Journalism
Investigative Journalism
Reporters and OSINT researchers load the skill into their agent of choice and let it drive reverse face searches during investigations, with built-in safety refusals for minors and non-consent.
FaceSearch Agent Skill
A Portable Agent Skill for Safe Face Search
The searching-faces agent skill teaches any AI agent when, how, and when NOT to run a face search. Ships with guardrails for minors, non-consent, and low-quality input. Drop it into Claude, Cursor, Cline, or any runtime that reads SKILL.md.
Open source • Progressive disclosure • Safety-first by default
Trusted by thousands worldwide
15,000+ Searches
50+ Countries
256-bit Encryption
99.7% Accuracy
How the Agent Skill Works
Install once, and any compatible agent loads the skill automatically when a request looks like a face search — then follows its instructions step by step.
1
Install Once, Anywhere
Drop the skill folder into ~/.claude/skills/, your Cursor rules directory, your Cline workspace, or any agent runtime that reads Markdown-based skill packages. One package, every client.
2
Your Agent Triggers It Automatically
When a user asks 'find where this face appears online' with an image, the agent recognizes the skill from its 338-character description and loads the full instructions on demand.
3
Safety Guardrails Apply
The agent skill enforces hard refusals for minors, non-consent, and stalking. It checks credits before submitting, polls responsibly, and presents results with confidence-score caveats.
Agent Skill Features
Everything the skill bundles so any AI agent can run face search safely and reliably.
Agent Skill Features
Everything the skill bundles so any AI agent can run face search safely and reliably.
Progressive Disclosure
SKILL.md stays under 300 lines and links to two reference files exactly one level deep (mcp-setup.md, rest-examples.md). The agent reads only what the current task needs, keeping context lean.
Hard Safety Refusals
Three non-negotiable refusals baked in: no searches on minors, no non-consensual identification, no searches on non-face images. The skill explains each refusal with clear language any agent can relay to the user.
Credit-Aware Workflow
The skill instructs the agent to check get_credits before submitting when the user has fewer than 10 credits, and to tell the user how many searches they can afford. No surprise INSUFFICIENT_CREDITS errors.
Result Interpretation Guide
The skill teaches agents how to read confidence scores: 90+ is exact, 83-89 is high, 70-82 is low, below 70 is likely not a match. Every claim ships with a caveat instead of asserting identity as fact.
Both MCP and REST
The skill works whether your agent is wired to the MCP server or only has an API key. Reference files cover both paths with copy-pasteable snippets.
CI-Linted Authoring
The repo ships scripts/lint-skills.ts which enforces portable agent-skill authoring constraints: frontmatter field limits, body line caps, one-level-deep reference rule, no backslash paths, no reserved words. CI catches drift before merge.
Install in one command
Drop the searching-faces skill into any agent runtime with a single npx call, then open the repo on GitHub to browse SKILL.md and the reference files.
Terminal one-liner
npx skills add face-search/facesearch-skillWho Installs the Agent Skill
From individual researchers to enterprise teams, the skill is for anyone who wants their AI agent to do face search responsibly.
Compliance
Compliance and KYC
Compliance teams install the skill so analysts can ask any supported agent to verify identity claims during a review, with the skill's confidence-score guidance making recommendations instead of assertions.
Developer
Developer Prototyping
Engineers building multi-agent workflows install the skill to quickly scaffold a face-search capability across whichever runtime they target, then use it as a reference when writing production pipelines.
Trusted Face Search Platform
10M+
Searches Completed
Trustworthy results worldwide
95%
Match Accuracy
Powered by advanced AI
50K+
Active Users
Growing community
100M+
Sources Scanned
Comprehensive coverage
What Skill Users Say
Feedback from early users who installed the agent skill across different runtimes.
"The hard refusals are exactly what I want. I don't have to remember to refuse minor or non-consent cases every single time — the skill enforces it and my agent backs me up with clear language."
"My agent explains confidence scores in plain English now. Before, I'd get a 78% match and have to decide what that meant. Now the skill teaches it to say 'this is a low match, here is why you should treat it as a lead not a conclusion'."
"scripts/lint-skills.ts is the single best thing in the repo for me. We have our own skills now and we copied the linter wholesale into our CI pipeline — it catches drift that manual reviews miss."
Simple, Transparent Pricing
Choose the plan that fits your needs. No hidden fees, cancel anytime.
MOST POPULAR
PRO
$29/month
For professionals and power users
- 100 Credits per month ($0.29 per credit)
- Face Search
- Search History
- Can Export Profile to PDF
Pay As You Go
Or Buy Credit Packs
Starter
3credits
$6
$2.00/credit
SAVE 20%
Basic
30credits
$24
$0.80/credit
SAVE 31%
Standard
100credits
$69
$0.69/credit
SAVE 34%
Pro
300credits
$199
$0.66/credit
SAVE 40%
Enterprise
1000credits
$599
$0.60/credit
Agent Skill FAQ
Everything skill users ask before installing.
Install the FaceSearch Agent Skill
Drop the skill into Claude, Cursor, Cline, or any runtime that reads SKILL.md, and your agent can search faces responsibly out of the box.
Install the Agent Skill
No credit card required
