Turns Codex usage into planning facts with linear pace, projected exhaustion, banked-reset expirations, and conservative unexpected-reset detection.
1 skill
Development version: not yet validated for formal assessments; use at your own discretion. Context-based significance assessment (CBSA) of heritage places, stage by stage with expert review and epistemic marks.
Plugin insites from marketplace insites-lab in InSites-Lab/insites. Commands read from the repo's manifest — 2 days ago.
assessRuns the InSites context-based significance assessment (CBSA) of a heritage place, Stage 0 to Stage 6, with an expert review and a hard stop after every stage, epistemic marks on every claim, and a closing session report. Use when the user uploads heritage documentation and says "start", "let's begi
claim-extractorExtract and classify substantive claims from CBSA assessment sessions (Stages 0–6). Produces a structured, reproducible claim-level dataset with epistemic analysis and cross-tabulations. Trigger on "extract claims", "claim analysis", "count claims", "claim extraction".
dashboardBuilds the InSites single-assessment dashboard as a thin artifact shell that loads the pinned atar-runtime and passes a DATA object projected from the approved Stage 0–6 outputs only. Use when the user says "dashboard", "summary dashboard", "create dashboard", "דשבורד" after Stage 6 of an InSites as
knowledge-graphBuilds the InSites knowledge graph of a heritage assessment as a thin artifact shell that loads the pinned atar-runtime and passes a DATA object projected from approved findings only. Use when the user says "kg", "knowledge graph", "create kg", "גרף ידע", after Stage 5 of an InSites assessment or wi
read-assessmentReads a completed heritage significance assessment — uploaded, pasted, or produced earlier in the session — and offers analytical, interpretive and generative readings without writing new assessment stages. Use when the user says "read assessment", "analyze assessment", "review assessment", "קריאת ה
read-collectionReads across a collection of heritage sites or assessments — a spreadsheet with at least two asset rows, one document with at least two assets, or several asset files — to surface patterns, gaps and decision-relevant insights, and builds the collection dashboard on request. Use when the user says "r
stage-specDerives a standalone, editable specification from one InSites CBSA stage — for reuse elsewhere or for a participant to study — without running the stage. Use when the user says "spec", "stage specification", "מפרט", "מפרט שלב N", optionally with "for use in…" / "לשימוש ב…".
epistemic-auditorUse this agent when the user asks for an independent check of the epistemic marks in an InSites stage output — whether each claim's mark (none, 〰️, 💭, citation) matches its actual basis in the uploaded sources. It reads with fresh context, flags, and never rewrites the output. <example> Context: St
Turns Codex usage into planning facts with linear pace, projected exhaustion, banked-reset expirations, and conservative unexpected-reset detection.
1 skill
Twelve-skill bundle covering the Conservation Biology manuscript lifecycle — from conservation-relevant topic fit through study design, analysis, data archiving, and revision — for the flagship journal of the Society for Conservation Biology.
12 skills
Context optimization, bloat detection, CPU/GPU monitoring, and token conservation for efficient Claude Code sessions
12 skills · 6 commands · 5 agents · hooks
Build production computer vision pipelines for object detection, tracking, and video analysis. Handles drone footage, wildlife monitoring, and real-time detection. Supports YOLO, Detectron2, TensorFlow, PyTorch. Use for archaeological surveys, conservation, security. Activate on "object detection", "video analysis", "YOLO", "tracking", "drone footage". NOT for simple image filters, photo editing, or face recognition APIs.
1 skill
Auto-resume and auto-retry for interrupted Codex tasks on Windows. Waits out a usage limit (until the reset time Codex reports, e.g. for a 5-hour or weekly window), a rate limit or a temporary failure, then continues the exact same conversation, so long-running or overnight work keeps going while that conversation is open in the Codex app. Setup downloads a checksum-verified release from GitHub; after that the watcher runs locally, read-only against Codex state, conservative by design.
2 skills
Tripartite skill plugin with GF(3) conservation
200 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.