Not in the top 1,000 by GitHub stars
Neeeophytee/ai-watermarks-reality-check
Test what AI watermark and provenance evidence exists, whether it verifies, and what survives publishing.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/audit-metadata-privacy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
0e8eb630b20f → 0e8eb630b20f
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 0e8eb630b20f
No earlier version was observed for comparison.
skills/audit-provenance/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
0e8eb630b20f → 0e8eb630b20f
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 0e8eb630b20f
No earlier version was observed for comparison.
skills/check-ai-transparency/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
0e8eb630b20f → 0e8eb630b20f
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 0e8eb630b20f
No earlier version was observed for comparison.
skills/detect-text-watermark/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
0e8eb630b20f → 0e8eb630b20f
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 0e8eb630b20f
No earlier version was observed for comparison.
skills/inspect-content-provenance/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
0e8eb630b20f → 0e8eb630b20f
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 0e8eb630b20f
No earlier version was observed for comparison.
skills/map-provenance-survival/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
0e8eb630b20f → 0e8eb630b20f
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 0e8eb630b20f
No earlier version was observed for comparison.
skills/verify-content-credentials/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
0e8eb630b20f → 0e8eb630b20f
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 0e8eb630b20f
No earlier version was observed for comparison.
Verified commit 0e8eb630b20f2b03ced0e77f3d650012a4ae48a1
git clone --filter=blob:none --no-checkout https://github.com/Neeeophytee/ai-watermarks-reality-check.git .hotskills/neeeophytee-ai-watermarks-reality-check && git -C .hotskills/neeeophytee-ai-watermarks-reality-check checkout --detach 0e8eb630b20f2b03ced0e77f3d650012a4ae48a1
# Copy each selected skill directory from .hotskills/neeeophytee-ai-watermarks-reality-check into .agents/skills/<skill-name>/Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- audit-metadata-privacy
skills/audit-metadata-privacy - audit-provenance
skills/audit-provenance - check-ai-transparency
skills/check-ai-transparency - detect-text-watermark
skills/detect-text-watermark - inspect-content-provenance
skills/inspect-content-provenance - map-provenance-survival
skills/map-provenance-survival - verify-content-credentials
skills/verify-content-credentials
How it works
audit-metadata-privacy
When your agent uses it
Audit supported metadata surfaces in images, SVG, PDF, and OOXML assets for privacy signals such as GPS, author, device, software, comments, and timestamps. Use when preparing a public release and metadata exposure must be assessed without altering or invalidating provenance.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
413 tokensWhen the skill is activated
Reference documents
188 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Boundaries
Scripts executed separately
scripts/audit_metadata.pyscripts/provenance_core.py
Files
SKILL.mdcore1,908 bytesSKILL.mdcore1,908 bytesagents/openai.yamlasset271 bytesreferences/privacy-boundaries.mddoc993 bytesscripts/audit_metadata.pyruns14,780 bytesscripts/provenance_core.pyruns66,891 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubaudit-provenance
When your agent uses it
Answer the five provenance questions for a single asset in one pass - was provenance located, verified, and trusted, was the scan complete, and what remains unknown. Use when a user asks for an overall provenance verdict on a file and does not want to orchestrate the individual analyzers themselves.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
464 tokensWhen the skill is activated
Reference documents
375 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Boundaries
Scripts executed separately
scripts/audit_provenance.pyscripts/provenance_core.py
Files
SKILL.mdcore1,985 bytesSKILL.mdcore1,985 bytesagents/openai.yamlasset305 bytesreferences/five-questions.mddoc1,505 bytesscripts/audit_provenance.pyruns10,524 bytesscripts/provenance_core.pyruns66,891 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcheck-ai-transparency
When your agent uses it
Review a structured record of AI-generated outputs for provenance evidence, human-readable disclosure, model identification, and documented edits. Use when preparing for publication or policy review and teams need gaps and next actions without a legal conclusion.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
384 tokensWhen the skill is activated
Reference documents
267 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Interpretation
Scripts executed separately
scripts/check_transparency.pyscripts/provenance_core.py
Files
SKILL.mdcore1,845 bytesSKILL.mdcore1,845 bytesagents/openai.yamlasset261 bytesreferences/record-schema.mddoc998 bytesscripts/check_transparency.pyruns11,332 bytesscripts/provenance_core.pyruns66,891 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdetect-text-watermark
When your agent uses it
Run every available text-provenance detector over a document or string and report per-detector states, including hidden Unicode channels and detached C2PA manifests. Use when a user asks whether text carries an AI watermark, contains invisible or smuggled characters, or is safe to feed into an agent pipeline.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
641 tokensWhen the skill is activated
Reference documents
720 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Why keyed watermarks cannot be detected here
- Non-negotiable language
- Deliberate non-goals
