WorkorAI
Overview
WorkorAI is a talent marketplace exposed to agents through an MCP server
(streamable HTTP at https://workorai.com/mcp, listed on the official MCP
Registry as io.github.work0r-ai/workorai). This skill routes requests by
intent across the dual-role tool surface: 9 candidate.* tools (job search,
job detail, applications, apply, invitations, saved jobs) and the
employer.* tools (job lifecycle, candidate discovery, invitations,
applicant review). Employer candidate discovery returns tiered rankings
(best/good/weak) with a white-box match explanation per candidate — fit
score, skills proven in interview, gaps, and a quotable rationale — instead
of a black-box score.
When to Use This Skill
- Use when a user asks to find a job, search vacancies, apply to a position,
or track their applications ("find me a job", "ищу работу").
- Use when an employer wants to post, publish, update, close, or archive a
job on WorkorAI.
- Use when an employer asks to find, rank, compare, or evaluate candidates,
or asks why a candidate matches a role.
- Use when a user needs to set up or troubleshoot the WorkorAI MCP
connection and API key onboarding.
How It Works
Step 1: Connect the MCP server
Add the WorkorAI MCP server to your agent's MCP configuration. For Claude
Code:
claude mcp add --transport http workorai https://workorai.com/mcp
If the user has no API key yet, call the request_access tool and follow
the onboarding it returns.
Step 2: Route by role and intent
Detect whether the request is a candidate flow or an employer flow, then use
the matching tool group:
- Candidate:
candidate.search_jobs, candidate.get_job,
candidate.apply_to_job, candidate.get_applications,
candidate.accept_invitation / candidate.decline_invitation,
candidate.withdraw_application, candidate.set_saved_job,
candidate.get_saved_jobs.
- Employer:
employer.create_job → employer.publish_job →
employer.close_job / employer.archive_job for the lifecycle;
employer.search_candidates_for_job or
employer.search_candidates_by_query for discovery;
employer.invite_candidate, employer.list_applicants,
employer.get_applicant_detail, employer.set_review_status for
pipeline work.
Step 3: Explain matches with white-box data
When presenting employer search results, keep the tier structure
(best/good/weak) and surface each candidate's matchExplanation: fit score,
interview-proven skills, gaps, and rationale. For deeper comparison, fetch
per-candidate interview evidence with employer.get_candidate_evidence and
employer.get_applicant_transcript.
Examples
Example 1: Candidate job search
User: "Find me remote TypeScript jobs and apply to the best one."
Agent: candidate.search_jobs(query="TypeScript", remote=true)
→ present ranked results → candidate.get_job(id)
→ confirm with the user → candidate.apply_to_job(id)
Example 2: Employer candidate discovery
User: "Who are the best candidates for my Senior Backend role?"
Agent: employer.search_candidates_for_job(jobId)
→ report Best tier with each candidate's fit score, proven
skills, and gaps → employer.invite_candidate on approval
Best Practices
- ✅ Confirm with the user before applying, inviting, or changing job
status — these are visible, stateful marketplace actions.
- ✅ Quote the white-box match explanation when recommending a candidate,
so the employer sees why, not just a score.
- ✅ Use
request_access for key onboarding instead of asking users to
paste credentials into chat.
- ❌ Don't fabricate fit scores or ranks — only report what the tools
return.
- ❌ Don't apply to jobs or send invitations in bulk without explicit
user approval.
Limitations
- Requires a WorkorAI account and API key; tools fail without a valid key.
- This skill does not replace environment-specific validation, testing, or
expert review.
- Stop and ask for clarification if required inputs, permissions, or safety
boundaries are missing.
Security & Safety Notes
- All operations go through the remote WorkorAI MCP server over HTTPS; the
skill itself runs no shell commands.
- Mutating tools (apply, withdraw, invite, publish, close, delete) should
be preceded by an explicit user confirmation.
- Treat API keys as secrets: store them in MCP client configuration, never
in chat transcripts or committed files.
