AD
Adversarial Review (General)
bmad-code-org · Workflow
Perform a Cynical Review and produce a findings report.
$15
Details
Security & Testing
AV
Available make commands
streamlit · Workflow
Lists available make commands for Streamlit development.
$15
Details
CH
Checking Changes
streamlit · Guardrail
Validates all code changes before committing by running format, lint, type, and unit test checks.
$49
Details
DE
Debugging and Error Recovery
addyosmani · Guardrail
Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any…
$19
Details
ED
Edge Case Hunter Review
bmad-code-org · Workflow
Walk every branching path and boundary condition in content, report only unhandled edge cases.
$45
Details
F
F Testing Patterns
affaan-m · Expertise
F# testing patterns with xUnit, FsUnit, Unquote, FsCheck property-based testing, integration tests, and test organization best practices.
$59
Details
AU
Audit Dependencies
payloadcms · Workflow
Use when fixing dependency vulnerabilities, running pnpm audit, or when the audit-dependencies CI check fails
$69
Details
EV
Eval Harness
affaan-m · Expertise
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.
$89
Details
FD
FDA Food Safety Auditor
satnamrsm · Guardrail
Expert AI auditor for FDA Food Safety (FSMA), HACCP, and PCQI compliance.
$15
Details
Bootstrap pointer that installs the external repo-scan skill from a pinned, reviewable commit.
$15
Details
TE
Test-Driven Development
addyosmani · Workflow
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that…
$99
Details
UI
UI4 Convert Tests
payloadcms · Guardrail
Use when UI changes are complete and e2e tests need updating.
$15
Details
AV
Avoid inline JavaScript
thedaviddias · Expertise
Use when reviewing scripts, client components, bundles, or runtime behavior related to Avoid inline JavaScript.
Free
Details
DI
Dify Frontend Testing
langgenius · Guardrail
Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities.
Free
Details
MU
Mutate what I changed
n8n-io · Output format
Run Stryker mutation testing on the source files changed in the current branch (vs origin/master) across vitest packages.
Free
Details
MU
Mutation Testing
metabase · Guardrail
Run mutation testing on a Clojure namespace, generate tests to kill surviving mutations, and open draft PRs with Linear issue tracking.
Free
Details
MU
Mutation testing — single file
n8n-io · Workflow
Run Stryker mutation testing on a single source file and return a structured, token-frugal report that's pipeable to a follow-up…
Free
Details
WE
Web Application Testing
anthropics · Workflow
Toolkit for interacting with and testing local web applications using Playwright.
Free
Details
IM
Impact Analysis with GitNexus
abhigyanpatwari · Guardrail
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code.
Free
Details
ST
Take a Stryker summary.json (from n8n:mutant-score), triage the surviving mutants by user-reachable-behaviour risk, write minimal…
Free
Details
WR
Writing Hookify Rules
anthropics · Workflow
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule"…
Free
Details
Security & Testing agent skills on mcprush sequence security work correctly — rotate the credential before rewriting the history, sketch the trust boundary before building the feature. The kinds are workflow, expertise, output format, voice & style and guardrail, and the one a skill belongs to is the fastest way to guess what it will do to your prompt.
What to look at before installing one is what it costs in context and what it takes away: a guardrail that refuses an action and a voice that rewrites a sentence are both skills, and only one of them will stop the agent doing something. Every skill here says which kind it is, what it costs in context, what it needs beside it to work and the licence it is published under, next to the publisher it came from and whether that publisher has been verified. The filters on the left narrow it further and the sort at the top decides what comes first.
A skill is not connected to anything: there is no endpoint to authorise and nothing routed through the gateway. Installing one drops a folder of instructions into the client’s own skill folder, and uninstalling it is deleting that folder. The exact line for each client is on the skill’s own page, because it differs by client rather than by skill.