← all publishers

agent-sh

@agent-sh source repo

50 published skills

  1. Agnix · agent-sh
    Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 455 rules.
    0
    installs
  2. Agnix 2 · agent-sh
    Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 455 rules across 10+ AI tools.
    0
    installs
  3. Test Skill 2 · agent-sh
    Use when testing per-client skill rules
    0
    installs
  4. Test Skill 3 · agent-sh
    Use when testing per-client skill rules
    0
    installs
  5. Test Skill 4 · agent-sh
    Use when testing per-client skill rules
    0
    installs
  6. Test Skill 5 · agent-sh
    Use when testing per-client skill rules
    0
    installs
  7. Test Skill 6 · agent-sh
    Use when testing per-client skill rules
    0
    installs
  8. Test Skill 7 · agent-sh
    Use when testing per-client skill rules
    0
    installs
  9. Test Skill 8 · agent-sh
    Use when testing per-client skill rules
    0
    installs
  10. Audit Project · agent-sh
    Use when user asks to 'review my code', 'audit the codebase', 'run code review', 'check for issues', 'find bugs', 'security review', 'performance review', or wants multi-agent iterative review. Spawns role-based reviewers (code-quality-reviewer, security-expert, performance-engineer, test-quality-guardian, architecture-reviewer, database-specialist, api-designer, frontend-specialist, backend-specialist, devops-reviewer) and loops until critical/high issues are resolved.
    0
    installs
  11. Banthis · agent-sh
    Use when user asks to ban, stop, or remember not to repeat an agent behavior ('stop doing X', 'you keep doing X', 'ban this'). Immediately capture it as a permanent negative rule using the banthis tool.
    0
    installs
  12. Can I Help · agent-sh
    Use when user asks to "contribute", "where can I help", "good first issue", "what needs work", "how to contribute", "where to start contributing", "find tasks", "help with project". Analyzes project needs and matches to developer skills.
    0
    installs
  13. Computer Use Linux · agent-sh bundle
    Linux desktop observation and control via native Pi tools or the computer-use-linux MCP server: accessibility trees, screenshots, window targeting, and input synthesis (click, type, scroll).
    0
    installs
  14. Drift Analysis · agent-sh
    Use when the user asks about plan drift, reality check, comparing docs to code, project state analysis, roadmap alignment, implementation gaps, or needs guidance on identifying discrepancies between documented plans and actual implementation state.
    0
    installs
  15. Onboard · agent-sh
    Use when user asks to "onboard to project", "what does this project do", "summarize codebase", "get oriented", "new to this repo", "quick overview", "project summary", "codebase tour", "help me understand this code". Collects project data automatically then guides interactively.
    0
    installs
  16. Skill Curator · agent-sh
    Use when user asks to create, improve, or review production-grade SKILL.md files for Claude Code, Cursor, Codex, OpenCode, Kiro, and other agent tools. Focuses on trigger quality, structure, cross-tool compatibility, and reliable activation.
    0
    installs
  17. Sync Docs · agent-sh
    Sync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelog, or after code changes.
    0
    installs
  18. System Prompt Curator · agent-sh
    Use when user asks to create, improve, or debug production-grade system prompts for autonomous coding agents and multi-agent orchestration. Not for user-facing messages or chat prompts.
    0
    installs
  19. Recommend · agent-sh
    Analyze accumulated skillers knowledge and suggest skills, hooks, and agents. Use when compacting is done and patterns need classification. Checks existing ecosystem before recommending.
    0
    installs
  20. Skillers Compact · agent-sh
    Compact conversation transcripts into themed knowledge files.
    0
    installs
  21. Glide Mq · agent-sh bundle
    Creates message queues, workers, job workflows, and fan-out broadcasts using glide-mq on Valkey/Redis Streams. Provides API reference, code patterns, and configuration for queues, workers, delayed/priority jobs, schedulers, batch processing, DAG workflows, request-reply, serverless producers, and AI-native primitives (usage tracking, token streaming, suspend/resume, budget caps, fallback chains, dual-axis rate limiting, rolling usage summaries, vector search, HTTP proxy/SSE). Triggers on "glide-mq", "glidemq", "job queue valkey", "background tasks valkey", "message queue redis streams", "glide-mq LLM queue", "glide-mq AI orchestration queue", "glide-mq token rate limiting", "glide-mq model fallback", "glide-mq human-in-the-loop queue", "glide-mq vector search", "glide-mq AI pipeline".
    0
    installs
  22. Glide Mq Migrate Bee · agent-sh bundle