Scripts executed separately
scripts/detect_text_watermark.pyscripts/provenance_core.py
Files
SKILL.mdcore2,896 bytesSKILL.mdcore2,896 bytesSKILL.mdcore2,896 bytesagents/openai.yamlasset329 bytesreferences/detector-registry.mddoc2,764 bytesscripts/detect_text_watermark.pyruns13,772 bytesscripts/provenance_core.pyruns66,891 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubinspect-content-provenance
When your agent uses it
Inspect local files or text for observable provenance metadata, possible C2PA markers, hashes, and text control characters. Use when a user asks whether an asset contains Content Credentials, an AI mark, provenance metadata, or suspicious invisible characters and a cautious inventory is needed before cryptographic verification.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
603 tokensWhen the skill is activated
Reference documents
217 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Non-negotiable language
Scripts executed separately
scripts/inspect_file.pyscripts/provenance_core.py
Files
SKILL.mdcore2,693 bytesSKILL.mdcore2,693 bytesSKILL.mdcore2,693 bytesagents/openai.yamlasset296 bytesreferences/evidence-model.mddoc980 bytesscripts/inspect_file.pyruns7,434 bytesscripts/provenance_core.pyruns66,891 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmap-provenance-survival
When your agent uses it
Compare an original asset with resized, converted, uploaded, or downloaded derivatives and produce a JSON, Markdown, or HTML provenance-survival report. Use when testing whether a CMS, image optimizer, social network, editor, screenshot, watermark-removal tool, or publishing workflow preserves Content Credentials.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
680 tokensWhen the skill is activated
Reference documents
304 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Shareable reports
- Evaluating a transformation tool
- Experimental discipline
Scripts executed separately
scripts/map_survival.pyscripts/provenance_core.py
Files
SKILL.mdcore3,250 bytesSKILL.mdcore3,250 bytesSKILL.mdcore3,250 bytesagents/openai.yamlasset273 bytesreferences/survival-testing.mddoc1,508 bytesscripts/map_survival.pyruns28,806 bytesscripts/provenance_core.pyruns66,891 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubverify-content-credentials
When your agent uses it
Verify C2PA Content Credentials in a local asset with the official c2patool, separating manifest presence, cryptographic integrity, and signer trust. Use when a user needs defensible validation instead of byte-marker guesses, including offline and unavailable-verifier cases.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
617 tokensWhen the skill is activated
Reference documents
291 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Captured-report review mode
- Boundaries
Scripts executed separately
scripts/provenance_core.pyscripts/verify_c2pa.py
Files
SKILL.mdcore2,808 bytesSKILL.mdcore2,808 bytesSKILL.mdcore2,808 bytesSKILL.mdcore2,808 bytesSKILL.mdcore2,808 bytesagents/openai.yamlasset278 bytesreferences/c2pa-verification.mddoc1,372 bytesscripts/provenance_core.pyruns66,891 bytesscripts/verify_c2pa.pyruns8,784 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- audit-metadata-privacy
- audit-provenance
- check-ai-transparency
- detect-text-watermark
- inspect-content-provenance
- map-provenance-survival
- verify-content-credentials
Repository facts
- License
- AGPL-3.0
- Created
- Aug 13, 2026
- Last pushed
- Aug 14, 2026
- Forks
- 2
- Open issues
- 1
- Project activity
- Slowing
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 13 notes
skills/audit-metadata-privacy/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audit-provenance/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/check-ai-transparency/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/detect-text-watermark/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/detect-text-watermark/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/inspect-content-provenance/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/inspect-content-provenance/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/map-provenance-survival/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/map-provenance-survival/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/verify-content-credentials/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/verify-content-credentials/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/verify-content-credentials/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/verify-content-credentials/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 3 network referencesin 2 files: verify-content-credentials/references/c2pa-verification.md:3 inspect-content-provenance/references/evidence-model.md:14
- 21 obfuscation signalsin 7 files: audit-metadata-privacy/scripts/provenance_core.py:66 audit-provenance/scripts/provenance_core.py:66 check-ai-transparency/scripts/provenance_core.py:66 and 4 more
- No instruction overrides
- 14 executable scriptsin 14 files: audit-metadata-privacy/scripts/audit_metadata.py:1 audit-metadata-privacy/scripts/provenance_core.py:1 audit-provenance/scripts/audit_provenance.py:1 and 11 more
- 2 references to secretsin 1 file: detect-text-watermark/scripts/detect_text_watermark.py:320
- No requests to vote in Hot
Show all 40 signals by file
skills/audit-metadata-privacy/scripts/audit_metadata.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/audit-metadata-privacy/scripts/provenance_core.py
skills/audit-provenance/scripts/audit_provenance.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/audit-provenance/scripts/provenance_core.py
skills/check-ai-transparency/scripts/check_transparency.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/check-ai-transparency/scripts/provenance_core.py
skills/detect-text-watermark/scripts/detect_text_watermark.py
