菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 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.
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 | company-research |
| version | 1.1.0 |
| description | 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. |
| mcp_server | primr |
| tools | ["estimate_run","research_company","check_jobs","wait_for_status_change"] |
| resources | ["primr://research/modes","primr://research/status","primr://output/latest","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}"] |
Use this skill to start and monitor Primr research runs through MCP. Treat MCP as the source of truth for current modes, defaults, and outputs.
Read primr://research/modes to confirm the current mode guidance.
Read primr://research/status to see whether a run is already active.
Call estimate_run before starting a new run. Supports platforms (array), strategy_type, and no_ai_strategy parameters. Returns estimated_time_range alongside estimated_time_minutes.
Present the estimate, state that the run incurs real API cost, and get explicit approval before calling research_company.
After starting a run, monitor with wait_for_status_change or check_jobs until terminal.
Read primr://output/artifacts/by_job/{job_id} to inventory completed-job
artifacts without report body content, then read primr://output/latest only
when a report preview is needed to present the result and next actions. Read
primr://output/qa_summary/by_job/{job_id} when QA artifacts are attached and
the user needs QA outcome metadata. Read
primr://output/usage_summary/by_job/{job_id} when the user needs cost,
timing, approval, or artifact-count metadata.
Read primr://output/source_summary/by_job/{job_id} when the user needs
citation/source appendix metadata.
Read primr://output/trace_summary/by_job/{job_id} when the user needs scrape
trace health metadata.
Read primr://output/verification_summary/by_job/{job_id} when the user needs
claim verification trust score, claim counts, status counts, first-party
downgrade counts, or source-reference counts without raw claims, source URLs,
search queries, explanations, or report body content.
Read primr://output/calibration_summary/by_job/{job_id} when the user needs
label-calibration counts, inference source-copy counts, evidence-review count
buckets, judge provenance, or judge-agreement metadata 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.
Prefer the lightest mode that answers the request.
Do not restate fixed pricing or provider defaults from memory. Use MCP resources and estimate_run.
If a job is already in progress, surface that state instead of starting a second run.
Treat full as the standard end-to-end workflow and premium as the higher-cost, higher-depth option.
Expect standard runs to take roughly 35-50 minutes and premium multi-vendor runs to reach 75-120 minutes.
Do not hold the client in a synchronous wait for the entire run; launch once, then monitor and resume from job state.
User: Research ExampleCo at https://example.com
1. Read primr://research/modes
2. Read primr://research/status
3. estimate_run(company_url="https://example.com", mode="full")
4. After approval: research_company(company_name="ExampleCo", company_url="https://example.com", mode="full", max_estimated_cost_usd=0.67)
5. wait_for_status_change(job_id="...", timeout_seconds=60)
job_in_progress: report the active run and offer to monitor it.
invalid_url or ssrf_blocked: ask for a valid public URL or switch to deep if appropriate.
rate_limit_exceeded: wait for the retry window and retry.