    Migrates Node.js applications from Bee-Queue to glide-mq. Covers the chained builder-to-options API conversion, Queue/Worker separation, and event mapping. Use when converting bee-queue projects to glide-mq, replacing bee-queue with glide-mq, or planning a bee-queue migration. Triggers on "bee-queue to glide-mq", "replace bee-queue with glide-mq", "migrate from bee-queue", "beequeue migration glide-mq".
    0
    installs
  23. Glide Mq Migrate Bullmq · agent-sh bundle
    Migrates Node.js applications from BullMQ to glide-mq. Covers connection config conversion, API mapping, breaking changes, and new features available after migration. Use when converting BullMQ queues and workers to glide-mq, replacing bullmq with glide-mq, or comparing BullMQ vs glide-mq APIs. Triggers on "bullmq to glide-mq", "replace bullmq with glide-mq", "migrate from bullmq", "switch from bullmq to glide-mq", "convert bullmq to glide-mq", "bullmq migration glide-mq".
    0
    installs
  24. Prepare Delivery · agent-sh
    Use when user asks to "prepare delivery", "run quality gates", "review code", "run pre-gates", "deslop and review", "validate before shipping", or has finished implementation and wants quality checks before shipping.
    0
    installs
  25. Validate Delivery · agent-sh
    Use when user asks to "validate delivery", "check readiness", or "verify completion". Runs tests, build, and requirement checks with pass/fail instructions.
    0
    installs
  26. Orchestrate Review · agent-sh
    Use when user asks to "deep review the code", "thorough code review", "multi-pass review", or when orchestrating the review loop in a delivery pipeline. Provides review pass definitions (code quality, security, performance, test coverage), signal detection patterns, and iteration algorithms.
    0
    installs
  27. Check Test Coverage · agent-sh
    Use when validating test coverage quality for new code. Checks that tests exist, are meaningful, and actually exercise new code - not just path matching.
    0
    installs
  28. Discover Tasks · agent-sh
    Use when user asks to "discover tasks", "find next task", "prioritize issues", "what should I work on", or "list open issues". Discovers and ranks tasks from GitHub, GitLab, local files, and custom sources.
    0
    installs
  29. Perf Code Paths · agent-sh
    Use when mapping code paths, entrypoints, and likely hot files before profiling.
    0
    installs
  30. Perf Theory Gatherer · agent-sh
    Use when generating performance hypotheses backed by git history and code evidence.
    0
    installs
  31. Maintain Cross Platform · agent-sh
    Use when preparing releases, validating cross-platform compatibility, or updating installation infrastructure. Meta-skill for maintaining AgentSys's 3-platform architecture.
    0
    installs
  32. Learn · agent-sh
    Research any topic online and create learning guides. Use when user asks to 'learn about', 'research topic', 'create learning guide', 'build knowledge base', or 'study subject'.
    0
    installs
  33. Debate · agent-sh
    Structured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools, 'debate topic', 'argue about', 'stress test idea', 'devil advocate'.
    0
    installs
  34. Deslop · agent-sh
    Use when user wants to clean AI slop from code. Use for cleanup, remove debug statements, find ghost code, repo hygiene.
    0
    installs
  35. Repo Intel · agent-sh
    Use when user asks to "run repo intel", "generate repo map", "analyze repo", "query hotspots", "check ownership", or "bus factor". Unified static analysis - git history, AST symbols, project metadata.
    0
    installs
  36. With Model · agent-sh
    Use when testing valid model configuration
    0
    installs
  37. Code Review · agent-sh
    Use when user asks to review code for quality and security issues.
    0
    installs
  38. Deploy Prod · agent-sh
    Use when deploying to production environment
    0
    installs
  39. Unknown Tool Skill · agent-sh
    Use when testing unknown tool validation
    0
    installs
  40. Invalid Agent Skill · agent-sh
    Use when testing invalid agent validation
    0
    installs
  41. Invalid Model Skill · agent-sh
    Use when testing invalid model validation
    0
    installs
  42. Invalid Context Skill · agent-sh
    Use when testing invalid context validation
    0
    installs
  43. With Custom Agent · agent-sh
    Use when testing custom agent validation
    0
    installs
  44. With Context Agent · agent-sh
    Use when testing valid context and agent configuration
    0
    installs
  45. Too Many Injections Skill · agent-sh
    Use when testing injection limit validation
    0
    installs
  46. Reference Skill · agent-sh
    Use when looking up documentation
    0
    installs
  47. Fork With Instructions · agent-sh
    Use when analyzing code quality
    0
    installs
  48. Social Source Evidence · agent-sh
    Use when reviewing X/Twitter exports as source evidence for social content decisions.
    0
    installs
  49. Agent Without Context Skill · agent-sh
    Use when testing agent without context validation
    0
    installs
  50. Test Skill · agent-sh
    Use when testing per-client skill rules
    0
    installs