skills/detect-text-watermark/scripts/provenance_core.py
skills/inspect-content-provenance/references/evidence-model.md
- Network accessline 14
Official source: https://support.claude.com/en/articles/16266773-how-claude-marks-ai-generated-content
skills/inspect-content-provenance/scripts/inspect_file.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/inspect-content-provenance/scripts/provenance_core.py
skills/map-provenance-survival/scripts/map_survival.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/map-provenance-survival/scripts/provenance_core.py
skills/verify-content-credentials/references/c2pa-verification.md
skills/verify-content-credentials/scripts/provenance_core.py
skills/verify-content-credentials/scripts/verify_c2pa.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 40 facts
- Executable script in code of a file that runsaudit-metadata-privacy/scripts/audit_metadata.py:1High confidence
- Executable script in code of a file that runsaudit-metadata-privacy/scripts/provenance_core.py:1High confidence
- Possible obfuscation in code of a file that runsaudit-metadata-privacy/scripts/provenance_core.py:66High confidence
- Possible obfuscation in code of a file that runsaudit-metadata-privacy/scripts/provenance_core.py:733High confidence
- Possible obfuscation in code of a file that runsaudit-metadata-privacy/scripts/provenance_core.py:928High confidence
- Executable script in code of a file that runsaudit-provenance/scripts/audit_provenance.py:1High confidence
- Executable script in code of a file that runsaudit-provenance/scripts/provenance_core.py:1High confidence
- Possible obfuscation in code of a file that runsaudit-provenance/scripts/provenance_core.py:66High confidence
- Possible obfuscation in code of a file that runsaudit-provenance/scripts/provenance_core.py:733High confidence
- Possible obfuscation in code of a file that runsaudit-provenance/scripts/provenance_core.py:928High confidence
- Executable script in code of a file that runscheck-ai-transparency/scripts/check_transparency.py:1High confidence
- Executable script in code of a file that runscheck-ai-transparency/scripts/provenance_core.py:1High confidence
- Possible obfuscation in code of a file that runscheck-ai-transparency/scripts/provenance_core.py:66High confidence
- Possible obfuscation in code of a file that runscheck-ai-transparency/scripts/provenance_core.py:733High confidence
- Possible obfuscation in code of a file that runscheck-ai-transparency/scripts/provenance_core.py:928High confidence
- Executable script in code of a file that runsdetect-text-watermark/scripts/detect_text_watermark.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuedetect-text-watermark/scripts/detect_text_watermark.py:320Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuedetect-text-watermark/scripts/detect_text_watermark.py:321Low confidence
- Executable script in code of a file that runsdetect-text-watermark/scripts/provenance_core.py:1High confidence
- Possible obfuscation in code of a file that runsdetect-text-watermark/scripts/provenance_core.py:66High confidence
- Possible obfuscation in code of a file that runsdetect-text-watermark/scripts/provenance_core.py:733High confidence
- Possible obfuscation in code of a file that runsdetect-text-watermark/scripts/provenance_core.py:928High confidence
- Network access in prose of documentationinspect-content-provenance/references/evidence-model.md:14Low confidence
- Executable script in code of a file that runsinspect-content-provenance/scripts/inspect_file.py:1High confidence
- Executable script in code of a file that runsinspect-content-provenance/scripts/provenance_core.py:1High confidence
- Possible obfuscation in code of a file that runsinspect-content-provenance/scripts/provenance_core.py:66High confidence
- Possible obfuscation in code of a file that runsinspect-content-provenance/scripts/provenance_core.py:733High confidence
- Possible obfuscation in code of a file that runsinspect-content-provenance/scripts/provenance_core.py:928High confidence
- Executable script in code of a file that runsmap-provenance-survival/scripts/map_survival.py:1High confidence
- Executable script in code of a file that runsmap-provenance-survival/scripts/provenance_core.py:1High confidence
- Possible obfuscation in code of a file that runsmap-provenance-survival/scripts/provenance_core.py:66High confidence
- Possible obfuscation in code of a file that runsmap-provenance-survival/scripts/provenance_core.py:733High confidence
- Possible obfuscation in code of a file that runsmap-provenance-survival/scripts/provenance_core.py:928High confidence
- Network access in prose of documentationverify-content-credentials/references/c2pa-verification.md:3Low confidence
- Network access in prose of documentationverify-content-credentials/references/c2pa-verification.md:4Low confidence
- Executable script in code of a file that runsverify-content-credentials/scripts/provenance_core.py:1High confidence
- Possible obfuscation in code of a file that runsverify-content-credentials/scripts/provenance_core.py:66High confidence
- Possible obfuscation in code of a file that runsverify-content-credentials/scripts/provenance_core.py:733High confidence
- Possible obfuscation in code of a file that runsverify-content-credentials/scripts/provenance_core.py:928High confidence
- Executable script in code of a file that runsverify-content-credentials/scripts/verify_c2pa.py:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/audit-metadata-privacy/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/audit-metadata-privacy/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/audit-metadata-privacy/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/audit-metadata-privacy/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/audit-metadata-privacy/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
