Ship agent workflows in 30 seconds. Browse 2,000+ expert-built and security scanned skill -> Browse skills
THE AGENSI STORE
68 skills found
A parent-supervised AI tutor for kids’ English reading, phonics, vocabulary, speaking, and writing. Turn books, worksheets, passages, and writing samples into short practice sessions, gentle feedback, review cards, and parent progress reports.
by LB Creations
Security review of Kandji agent configurations, library items, and automation for compliance and safety
by LocoLoboZ
A proactive governance layer that validates MCP tool intent and scope to ensure safe, compliant agent behavior.
Scan your schemas, seed data, config, and logs for personal data before it leaks. Detects PII-indicating column and key names (email, ssn, phone, address) across SQL, CSV, and JSON, plus PII in the data itself: email addresses, SSN-like numbers, credit-card-like numbers, phone numbers, and PII written into log files. Each finding is flagged with its location and a GDPR-style review note. Heuristic by design: it surfaces what to review, not a compliance guarantee.
by LB Creations
Review Jamf and Kandji scripts for safer user context, prompts, logging, and rollout readiness.
Professional Zig 0.16.0 development specialist focusing on memory safety, 0.16.0 API compliance, and systems performance.
by LB Creations
Review scripts and docs for safer handling of passwords, tokens, keys, and sensitive values.
by LB Creations
Preflight Jamf smart group and deployment scope mistakes.
by LocoLoboZ
Automate weekly receipt reconciliation, bank matching, and Zoho Books posting with strict safety gates.
by LB Creations
Review bash and zsh admin scripts for safer quoting, input handling, permissions, and rollout readiness.
Automatically detect GDPR compliance risks in websites, codebases, marketing assets, and AI workflows.
Systematic audit for AI prompts to detect security flaws, bias, and cost-inefficiencies with auto-optimization.
by LocoLoboZ
Build safety-first, framework-aligned incident response playbooks for ICS, SCADA, and OT environments.
by Zotri
Run Claude Code unattended with a battle-tested safety framework, hardened deny-rules, and a 6-layer rollback ladder.
by Timoranjes
The security auditor for AI agents. Detect prompt injection, secret leaks, and unsafe tool access in SKILL.md files.
An adversarial security gate that audits untrusted content — web pages, tool outputs, documents, emails — for embedded instructions, exfiltration, and authority spoofing, then returns a SAFE/REVIEW/BLOCK verdict.
Before an agent acts on a plan, verify that the things it named actually exist. Checks each referenced file path, function or method, import or package, environment variable, and CLI command against your repo, and flags the ones that do not resolve. Catches the hallucinated function and the phantom package before the edit, not after the build breaks. Resolves Python and JavaScript/TypeScript.
Scaffold and audit secure MCP servers with input schemas, confirmation gates, and safety-first tool definitions.
Catch the dangerous migration before it locks or wrecks your production database. Scans SQL migration files for destructive and risky operations: DROP and TRUNCATE, drops without IF EXISTS, lossy column-type changes, NOT NULL added without a default, DELETE or UPDATE with no WHERE, non-concurrent index builds, dropped constraints, renames, and data backfills mixed into schema changes. Each finding is ranked by severity with a safer rewrite. Postgres, MySQL, and SQLite.
Plan, review, and execute safe database migrations with automatic rollback plans, backfill strategies, and zero-downtime sequencing.
Transform fragile AI prototypes into resilient, enterprise-ready production agents with professional hardening tools.
The migration ran instantly in staging and locked a 40-million-row table in production for nine minutes — because staging had 400 rows
by Timoranjes
Deep audit of TypeScript codebases for type safety violations, unsafe casts, and runtime-risk anti-patterns.
Adversarial memory audit to remove PII, stale facts, and injected instructions from agent storage.