Additional Resources
1---2name: workorai3description: "WorkorAI talent-marketplace skill: candidates search jobs and manage applications; employers run the job lifecycle and get ranked candidate matches with white-box fit explanations."4category: productivity5risk: critical6source: community7source_repo: work0r-ai/agent-kit8source_type: community9date_added: "2026-07-03"10author: work0r-ai11tags: [job-search, hiring, recruiting, talent-marketplace, mcp]12tools: [claude, cursor, gemini]13license: "MIT"14license_source: "https://github.com/work0r-ai/agent-kit/blob/main/skills/workorai/LICENSE.txt"15metadata:16 source: https://skillmd.com/skills/mhassan0000/workorai17---1819# WorkorAI2021## Overview2223WorkorAI is a talent marketplace exposed to agents through an MCP server24(streamable HTTP at https://workorai.com/mcp, listed on the official MCP25Registry as `io.github.work0r-ai/workorai`). This skill routes requests by26intent across the dual-role tool surface: 9 `candidate.*` tools (job search,27job detail, applications, apply, invitations, saved jobs) and the28`employer.*` tools (job lifecycle, candidate discovery, invitations,29applicant review). Employer candidate discovery returns tiered rankings30(best/good/weak) with a white-box match explanation per candidate — fit31score, skills proven in interview, gaps, and a quotable rationale — instead32of a black-box score.3334## When to Use This Skill3536- Use when a user asks to find a job, search vacancies, apply to a position,37 or track their applications ("find me a job", "ищу работу").38- Use when an employer wants to post, publish, update, close, or archive a39 job on WorkorAI.40- Use when an employer asks to find, rank, compare, or evaluate candidates,41 or asks why a candidate matches a role.42- Use when a user needs to set up or troubleshoot the WorkorAI MCP43 connection and API key onboarding.4445## How It Works4647### Step 1: Connect the MCP server4849Add the WorkorAI MCP server to your agent's MCP configuration. For Claude50Code:5152```bash53claude mcp add --transport http workorai https://workorai.com/mcp54```5556If the user has no API key yet, call the `request_access` tool and follow57the onboarding it returns.5859### Step 2: Route by role and intent6061Detect whether the request is a candidate flow or an employer flow, then use62the matching tool group:6364- Candidate: `candidate.search_jobs`, `candidate.get_job`,65 `candidate.apply_to_job`, `candidate.get_applications`,66 `candidate.accept_invitation` / `candidate.decline_invitation`,67 `candidate.withdraw_application`, `candidate.set_saved_job`,68 `candidate.get_saved_jobs`.69- Employer: `employer.create_job` → `employer.publish_job` →70 `employer.close_job` / `employer.archive_job` for the lifecycle;71 `employer.search_candidates_for_job` or72 `employer.search_candidates_by_query` for discovery;73 `employer.invite_candidate`, `employer.list_applicants`,74 `employer.get_applicant_detail`, `employer.set_review_status` for75 pipeline work.7677### Step 3: Explain matches with white-box data7879When presenting employer search results, keep the tier structure80(best/good/weak) and surface each candidate's `matchExplanation`: fit score,81interview-proven skills, gaps, and rationale. For deeper comparison, fetch82per-candidate interview evidence with `employer.get_candidate_evidence` and83`employer.get_applicant_transcript`.8485## Examples8687### Example 1: Candidate job search8889```90User: "Find me remote TypeScript jobs and apply to the best one."91Agent: candidate.search_jobs(query="TypeScript", remote=true)92 → present ranked results → candidate.get_job(id)93 → confirm with the user → candidate.apply_to_job(id)94```9596### Example 2: Employer candidate discovery9798```99User: "Who are the best candidates for my Senior Backend role?"100Agent: employer.search_candidates_for_job(jobId)101 → report Best tier with each candidate's fit score, proven102 skills, and gaps → employer.invite_candidate on approval103```104105## Best Practices106107- ✅ Confirm with the user before applying, inviting, or changing job108 status — these are visible, stateful marketplace actions.109- ✅ Quote the white-box match explanation when recommending a candidate,110 so the employer sees why, not just a score.111- ✅ Use `request_access` for key onboarding instead of asking users to112 paste credentials into chat.113- ❌ Don't fabricate fit scores or ranks — only report what the tools114 return.115- ❌ Don't apply to jobs or send invitations in bulk without explicit116 user approval.117118## Limitations119120- Requires a WorkorAI account and API key; tools fail without a valid key.121- This skill does not replace environment-specific validation, testing, or122 expert review.123- Stop and ask for clarification if required inputs, permissions, or safety124 boundaries are missing.125126## Security & Safety Notes127128- All operations go through the remote WorkorAI MCP server over HTTPS; the129 skill itself runs no shell commands.130- Mutating tools (apply, withdraw, invite, publish, close, delete) should131 be preceded by an explicit user confirmation.132- Treat API keys as secrets: store them in MCP client configuration, never133 in chat transcripts or committed files.134135## Additional Resources136137- [Source repository](https://github.com/work0r-ai/agent-kit) — full skill138 with reference files and agents (npm: `@workorai/agent-kit`)139- [WorkorAI MCP endpoint](https://workorai.com/mcp)