~/agentstafferAgentStaffer
Find, trial, compare, and govern AI agents before hiring
Roles / Technical Category
Review matching candidates
Next best action: Open a profile, compare evidence, then run a sandbox trial
Workflow Automation
Agents that run repeatable workflows, automate operations, trigger actions, or coordinate task pipelines.
4996total
4996filtered
312page
417pages
Category fit
Which technical function should the agent perform?
Filter candidates by capability, protocol, trust, install readiness, and trial status.
- Turn a repeatable business process into a safe workflow.
- Connect triggers, queues, and review gates.
- Run a dry-run before production automation.
Recommended trials and bundles
explainx / skill
llm-evaluation
Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
llm-function-calling skill by amnadtaowsoam/cerebraskills
This skill enables LLM function calling to execute external tools and return structured results for seamless integrations.
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
llm-integration skill by yonatangross/orchestkit
This skill provides production-ready LLM integration patterns for function calling, streaming, local inference, and fine-tuning to streamline tool use.
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
lnemail skill by openclaw/skills
This skill helps agents securely obtain anonymous email via LNemail for 2FA, notifications, and messages using Lightning payments.
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
explainx / agent
LobeChat
LobeChat Cloud offers 450,000 free computing credits to registered users, with no complex configuration required, ready-to-use features, unlimited conversati…
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
explainx / agent
LobeHub
LobeChat: Personal LLM productivity tool, surpassing the ChatGPT / OLLaMA user experience
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
local-llm-router skill by hoodini/ai-agents-skills
This skill routes coding queries to local LLMs in air-gapped environments, leveraging Serena MCP for semantic code understanding and secure offline inference.
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
localization-testing skill by proffesor-for-testing/agentic-qe
This skill helps validate multilingual translations, locale formatting, RTL layouts, and cultural appropriateness across products.
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
Review support
Open Category guide
Review links
Technical category pages stay focused on job browsing; complete review records and finalist profile resources stay linked here.
Supporting review linksLinks, review order, and page-specific notes remain available here.
Category guideTechnical role guideAgent inventoryResource mapReview guideAPI referenceSite contextSitemapProfile resources
4996 matching candidates for Workflow Automation. Open candidate profiles for fit, setup guidance, trust evidence, and sandbox trial planning.
- 01Site contextShared review rules
- 02Role categoryOpen the focused review record
- 03Agent inventoryBrowse the matching inventory
- 04Profile resourcesEvidence, setup, trust, trial, and history files
Use the links and review path below for role-category candidates, related playbooks, and finalist profile resources before action.
Review route: OpenAI review tools can start with openai.json; otherwise use site context and agent inventory before opening the finalist's complete review materials before install, hire, or promotion.