Build Outcome Verifier
by Elston Gunn
Physically installs and launches your APK before the agent declares the build done. Catches broken artifacts every time.
Ship agent workflows in 30 seconds. Browse 2,000+ expert-built and security scanned skill -> Browse skills
THE AGENSI STORE
610 skills found
by Elston Gunn
Physically installs and launches your APK before the agent declares the build done. Catches broken artifacts every time.
Run this on your plan, spec, or prompt before any work starts. It surfaces the decisions you never made, names what an agent would silently assume for each, ranks them by the cost of a wrong guess, and hands back a short list of choices to make now — plus the gaps that are safe to leave open.
by Samuel Rose
Transform raw incident logs and Slack threads into blameless, structured postmortems and 5-Whys RCA reports.
by Samuel Rose
Audit dependencies for security, licenses, and health while generating a phased, low-risk upgrade and migration plan.
by Shogun Labs
Project-specific Claude Code agent harness setup
by Shandra
Professional DevOps diagnostics for AI agents to solve failed deployments, Docker crashes, and CI/CD pipeline errors.
An adversarial gate that audits a research brief or AI-generated answer for unsupported claims, weak or outdated sources, missing citations, and one-sided framing — returning a structured TRUST/VERIFY/REJECT verdict with the exact passage quoted and what to verify for each.
by LocoLoboZ
Convert cyber incident evidence into blameless post-mortem reports, root cause analyses, and action trackers.
by LocoLoboZ
Professional security incident triage for SOC teams to classify alerts, assess severity, and draft response plans.
Audit your Supabase project for the row-level-security mistakes that quietly expose data: tables without RLS, policies that resolve to true, leaked service-role keys, missing auth.uid() checks, open storage buckets, overbroad grants, and migration drift. A local, read-only scan plus a full review checklist, each finding with severity, evidence, and a fix. No database changes without confirmation.
by LocoLoboZ
Build, review, and automate structured incident response playbooks for enterprise security operations.
One-line summary description Stop your agent from claiming "done" before it's proven. A verification gate that classifies each change by risk (payment, auth, database, user-facing), picks the tests that actually cover it, demands evidence, maps regression risk, and outputs an honest pass/fail report. Turns "looks good to me" into "here's what I ran, and here's what's still unverified."
A pre-publish audit gate to extract claims, verify facts, and flag compliance risks in public-facing content.
Runs an ordered evidence-integrity gate over any AI draft — grade sources, ground claims, verify technical assertions, stress-test — then returns one PASS/REVISE/FAIL ship decision.
by Ikerg
Deterministic CSV profiling with automated data quality audits, interactive Plotly reports, and Pandas fix snippets.
by Nex AI
Implement Clerk Organizations multi-tenancy with local DB syncing, RBAC mapping, and secure webhook handling.
Audit and harden GitHub Actions workflows against overbroad permissions, secrets exposure, and supply-chain risks.
Systematically refactor large codebases, eliminate circular dependencies, and define clean module boundaries.
by Nex AI
Turn MP4 videos into luxury, frame-by-frame scroll-animated websites with cinematic overlays and a dwell-stop engine.
by Matthew King
Architect, scaffold, and audit enterprise-grade Playwright test suites with professional CI and auth patterns.
A structured protocol for AI agents to orchestrate sub-agents with role contracts and disciplined handoffs.
by Nex AI
A production-ready Chrome Extension for 1-click 'Not Interested' buttons across social media feeds.
by Nex AI
Deploy appetizing, local-SEO-optimized landing pages for bakeries, butchers, and specialty food shops.
A repo visitor decides in about ten seconds whether your project solves their problem — and most READMEs spend those ten seconds on installation instructions instead of answering 'what does this actually do'