Skill Claude CodeCodex
Save media into global archive buckets reusable across cases, stand up bucket indexes (face/semantic/image/audio/ask) with the archive setup wizard, and run "does this match anything I've archived?" checks from inside any case.
Skill Claude CodeCodex
Map a target's internet-exposed hosts and services with the shodan source, capture host reports, brief the exposure, and optionally stand up a monitor for newly exposed services.
Skill Claude CodeCodex
Same recording, surfaced again — fingerprint audio into a local audio-fp index, then match a query clip against it (or clip-to-clip) with time-offset alignment, gate out sped-up re-uploads with a margin, and escalate a fingerprint miss to a CLAP semantic pass.
Skill Claude CodeCodex
Be on the lookout — stand up a standing face/image watchlist: register a reference face, point a monitor at incoming feeds, auto-match every new item against the reference, and surface hits as a triage queue + alert so a match announces itself.
Skill Claude CodeCodex
Same camera shot these — pull EXIF device fingerprints (make/model/lens/serial) off every case image and video, roll them up by camera with devices, and tell a strong serial link from a weak make+model+lens one, feeding the connections into the graph and the map.
Skill Claude CodeCodex
Canvass the cameras near a location — resolve a street address (or accept a raw lat,lng) to a point, fan the OSM fixed-camera and live public-webcam sources around it at a radius, and plot every hit on one map to triage which cameras could overlook the scene. A leads generator, not a guaranteed complete camera…
Skill Claude CodeCodex
String the board — build the case knowledge graph, read its hubs (shared media, targets, device fingerprints, places, typed entities), focus the neighborhood around a node, optionally run the opt-in LLM entity pass, and promote real connections into evidence via findings.
Skill Claude CodeCodex
Hunt re-uploads and reskins of original video content across X / YouTube / TikTok — escalate from cheap metadata triage to frame/face/transcript matching and produce citable copycat findings.
Skill Claude CodeCodex
Turn a case into a visual evidence board — materialize face and object crops, link the same person across clips, connect themes, and render the corkboard as a CSI brief plus a live monitor wall.
Skill Claude CodeCodex
Google-dork a target domain for exposed documents, directory listings, login portals, and misconfigurations using the dork source (real Google operators), then capture the result pages and produce a cited exposure brief.
Skill Claude CodeCodex
Make unreadable footage legible — denoise/upscale a marked moment, re-run OCR and detection on the enhanced output, and record what was recovered with honest provenance (interpolation is a lead, not proof).
Skill Claude CodeCodex
Localize the exact instant of a one-way state change (light on, door opens, poster removed) by binary-searching frames — log2(N) VLM calls.
Skill Claude CodeCodex
Follow the money trail — register a blockchain address (chain) or an SEC EDGAR filer (edgar) as an OSINT source, scan the public transaction / filing history into cited scan records, connect the flow-of-funds and counterparties on the case graph, and promote a movement or filing to a finding on a line of…
Skill Claude CodeCodex
Triage a whole clip in one VLM call — tile sampled frames into a labeled contact sheet, ask which cells show the target, then zoom in.
Skill Claude CodeCodex
Install and configure overcast for this harness: install the CLI, verify the system ffmpeg, and configure reusable provider profiles. Use once per machine/profile before driving the overcast skill.
Skill Claude CodeCodex
Build a persistent local face database out of case media — the mugshot book — then run a suspect photo through it to identify who they are and where else they appear, with cited similarity scores.
Skill Claude CodeCodex
Analyze screen recordings, product demos, customer support videos, and audio notes into actionable, cited bug reports for coding agents.
Skill Claude CodeCodex
Read foreign-language text off an image or video frame, translate it, and re-search in the SOURCE language — OCR a sign/screen/poster with see --ocr, translate it yourself, then scan the open web (and dork) with native-language queries, and cite what the text revealed.
Skill Claude CodeCodex
Pinpoint WHEN a specific thing happens in a video — funnel from cheap coarse candidates (shots / CLIP / grid) to a frame-verified time window.
Skill Claude CodeCodex
Find the interval a person or object is present — anchor one appearance, then sweep outward with face-match / detect until it drops off both sides.
Skill Claude CodeCodex
Trace a suspicious or viral clip back to its earliest appearance and originator — reverse-image-search distinctive frames, sweep sources with no recency floor, and return a cited origin verdict.
Skill Claude CodeCodex
Scan or monitor public sources for a target, capture relevant hits, sense media, and produce cited investigation briefs.
Skill Claude CodeCodex
Listen to the police scanner — register a dispatch (CAD / calls-for-service) feed on the Socrata SODA API, validate with one scan, then monitor it on an interval, plot the geolocated calls on a map, and triage call-types against the case's lines of investigation.
Skill Claude CodeCodex
Work out where a photo or clip was taken — check embedded EXIF/GPS first, then pull signage, landmarks, and terrain clues, reverse-image-search the strongest ones, and corroborate to a location with cited evidence.