菜单
Reads a raw JD and produces a YAML snippet for opportunities.yaml plus optional jd_catalog.csv row. Use when adding a new pipeline opportunity from data/raw, ingesting a JD file, or bootstrapping opportunity id and next_action fields.
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。
Researches a company and writes a structured SWE-focused brief with source discipline, personal fit vs master.yaml, and Proceed/Pass-style conclusion. Use when the user asks for company research or employer due diligence.
End-to-end JD processing workflow: normalize raw JD, research company, score fit/gap, generate analysis reports, and import to opportunity tracker. One-shot skill that orchestrates the full analysis and opportunity import.
Produces next-steps markdown for a single opportunity from opportunities.yaml using opportunity_report_next_steps_one template. Use when the user asks for one-opportunity next actions, 24–72h moves, or snapshot for a given id.
Builds sorted rollup of next actions across all active opportunities using opportunity_report_next_steps_rollup template. Use when user asks for combined backlog, rollup next steps, or sorted pipeline todos by date.
Builds the full opportunity pipeline markdown report from opportunities.yaml using opportunity_report_tracking template. Use when the user asks for tracking list report, pipeline snapshot, or opportunity-tracking markdown output.
Updates one opportunity in opportunities.yaml (stage, next actions, close outcome, history). Use when the user changes pipeline stage, notes, next_action, or closes an opportunity by id.
基于 SOC 职业分类
| name | opportunity-from-jd |
| description | Reads a raw JD and produces a YAML snippet for opportunities.yaml plus optional jd_catalog.csv row. Use when adding a new pipeline opportunity from data/raw, ingesting a JD file, or bootstrapping opportunity id and next_action fields. |
Role: Assistant — career / opportunity tracking (see docs/AGENT_ROLES.md).
Context to load:
data/<filename>.mdtemplates/opportunities_tracker_template.yamldata/master.yaml for fit notesconfig/jd_catalog.csv to register job_idScope:
Task:
"Unknown (SF-based startup)"). No label either: ask first.id: short slug, unique in data/opportunities.yaml (e.g. acme-senior-backend-2026).stage: usually Interested or Applied (user may override).jd_source: min raw_path: "data/raw/<FILENAME>". If user wants catalog tracking, output one CSV row for jd_catalog.csv with columns job_id,alias,role,raw_path,normalized_path,status (fill unknowns with placeholder or ask).next_action and next_action_date (concrete, within 7 days if possible), priority (P0/P1/P2), short notes.contacts[] — each: name, role (recruiter|hiring_manager|referral|hr|other), channels (free map: any platform key → handle/URL/number, e.g. linkedin, email, zalo, whatsapp, telegram, messenger, phone), notes. Omit key if no contacts known.links (application_portal, job_posting, or free key). Canonical spots for manual status checks. Omit key if no URLs known.updated_at to today (ISO date).active: in data/opportunities.yaml (or merge instructions if file exists). No duplicate id.Output sections:
active[] item onlyConstraints:
data/ is gitignored — full detail fine for YAML/chat drafts that stay local.Unknown, note in Assumptions, ask one clarifying question before locking id or company_display.My inputs (collect, confirm, or ask):
data/raw/, opportunities.yaml): ask before emitting final YAML.data/raw/: <...><Interested | Applied | ...><...><...><...>