Menu
Run and monitor company research through Primr MCP. Use when the user wants a new research run, asks for status, or needs mode selection help before starting.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Produce a primr-style strategic company brief using ONLY the host agent's own tools (web search, page fetch, shell DNS lookups) at subscription cost. No primr install, no API keys, no GPU. Use when the user wants a structured pre-discovery brief on a company but cannot or does not want to run the full primr pipeline. For the full pipeline (deeper scraping, 40+ sources, cross-validation, QA gates), use the primr skill instead.
Build a substantial, sourced Primr-style company dossier with zero Primr model API spend by combining keyless evidence collection with an official agent host. Use when an agent host receives a bare Primr company-and-URL request without explicit paid intent, the user has no API keys or GPU, wants to use an included Codex, Claude, Copilot, Gemini, Cowork, or other plan allowance, asks for a free or hard-zero Primr path, or supplies a Primr prep evidence bundle. Verify that the host is plan-backed and will not bill API usage or overages before promising zero total incremental spend.
Route and run Primr company research from an agent host. Use for a bare Primr company-and-URL request, named Primr report, full strategic dossier, Strategic Overview, or strategy module. Default to Primr Zero unless the user explicitly requests paid, metered, provider-backed, or premium execution; use an inline primr prep fallback when primr-zero is unavailable. Route quick briefs to host web research and DNS-only requests to primr recon.
Run end-to-end company research through Primr. Use when the user asks to research a company, provides a company URL, or wants a new strategic analysis run.
Guide mode selection when site scraping is weak, blocked, or low quality. Use when the user asks why scraping failed or how Primr should proceed on a protected site.
Generate strategy documents from completed Primr research. Use when the user wants AI, CX, security, or data strategy deliverables from an existing report.
| name | primr-research |
| version | 1.1.0 |
| description | Run and monitor company research through Primr MCP. Use when the user wants a new research run, asks for status, or needs mode selection help before starting. |
| metadata | {"openclaw":{"requires":{"bins":["primr-mcp"],"env":["XAI_API_KEY","GEMINI_API_KEY"],"os":["linux","darwin","win32"]}}} |
| mcp_server | primr |
| tools | ["estimate_run","research_company","check_jobs","cancel_job","wait_for_status_change"] |
| resources | ["primr://research/modes","primr://research/status","primr://output/latest","primr://output/artifacts","primr://output/artifacts/by_job/{job_id}","primr://output/qa_summary/by_job/{job_id}","primr://output/usage_summary/by_job/{job_id}","primr://output/source_summary/by_job/{job_id}","primr://output/trace_summary/by_job/{job_id}","primr://output/verification_summary/by_job/{job_id}","primr://output/calibration_summary/by_job/{job_id}"] |
This skill is a thin orchestrator over Primr MCP.
Use MCP resources to discover current behavior instead of assuming fixed costs, providers, or defaults from the skill text. full is the standard end-to-end workflow, premium is the higher-depth option, and scrape and deep are narrower research modes.
Research runs are async jobs. Start the run, then monitor status until terminal. Standard runs often take 35-50 minutes; premium multi-vendor runs can take 75-120 minutes.
Read primr://research/modes before advising on mode selection.
Use scrape for first-party reconnaissance.
Use deep when the site is blocked or low-signal.
Use full for the default strategic analysis workflow.
Use premium when the user explicitly wants maximum depth.
Always call estimate_run before research_company, then state that the run incurs real API cost and wait for explicit user approval.
estimate_run(company_url="https://example.com", mode="full")
After user approval, call research_company and pass the approved max_estimated_cost_usd when available, then monitor with wait_for_status_change, check_jobs, or primr://research/status. Do not assume the client session will stay attached for the entire run.
research_company(company_name="ExampleCo", company_url="https://example.com", mode="full")
When the run completes, read primr://output/artifacts/by_job/{job_id} first
to inventory artifacts without report body content. Read
primr://output/qa_summary/by_job/{job_id} when QA artifacts are attached.
Read primr://output/usage_summary/by_job/{job_id} when cost, timing,
approval, or artifact-count metadata is needed.
Read primr://output/source_summary/by_job/{job_id} when citation/source
appendix metadata is needed.
Read primr://output/trace_summary/by_job/{job_id} when scrape trace health
metadata is needed.
Read primr://output/verification_summary/by_job/{job_id} when claim
verification trust score, claim counts, status counts, first-party downgrade
counts, or source-reference counts are needed without raw claims, source URLs,
search queries, explanations, or report body content.
Read primr://output/calibration_summary/by_job/{job_id} when
label-calibration counts, inference source-copy counts, evidence-review count
buckets, judge provenance, or judge-agreement metadata is needed without raw
claims, source URLs, evidence reviews, rationales, or report body content.
MCP resource reads are audit-logged with hashed URI/result values and
normalized resource kind, without raw URI query values or resource bodies.
A2A skill calls are audit-logged with hashed message/result payloads, hashed
caller ids, granted scopes, duration, outcome, and job id when present, without
raw message text, task ids, URLs, report paths, raw results, or caller ids.
Read primr://output/latest only when the next step needs a report preview.
job_in_progress: report the existing run and monitor it instead of starting another.
invalid_url or ssrf_blocked: require a valid public URL, or consider deep mode.
rate_limit_exceeded: wait for the retry window.
api_error: surface the provider error clearly and recommend retry or diagnostics.