Peer Review Stress Test — Make Your Agent Its Own Harshest Reviewer
An adversarial self-review gate that hunts your agent's weakest claim, overclaims, and missing limitations before a human sees the output.
Ship agent workflows in 30 seconds. Browse 2,000+ expert-built and security scanned skills. Browse skills
THE AGENSI STORE
1298 skills found
An adversarial self-review gate that hunts your agent's weakest claim, overclaims, and missing limitations before a human sees the output.
Expert Oracle PL/SQL architect for writing, refactoring, and performance-tuning enterprise database logic.
by LocoLoboZ
Rigorous academic and internal research verification to score idea novelty and identify prior work.
Audit, verify, and format academic citations across AMA, APA, and Vancouver styles to eliminate AI hallucinations.
by LocoLoboZ
A technical reference and troubleshooting expert for connecting Make.com scenarios to MCP-compatible AI agents.
An adversarial gate that audits an AI eval or test suite — LLM-judge rubrics, datasets, regression tests, metrics — for gameable criteria, data leakage, missing edge cases, and non-determinism, then returns one PASS/REVISE/FAIL verdict.
by LocoLoboZ
Design and analyze industrial control system anomaly detection logic for safe, protocol-aware OT security monitoring.
by LocoLoboZ
Architect sophisticated Make (Integromat) scenarios with structured module sequences, routing logic, and error handling.
Turn CRM exports into sales rep scorecards: 0-100 performance scores across activity, pipeline, conversion, and forecast accuracy, plus evidence-based coaching notes for weekly 1-on-1s. One review-ready report instead of a spreadsheet weekend.
Turn a raw account CSV into balanced sales territories: assigns accounts by region, industry, workload, and ARR, flags orphaned high-value accounts, and hands managers specific rebalancing moves. Compares region-based vs industry-based models so coverage is even instead of cherry-picked.
by LB Creations
Preflight Jamf smart group and deployment scope mistakes.
by LocoLoboZ
Professional academic citation formatting and auditing specializing in APA 7, IEEE, and AGLC styles.
An adversarial gate that audits a research brief or AI-generated answer for unsupported claims, weak or outdated sources, missing citations, and one-sided framing — returning a structured TRUST/VERIFY/REJECT verdict with the exact passage quoted and what to verify for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.
Run a 10,000-iteration Monte Carlo forecast on your pipeline CSV to get P50/P70/P90 revenue confidence intervals, an ASCII distribution histogram, and what-if scenarios for slipped deal dates. Answers 'how likely are we to hit the number?' instead of a flat weighted-pipeline guess.
by Nex AI
The end-to-end strategic operating system for launching and scaling a solo digital agency for Belgian SMEs.
by Y_Y_ai
Generates 10-year future visions, identifies product bottlenecks, and creates innovative R&D ideas with execution roadmaps.
Repo gets views but no stars? Get the one ready-to-paste README fix for the biggest blocker killing your conversion.
by Nex AI
Deploy conversion-optimized, schema-rich websites for vets, grooming salons, and pet boarding businesses.
by Nex AI
A complete Manifest V3 Chrome extension to detect and highlight manipulative UI dark patterns on any website.
by Nex AI
Automated client onboarding flow for web agencies: kickoff mails, asset requests, and intake checklists.
by Nex AI
A production-ready Manifest V3 extension to strip tracking parameters and hidden Unicode from copied text.
Strategic career advisor for job search strategy, LinkedIn optimization, interview prep, and salary negotiation.
by Nex AI
Deploy a gallery-forward, SEO-optimized portfolio website for photographers and creative studios.
Scan a draft for the tells that make writing read as AI-generated, so you can revise them before publishing. Flags the delve/tapestry/underscore/harness vocabulary cluster, hedging and filler phrases ("it's worth noting," "in today's digital age"), the "not just X, it's Y" antithesis tic, em-dash overuse, rule-of-three pile-ups, unusually uniform sentence cadence, and generic conclusion openers. It marks locations for you to fix; it does not rewrite.