Гейты качества перед delivery: тесты, lint (ruff/ESLint v9/Biome), types (pyright), LSP, browser/security/design.
Builds a deterministic, reproducible proof-of-concept for a suspected vulnerability before writing a finding — eliminating false positives and producing airtight evidence.
Prepare an evidence-bound vulnerability publication and publish the exact approved advisory through Runx Connect with independent provider readback.
3-wave parallel audit — Wave 1 discovery (4 agents), Wave 2 verification (4 agents), Wave 3 cross-optimization (1 synthesizer). Each wave runs agents in parallel.
Gather security intelligence for Proteus hypotheses: expected behavior, public-known status, advisories, changelogs, issues, PRs, docs, tests, affected-version timeline, duplicate…
Use for cold-start, time-boxed, multi-axis audits of unfamiliar codebases — take-home assessments, post-acquisition or due-diligence reviews, inherited-service onboarding,…
Use this skill when investigating events in the ThreatLocker Action Log (the API name is "audit") — building incident timelines, tracing a file's history across endpoints,…
Knowledge engine over the Colombian Truth Commission (CEV) final report "Hay Futuro Si Hay Verdad" (2022) — the findings, statistics, armed-actor responsibilities, differential…
A Cursor Canvas is a live React app (.canvas.tsx) that the user can open beside the chat. Use a canvas when the agent produces a standalone analytical artifact — quantitative…
Analyzes SQL Server ERRORLOG files for operational issues, availability group failures, memory pressure, I/O subsystem warnings, and security events.
Apply structured critical thinking — identifying claims, evidence, reasoning chains, hidden assumptions, and logical fallacies — to evaluate or construct specific written…
Run a structured check on whether an image or video is AI-generated, digitally manipulated, or authentic-but-miscaptioned, and produce a sourced verdict with a confidence level.
Use this skill when working with SentinelOne XSPM misconfigurations - cloud security posture management across AWS, Azure, GCP, Kubernetes, identity, and infrastructure-as-code.
> Use this skill whenever asked about Netherlands cryptocurrency or digital asset taxation. Trigger on phrases like \"crypto tax Netherlands\", \"Bitcoin Netherlands\", \"crypto…
A skill that runs a GAP ANALYSIS & feedback review of an existing project through a multi-agent harness instead of a single review pass.
A skill that runs a GAP ANALYSIS & feedback review of an existing project through a multi-agent harness (enhanced variant: GPT-5.5 cross-model adversarial confirmation) — from…
Special Court for Sierra Leone (SCSL, 2002-2013) and the Residual Special Court for Sierra Leone (RSCSL, 2013-) research, drafting, and analysis.
This skill designs and runs the security awareness training programme for all employees. Use when asked to create security training, run phishing simulations, or track training…
Extends Capability Evolver with verification, rollback, and promotion gating. Use when an agent logs a learning, proposes a self-improvement, or wants to promote a learning to…
Special Tribunal for Lebanon (STL / TSL — Tribunal Spécial pour le Liban) research, drafting, and analysis.