gemini batches frozen and reuse exact prior
upload-hash verdicts.
For clean-control or processed video and audio uploads, pass
--require-clean-media to prepare so residual AI metadata, invisible hints,
and visible provider marks are rejected up front and per-stream decoded SHA-256
digests (stream_hashes) are bound into manifest.json.
Submit each frozen artifact at most once per slot in that pass. Preserve inconclusive results and disagreements between accounts. Stop when the plan is complete or no configured usable slot or route remains, and report remaining rows. Do not start a new login. Do not change candidate pixels. An API result is not replaced by the Web result. Run Web as its own acknowledged check and keep its verdict separate.
Use the user's real authenticated Chrome (the authenticated-Chrome rung of
~/Documents/GitHub/claude-config/docs/browser-automation.md). Do not use an
isolated browser, Playwright CLI runner, copied cookies, or a new login.
browser_profile against the available
real Chrome profile and navigate directly to
https://gemini.google.com/u/<google_account_index>/app.gemini-web batch outside the repository.
For every image check, visually inspect the source first. Remove every visible
AI-provider logo or label with the project's visible-mark remover, derive all
paired controls and candidates from that cleaned image, and let prepare strip
AI metadata. Inspect the prepared upload again and do not submit it if a visible
provider mark remains. A model answer based on a visible logo is not a SynthID
result.Does this image/video/audio contain a SynthID watermark? Use the SynthID verification tool only; do not infer from visible content, logos, text, or metadata. Do not substitute a general
Google-AI-origin question; it permits visual-content reasoning instead of a
SynthID verdict.If a planned Chrome profile or /u/N/ account is not already authenticated,
record that it is unavailable and continue with another configured existing
session. When no usable Gemini session remains, record that and continue with
synthid-web. Do not start a new login.
Use the isolated Playwright runner at https://synthid.com/. The page does not
require an account login, so the slot may name a proxy. Do not start a sign-in.
The portal's terms forbid bulk verification and quota evasion, so one invocation
submits the prepared rows once and does not retry.
synthid-web slot. It does not name account_label,
browser_profile, or google_account_index. It may name proxy_url_env.run-web with the upload acknowledgement. The runner attaches one
prepared upload through the page's file input.Watermark detected and SynthID was detected
are detected. Watermark not detected and SynthID was not detected
are not_detected. Conflicting labels stay indeterminate. Quota and
unclear wording stay refused or indeterminate. Do not click a sign-in
button.Please sign in before detection. and returns no
watermark label, keep that row. Open the same prepared upload in the user's
existing real Chrome, where a session is already signed in, on the direct
route. Do not start a new login, do not copy cookies into
Playwright, and do not send that Chrome session through a proxy. If that
Chrome also asks for sign-in, leave its row unsubmitted.Use the isolated Playwright runner. Do not attach that runner to the user's real Chrome:
uv run python scripts/provider_oracles.py run-web /outside/repo/batch/manifest.json \
--acknowledge-uploads --env-file .env
The runner is headed by default because OpenAI's Cloudflare gate blocks the
same isolated Chromium in headless mode. Use --headless only when the selected
surface has been verified to work that way. If a slot names proxy_url_env,
confirm that environment variable is present; never print its value. One
invocation does not retry. CAPTCHA, bot checks, throttling, transport
failure, and unknown page wording remain distinct recorded outcomes. After any
of those, or after a refusal, run the next configured route or surface.
Do not replace the runner's per-surface upload-readiness waits with one shared
wait (docs/provider-oracles.md). Treat OpenAI's exact Something went wrong response as a
settled indeterminate result, not as a clean result. Do not resubmit that
same page in the same batch; continue with the next configured route or surface.
A ThorData credential may live in one gitignored environment variable. Do not
prepare a country or a session in that URL or in a slot: each run picks its own
exit session (docs/provider-oracles.md). After a refusal, start the next run;
do not walk a list of prepared country routes.
Use check-openai with one explicit upload acknowledgement. Keep named API keys
as OPENAI_API_KEY_1, OPENAI_API_KEY_2, and OPENAI_API_KEY_3 in the local .env, and select
only their variable names through an openai-api slot's api_key_env. Never
print a key or copy one into a slot or manifest. Continue through the configured
named API slots, with a separate batch for each and one call per slot, and then
continue to openai-web. API calls never take a proxy. The current adapter is
image-only.
Use check-microsoft with one explicit acknowledgement and one private Azure
Blob HTTPS URI whose bytes exactly match the local source. Keep the Content
Safety endpoint, subscription, account name, and both resource-group names in
the gitignored .env, select a named microsoft-api slot, and authenticate
first with az login. Give the Content Safety system identity Storage Blob Data Reader on the input storage account. After that call is refused, hits quota, fails, or
returns indeterminate, continue with another microsoft-api slot or with
microsoft-web. Keep Microsoft's Watermark and C2PA markers as separate verdicts.
uploads/ directory.manifest.json and manifest.sha256 immutable.detected, not_detected, indeterminate, refused, and
unreachable distinctly.present, absent, indeterminate,
or unavailable.verify --require-complete; report incomplete rows explicitly.Run hash-bound Google, OpenAI, Microsoft, or Meta watermark-oracle checks for this repository. Use for provider verification, multi-account Gemini checks, SynthID Detector checks at synthid.com, isola
---name: provider-oraclesdescription: Run hash-bound Google, OpenAI, Microsoft, or Meta watermark-oracle checks for this repository. Use for…---# .claude/skills/provider-oracles/SKILL.md概要
Run hash-bound Google, OpenAI, Microsoft, or Meta watermark-oracle checks for this repository. Use for provider verification, multi-account Gemini checks, SynthID Detector checks at synthid.com, isolated Playwright checks, or recording oracle evidence. Walk the existing plan automatically when a task needs a provider verdict.
よくある質問
公開元から .claude/skills/provider-oracles/SKILL.md をダウンロードするか、パスをコピーしてリポジトリを開いてください。PlugMCP はスキルを掲載するだけで、ファイルはホストしていません。
公開元は https://github.com/wiltodelta/remove-ai-watermarks で管理しています。
Claude、Cursor、Codex、Grok Build は、公開元のリポジトリから追加した SKILL.md を読み込めます。Grok Bot は、チャットでスキルの GitHub フォルダーのリンクを送るとインストールします。