nano-banana-ultimate
claudeGenerate and edit images via Google Gemini with domain-specialized prompt building
8 skills
Quality assurance toolkit to analyze codebases, review code changes, perform focused appsec reviews, babysit PR CI until green, ship production security hotfixes for vulnerable npm dependencies, remove dead code with verified Haiku subagents, audit React patterns, fix the agentic harness, and improve skills
Plugin devx-qa from marketplace devx-plugins in agentic-dev3o/devx-plugins. Commands read from the repo's manifest — 2 days ago.
appsec-reviewThis skill should be used when the user asks to "security review this PR", "review this diff for vulnerabilities", "appsec review these changes", "audit this branch for auth, injection, or data exposure bugs", "check this code for exploitable security issues", or requests a focused application secur
babysit-prMonitors a GitHub pull request's checks with the gh CLI, reads the logs of failing GitHub Actions jobs, classifies each failure as branch-caused or infrastructure, and drives the PR to green — fixing the branch's own breakage and delegating every commit, merge, and push to the devx-git skills. Use w
code-reviewReviews pull requests and code changes for correctness, conventions, maintainability, performance, test coverage, and security. Use when the user asks for a code review, PR review, feedback on a diff, or to check code quality.
dead-code-fixerFinds and removes dead code across a repository too large for one context window. Static analyzers and a repository-wide reference count propose candidates, Haiku subagents verify each one through three independent lenses, and confirmed-dead code is deleted in waves gated by the project's type-check
explaining-architectureAnalyzes project architecture and generates ASCII state machine and sequence diagrams. Use for explaining a project, analyzing architecture, tracing an entrypoint, showing a state machine, or generating a sequence diagram.
fixing-harnessAudits a project's agentic harness (CLAUDE.md, AGENTS.md, .claude/rules, .claude/settings.json) and refactors it into a layered, path-scoped configuration that loads only what is relevant. Rewrites CLAUDE.md and AGENTS.md as a thin critical-rules layer, segments domain rules with `paths:` frontmatte
fixing-react-antipatternsAudits React codebases for anti-patterns (useEffect misuse, missing cleanup, stale closures, derived-state-in-effects, memory leaks) and produces a scored gap analysis table with severity ratings. Applies prioritized fixes on request. Triggers on: audit react code, fix react anti-patterns, review re
sec-patching-tsShips a production security hotfix for vulnerable npm dependencies in a TypeScript or Node.js repository, on a trust-but-verify basis with proportional risk handling. It trusts the package manager to resolve a patched version, then verifies that the advisory is real and reaches production, that the
fixing-skillsEvaluate and improve a plugin's skills by applying Anthropic's skill authoring best practices. Use to fix, improve, or review skills for a specific plugin or agent team.
dead-code-removerEditing agent dispatched by the devx-qa dead-code-fixer skill to delete declarations that three verifiers confirmed dead, inside the files its unit allows. Not for direct use.
dead-code-scannerRead-only inventory agent dispatched by the devx-qa dead-code-fixer skill to list every declaration in one shard of source files. Not for direct use.
dead-code-verifierRead-only verifier dispatched by the devx-qa dead-code-fixer skill to try to prove, through one lens, that dead-code candidates are still used. Not for direct use.
Generate and edit images via Google Gemini with domain-specialized prompt building
8 skills
Streamline your git workflow with simple commands for committing, pushing, and creating pull requests
3 skills
Audit agents, tool loops, and inference requests across six dimensions, and rewrite prompts using Anthropic best practices
2 skills
Create high-converting landing pages with structured copywriting and opinionated HTML/CSS generation
2 skills
Phosphorer sur son produit jusqu'à ce qu'il tienne la route : personas, pari, principes, fonctionnalités, puis une spécification fonctionnelle prête pour la maquette et le développement
1 skill
Security hook that blocks Claude from reading, writing, or accessing secret and sensitive files
hooks
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.