Ship better in 30 seconds. Browse 2,000+ expert-built and security scanned skills -> Browse skills
THE AGENSI STORE
126 skills found
by Matthew King
Audit, score, and improve your AI agent skills for higher quality, lower token costs, better reliability, and marketplace success. Get actionable recommendations for prompts, instructions, tool usage, error handling, and user experience.
Turn a CRM export or live HubSpot/Salesforce/Pipedrive sync into an executive-ready pipeline report: a 12-month weighted forecast with three scenarios, win/loss themes pulled from deal notes, data-quality flags, and a board-ready PDF. Can run weekly and email itself to stakeholders.
Professional bilingual audit tool with Monte Carlo sampling and structured fix proposals for high-volume translations.
Design scalable, data-driven SEO page systems with keyword templates and quality-controlled workflows.
by Sir Benjamin
A lightweight defensive layer that prunes hallucinations and boosts reasoning quality for 8k-32k context 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.
An adversarial self-review gate that hunts your agent's weakest claim, overclaims, and missing limitations before a human sees the output.
Audit any AI-generated output for unsupported claims, then verify every factual and technical assertion against its real source before it ships.
by Roy Yuen
Enforce senior-level coding standards (Surgical, Simple, Goal-Driven) on every AI-generated code change.
A reusable rubric that grades every source by type, recency, authority, independence, and corroboration, then ranks them and resolves conflicts by evidence weight.
An adversarial gate that audits a research brief or AI-generated answer for unsupported claims, weak or outdated sources, missing citations, and one-sided framing — returning a structured TRUST/VERIFY/REJECT verdict with the exact passage quoted and what to verify for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.
Audit codebases for structural debt, TODOs, and dependency rot to generate prioritized remediation reports.
An adversarial editing gate that scans any AI-assisted draft and flags the exact tells that make it sound machine-written — filler phrases, formulaic structure, robotic cadence, punctuation tics — returning a structured PASS/REVISE/FAIL verdict with specific fixes.
An adversarial reviewer for AGENTS.md and agent instruction files. It flags ambiguous or contradictory rules, missing guardrails, vague tool and scope definitions, and untestable instructions, then returns a PASS / REVISE / BLOCK verdict — before the config drives your agent.
Continuously monitor data pipelines, detect anomalies, and explain root causes before failures impact production.
An adversarial senior engineer review gate that audits AI-written code for security gaps and logic errors before shipping.
A senior-level code reviewer that uses Socratic questioning to identify architectural flaws and teach better patterns.
An adversarial reviewer for landing pages and conversion copy. It flags an unclear value proposition, a weak or buried call to action, missing social proof, funnel friction, and unsupported claims, then returns a PUBLISH / REVISE / HOLD verdict — before the page goes live.
Map supply chains, identify overlooked upstream chokepoints, score candidate quality, audit evidence, and generate research reports.
Audit your dbt project for the test and documentation gaps that let bad data ship. Flags models with no unique or not_null tests, sources missing freshness config or tests, likely keys without a not_null test, models missing descriptions, SELECT * in models, and raw table references that should use ref() or source(). Each finding comes with a suggested tests: YAML snippet to drop into schema.yml.
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 Shogun Labs
Battle-tested prompting patterns to eliminate LLM output drift. Sandwich structure, few-shot examples, history limits, retry, and token caps — 6 composable layers for production-grade agent reliability.
An adversarial gate that audits any chart, data summary, or statistic for misleading visuals and unsound inference, then returns one PASS/REVISE/FAIL verdict.