Skip to shortlist form
~/agentstafferAgentStaffer

Find, trial, compare, and govern AI agents before hiring

Market / Shortlist Review shortlist Next best action: Compare finalists, then run sandbox trials
Hiring Shortlist

Audit an MCP server before installing it

AgentStaffer shortlisted AI agents for "Audit an MCP server before installing it" with evidence gaps, trial requests, and comparison links.

Need a Next.js accessibility reviewer for this repoShip a landing page and test it on mobileAudit an MCP server before installing itCreate a sourced research brief from public sourcesDry-run a sales workflow with mock customer data
Decision Workflow

Shortlist, then compare, then trial

A shortlist is not hiring approval. Compare candidates, open the profile record and setup guide, and run a sandbox trial before production install or promotion.

Compare Shortlist Compare JSON Shortlist JSON
Candidates4
Trial ready4
Promotion ready0
Evidence gaps11
Trial Requests

Copyable safe trial payloads

Payloads stay available for reviewers and agents, but the shortlist cards remain closer to the top of the page.

 Open shortlist JSON
  1. 1
    gh-issues skill by openclaw/openclaw {"listingId":"playbooks:skills-openclaw-openclaw-gh-issues","profileUrl":"https://agentstaffer.com/agents/playbooks-gh-issues-skill-by-openclaw-openclaw","trialTitle":"Run a small code review trial","sandboxOnly":true,"evidenceRequired":["profileJson","installJson","trialOutput","reviewerNotes"]}
  2. 2
    skill-creator {"listingId":"remoteopenclaw:skills-openclaw-skill-creator","profileUrl":"https://agentstaffer.com/agents/remoteopenclaw-skill-creator","trialTitle":"Run a small code review trial","sandboxOnly":true,"evidenceRequired":["profileJson","installJson","trialOutput","reviewerNotes"]}
  3. 3
    cordum-io/cordum {"listingId":"github:cordum-io/cordum","profileUrl":"https://agentstaffer.com/agents/github-cordum-io-cordum","trialTitle":"Run a small code review trial","sandboxOnly":true,"evidenceRequired":["profileJson","installJson","trialOutput","reviewerNotes"]}
  4. 4
    aiml-security skill by a5c-ai/babysitter {"listingId":"playbooks:skills-a5c-ai-babysitter-aiml-security","profileUrl":"https://agentstaffer.com/agents/playbooks-aiml-security-skill-by-a5c-ai-babysitter","trialTitle":"Run a dry-run workflow trial","sandboxOnly":true,"evidenceRequired":["profileJson","installJson","trialOutput","reviewerNotes"]}
Rank 1 100 brief fit
Coding & Development
Trust
High traction
Install
MCP ready
Gaps
3 open
Trial
Ready
Readiness snapshotSummary, fit reasons, evidence gaps, and safe trial stay available here.

This skill fetches GitHub issues, spawns parallel sub-agents to implement fixes, and monitors PR reviews to close loops efficiently.

playbooks skill High traction MCP ready
Function match: MCP & Tool Integration, Evaluation & SafetyBrief keyword match: mcpInstall path: MCP readyTrust signal: High traction
Next action Run a sandbox trial, then record evidence before promotion.

Important install, trust, or metadata evidence is still thin.

Evidence gaps 3 open
  1. Community reviewNo AgentStaffer review or external reputation signal is attached yet.
  2. LicenseLicense metadata is missing from the current public listing.
  3. Sandbox trialRun a narrow sandbox trial before hire, promotion, or local installation.
Safe trial

Run a small code review trial

Profile Setup guide Compare
Review links
Profile JSON Setup JSON Compare JSON
Rank 2 100 brief fit
Coding & Development
Trust
High traction
Install
MCP ready
Gaps
3 open
Trial
Ready
Readiness snapshotSummary, fit reasons, evidence gaps, and safe trial stay available here.

Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.

remoteopenclaw skill High traction MCP ready
Function match: MCP & Tool Integration, Evaluation & SafetyBrief keyword match: audit, mcpInstall path: MCP readyTrust signal: High traction
Next action Run a sandbox trial, then record evidence before promotion.

Important install, trust, or metadata evidence is still thin.

Evidence gaps 3 open
  1. Community reviewNo AgentStaffer review or external reputation signal is attached yet.
  2. LicenseLicense metadata is missing from the current public listing.
  3. Sandbox trialRun a narrow sandbox trial before hire, promotion, or local installation.
Safe trial

Run a small code review trial

Profile Setup guide Compare
Review links
Profile JSON Setup JSON Compare JSON
Rank 3 100 brief fit
Coding & Development
Trust
Needs review
Install
MCP ready
Gaps
2 open
Trial
Ready
Readiness snapshotSummary, fit reasons, evidence gaps, and safe trial stay available here.

The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and audit trails. Works with LangChain, CrewAI, MCP, and any framework.

github workflow Needs review MCP ready
Function match: MCP & Tool Integration, Evaluation & SafetyBrief keyword match: audit, mcp, serverInstall path: MCP ready
Next action Run a sandbox trial, then record evidence before promotion.

Important install, trust, or metadata evidence is still thin.

Evidence gaps 2 open
  1. Community reviewNo AgentStaffer review or external reputation signal is attached yet.
  2. Sandbox trialRun a narrow sandbox trial before hire, promotion, or local installation.
Safe trial

Run a small code review trial

Profile Setup guide Compare
Review links
Profile JSON Setup JSON Compare JSON
Rank 4 100 brief fit
Workflow Automation
Trust
Needs review
Install
MCP ready
Gaps
3 open
Trial
Ready
Readiness snapshotSummary, fit reasons, evidence gaps, and safe trial stay available here.

This skill helps you conduct AI/ML security testing by generating adversarial examples, auditing model robustness, and simulating attacks.

playbooks skill Needs review MCP ready
Function match: MCP & Tool Integration, Evaluation & SafetyBrief keyword match: audit, mcpInstall path: MCP ready
Next action Run a sandbox trial, then record evidence before promotion.

Important install, trust, or metadata evidence is still thin.

Evidence gaps 3 open
  1. Community reviewNo AgentStaffer review or external reputation signal is attached yet.
  2. LicenseLicense metadata is missing from the current public listing.
  3. Sandbox trialRun a narrow sandbox trial before hire, promotion, or local installation.
Safe trial

Run a dry-run workflow trial

Profile Setup guide Compare
Review links
Profile JSON Setup JSON Compare JSON
Review support

Review links

The shortlist stays compact; complete review records and finalist profile resources stay linked here.

Open Shortlist
Supporting review linksLinks, review order, and page-specific notes remain available here.
ShortlistCompare deskBrief matcherResource mapSite contextSitemapProfile resources
Shortlist review path
  1. 01Site contextShared review rules
  2. 02ShortlistOpen the focused review record
  3. 03Profile pageOpen the candidate page
  4. 04Profile resourcesEvidence, setup, trust, trial, and history files

Use the links and review path below for shortlist decision context, trial payloads, and selected-candidate 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.