Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
danstrem2/clawdbot-skill-master-pack
Agent Claude Code
Senior Frontend Architect who builds maintainable React/Next.js systems with performance-first mindset. Use when working on UI components, styling, state management, responsive design, or frontend architecture. Triggers on keywords like component, react, vue, ui, ux, css, tailwind, responsive.
Agent Claude Code
Use this agent when you need to understand and list OpenShift CI components including workflows, chains, and refs in a hierarchical structure.
Agent Claude Code
End-to-end bug fix agent — opens a Jira bug, writes the fix with tests, verifies build/format/tests pass, commits, posts a PR, and moves the ticket to Code Review. Use when the user says 'fix this bug', 'open a bug and fix it', 'file a bug', or describes a bug they want tracked and resolved in Jira with a PR.
Agent Claude Code
Executes quest phases end-to-end — plan, execute, verify, report. Spawned by quest-run orchestrator with fresh context per phase.
Agent Claude Code
Profile the application across frontend, backend, and database layers — identify bottlenecks and apply targeted optimizations.
Agent Claude Code
Orchestrates dual-pipeline code review with parallel Opus and Codex reviewers, synthesis, and interactive fix delegation. Use when performing code review, reviewing changes, or checking code quality. Context: User wants to review uncommitted changes user: "Review my dirty files" assistant: "I'll use the code-reviewer…
Agent Claude Code
A reasoning-focused coding subagent for architecture design, complex bug analysis, algorithm design, and comparing technical trade-offs.
Agent Claude Code
A legal-advice agent for checking jurisdiction-specific rules, privacy policies, terms of service, and open-source licence compatibility using primary sources.
Agent Claude Code
A lead research agent that receives a user's question, breaks it into smaller research tasks, coordinates six research groups, and combines their results. The source describes the groups and workflow in Chinese.
solanabr/position-manager-skill
Agent Claude Code
Use when: evaluating range/IL/exposure risk before a rebalance or deposit. Analyzes concentrated liquidity positions for impermanent loss, fee APR, range width, capital efficiency, and cross-DEX yield comparison. Triggers on keywords: IL, impermanent loss, range risk, rebalance risk, deposit risk, exposure, fee APR…
saugatapaul1010/claude-code-top1-setup
Agent Claude Code
You are the architecture-review-board — .
konveyor-ecosystem/playpen-pf-mig-skills
Agent Claude Code needs its repo
Generate a migration report from workspace artifacts. Reads status.md, visual reports, and screenshot directories to build report-data.json, then runs the HTML report generator.
asv-digital/agents-funcionarios
Agent Claude Code
Especialista em copy Google Ads — RSA (15 headlines max 30 chars + 4 descriptions max 90 chars com pinning Pos 1/2/3), 8 sitelinks (titulo 25 / desc 35-35), 4-10 callouts (25 chars), 4 structured snippets (25 chars por valor), price extension, promotion extension, copy Display, scripts YouTube (Bumper 6s / Non-skip…
Agent Claude Code
Stage, commit, and push code changes with conventional commits. Use when user says "commit", "push", or finishes a feature/fix.
Agent Claude Code
Create review-ready documents only. No implementation. Save documents to docs/.
Agent Claude Code
Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. Masters REST/GraphQL/gRPC APIs, event-driven architectures, service mesh patterns, and modern backend frameworks. Handles service boundary definition, inter-service communication, resilience patterns, and…
Agent Claude Code
Generates the final pull-request title and body after a 4CO-OP run is approved. Uses the plan, diff, builder notes, reviewer notes, and gatekeeper verdict to produce a clear PR description.
Agent Claude Code
Designs a concrete implementation blueprint for a new feature and writes the six plan documents directly — slices, files to create/modify, frozen per-slice API contracts, and data model changes. Slices the work vertically into contract-bounded work-units decomposed for maximum parallelism (BE/FE halves parallelise…
Agent Claude Code
Teach and explain existing codebases at project, module, and deep source-reading scopes, with source-grounded call paths, tensor shapes, formulas, and persistent learning plans when useful.
Agent Claude Code
Use this agent to find relevant best practices, examples, and anti-patterns for a specific prompt. Searches the references/ folder to find transformation patterns that match the task type. Returns specific examples, rules, and guidance to apply during transformation. Context: User wants to transform "fix the login…
Agent Claude Code
Generate comprehensive tests for Flutter code. Use when asked to "write tests", "add test coverage", or "generate tests for" a file or feature.
Agent Claude Code
A specialized helper for analyzing performance profiles from Ascend NPU tools, using local paths to profiling files such as ascendpt, ascendms, or PROF data.
Agent Claude Code
Runs the full coding workflow end-to-end for a given goal: clarify → analyze codebase → plan → implement → review → test. Spawns codebase-analyst and mcp-manager as subagents. Use when given a feature request or bug fix that requires understanding the codebase before touching code.
Agent Claude Code
Score compiled child skill artifacts against compilation-checklist. Dispatch after compile-write in Phase 3.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: