97 tagged claude desktop, measured the same way as everything else here.
Browse within: plugins 36claude-marketplace 23fastmcp 15data-analytics 11claude-code-skills 8ai-skills 6claude-code-skill 6openskills 6product-management 6claude-plugin 5
Agent Codex
GitHub issue and PR triage agent for slopus/happy. Use when you need to: review open issues/PRs, find duplicates, identify what needs a reply, close resolved items, draft maintainer responses, or get a status overview of the backlog. Invoke with /triage or when asked about issues, PRs, contributors, or community…
Agent Claude Code
Use this agent when you need to add new translatable strings to the application or verify existing translations. This includes: adding new UI text that needs to be translated, ensuring translations are consistent across all language files, verifying that translations fit the UI context (headers, buttons, multiline…
Agent
Drafts CHANGELOG entries from git log applying pm-skills CHANGELOG hygiene rules from CLAUDE.md: describe what changed (not where), public paths only, never reference gitignored NOTES/ or agent-context/SESSION-LOG/ or docs/internal/efforts/. Distinguishes user-facing from internal-only commits. Returns a draft for…
Agent
Use proactively after any PM-artifact-producing skill completes (deliver-prd, foundation-meeting-recap, foundation-okr-writer, foundation-persona, foundation-lean-canvas, discover-interview-synthesis, define-problem-statement, define-hypothesis, deliver-edge-cases, deliver-user-stories, deliver-acceptance-criteria…
Agent
Runs an ordered sequence of pm-skills from a prioritized-action-plan or a user-named chain, pausing for go/no-go and stopping on a failed or empty step. Explicit invocation only; never fires proactively.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Agent
Read-only helper that queries Binary Ninja MCP / BinAssistMCP and static-analysis CLIs (radare2, objdump, strings, otool, class-dump) on behalf of the main agent. Spawn this when a static probe will return >1 KB of disassembly, a function decompile, a symbol cross-reference list, or a full S-box / round-constant table…
Agent
Independent blue-team reviewer for algokiller Hypothesis Ledger. The main trace-analysis agent MUST spawn this reviewer before any hypothesisconclude(finalconfidence="high") call on a load-bearing hypothesis (one that will be cited by the final writeartifact). The reviewer examines the cited hypothesis in isolation …
Agent
Read-only ledger consistency reviewer. Spawn this near the end of a long ciphertext-recovery / trace-analysis session, BEFORE the main agent calls writeartifact on the final recovered.py / report.md. The curator scans the hypothesis ledger and produces a one-page audit of (a) which concluded hypotheses are cited by…
MarcusJellinghaus/mcp-workspace
Agent Claude Code
Commits and pushes changes. Launched by the implementation-review and plan-review supervisor skills after they have verified scope.
MarcusJellinghaus/mcp-workspace
Agent Claude Code
Approves an issue for workflow status transition. Launched by the issue-analysis supervisor skill once no open questions remain.
MarcusJellinghaus/mcp-workspace
Agent Claude Code
Updates a GitHub issue with refined content. Launched by the issue-analysis supervisor skill after the content has been agreed.
adityaarsharma/youtube-marketing-skills
Agent
POSIMYTH Golden Circle — Email Agent. Handles FluentCRM newsletters, onboarding sequences, release emails, win-backs, and awareness broadcasts. Enforces POSIMYTH brand voice, Gutenberg block format, and hard quality rules on every draft.
adityaarsharma/youtube-marketing-skills
Agent
YouTube Video Updater Agent — bulk-optimises your product/brand videos for CTR, search rank, and LLM discoverability. Fixes links, injects keywords, improves timestamps, generates A/B title variants, posts pinned keyword comment. Sends full diff report before any live write.
kylehughes/writing-prose-like-a-human-for-agents
Agent
Rewrites prose to remove AI writing patterns. Use when editing documentation, READMEs, PR descriptions, commit messages, or any text that should not read like AI output.
charles-adedotun/notifications-mcp-server
Agent Claude Code
Specialized agent for server-side development with modern backend frameworks, APIs, databases, and cloud infrastructure. Expert in building secure, scalable, and performant backend systems across multiple languages and platforms with comprehensive testing and monitoring strategies.
charles-adedotun/notifications-mcp-server
Agent Claude Code
Specialized agent for React frontend development with shadcn/ui, Tailwind CSS v4, and modern best practices. Expert in implementing design systems, ensuring accessibility, and building performant user interfaces following the 4-font-size, 2-weight typography system, 8pt grid spacing, and 60/30/10 color distribution…
charles-adedotun/notifications-mcp-server
Agent Claude Code
Specialized agent for product requirements analysis, system architecture design, and technical specifications. Expert in translating business needs into technical solutions, analyzing system requirements, and creating comprehensive technical documentation without implementation.
Agent
Automated testing verification and generation agent for NPM applications. Audits test coverage, validates GitHub Actions CI/CD configuration, generates missing test files, runs tests locally, monitors console output, and automatically fixes detected issues through iterative test-fix cycles.
Agent
Wiki and documentation agent for BetTrack. Use when: writing or updating wiki pages, updating API-DOCUMENTATION.md or Database-Guide.md, adding changelog entries, auditing broken links, generating Tables of Contents, documenting new API endpoints, documenting database schema changes, reviewing documentation…
Agent
Vulnerability-hunting rigor reviewer. The main agent spawns three concurrent instances of this subagent when claiming a finding has reached the session goal severity. Each instance carries one of three audit perspectives (Technical-Nitpick / Impact-Skeptic / Scope-Policy). Independent PASS or FAIL verdict per…
Agent
Vulnerability-hunting strategist. The main agent spawns six concurrent instances of this subagent when stuck, hitting walls, showing quit semantics, or about to ask the user "what next" during hunting. Each instance carries one of six thinking perspectives (Chainer / Skeptic / Lateral / DevPsych / Scope-Expander /…