浏览器与自动化
Management and autonomy (only if
profile
Captures and structures the user's profile from CV + questionnaire to make decisions on their behalf. Ensures quality matching.
galiprandi · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add galiprandi/job-seeker --skill profile技能说明
name: profile description: Captures and structures the user's profile from CV + questionnaire to make decisions on their behalf. Ensures quality matching. trigger: profile
Profile
Pre-flight
- Load active preferences (see
memoryskill):node scripts/db.js "SELECT category, key, value, confidence, source FROM preferences WHERE user_id = <user_id> AND status = 'active' ORDER BY category, key" - Load existing profile if present:
node scripts/db.js "SELECT data->'profile' AS profile, data->'job_preferences' AS job_preferences, data->'style_profile' AS style_profile FROM users WHERE id = <user_id>" - If profile exists, validate changes before overwriting
Flow overview
Step 1: CV analysis → extract experience, sector, profile, inferred seniority
Step 2: Gap questionnaire → only what the CV doesn't clarify (adaptive to inferred profile)
Step 3: Current situation + expectations → employment status, urgency, salary, work mode, availability
Step 4: Strategy → targets, sources, aggressiveness (informed by everything above)
Step 5: Polish suggestion → align CV and LinkedIn profile to the job target to maximize matches
Step 1: CV analysis
Ask user for CV (URL or PDF). Extract:
- Full name and title/profession
- Professional summary (elevator pitch)
- Work experience (company, role, period, achievements, team size, reporting line if applicable)
- Core competencies and tools (tech stack, software, methodologies, equipment, whatever is relevant to the field)
- Soft skills (leadership, communication, etc.)
- Certifications and courses
- Education (degrees, institutions)
- Languages and proficiency level
- Quantifiable achievements (metrics, impact)
- Notable projects or relevant work samples
Step 1b: Inferred profile
From the CV data, infer:
| Signal from CV | Inferred field | Used for |
|---|---|---|
| Years of experience, previous roles | career_stage (intern, junior, mid, senior, staff, principal, director+) | Which questionnaire blocks to show, seniority filtering |
| Team size managed, titles with Lead/Manager/Head | has_management (bool) | Whether to show management-related questions |
| Core competencies and tools | core_skills | Step 2 gap questions on skill preferences |
| Industries of previous employers | industry_history | Step 2 gap questions on industry preferences |
| Company sizes (startup vs corporate) | company_size_history | Step 2 gap questions on company size |
| Sector or functional area | sector | Step 2 gap questions, platform tiering |
| Languages and publications/conferences | visibility_level | Outreach tone, referral strategy |
Save to users.data.profile as JSONB, including the inferred fields:
node scripts/db.js "UPDATE users SET data = jsonb_set(data, '{profile}', '<json>'::jsonb) WHERE id = <user_id>" --write
The inferred profile is preliminary. Step 2 confirms or corrects it.
Step 2: Gap questionnaire
Not a fixed set of blocks. The agent generates questions based on what the CV already answered clearly. Only ask about gaps.
Each answer must have a weight: Must (non-negotiable), Strong (strong preference), Nice (would be a plus).
Core questions (always ask if the CV doesn't clarify)
Role and career direction
- Role type (IC, manager, mixed, specialist, leadership) — adapt options to
career_stageandhas_management - Career stage confirmation (the agent proposes the inferred value, user confirms or corrects)
- Growth direction (stay in current path, wants to pivot, wants to move to leadership, unsure)
- Mentorship expectations (wants mentorship, wants autonomy, indifferent) — only if
career_stageis junior/mid
Management and autonomy (only if has_management = true or user expressed leadership aspirations)
- Expected reporting line (CEO, CTO/COO, VP, other director) — adapt to sector
- Expected hiring/firing authority
- Budget authority (own budget decisions)
- Org scope (single team, multiple squads, department, company-wide)
Work mode and geography
- Work mode (remote, hybrid, on-site)
- Current location and willingness to relocate
- Accepted timezones (Americas, Europe, Asia, global)
- Contract type (employee, contractor, freelancer)
Company type and sector
- Company size (startup, scale-up, mid-size, corporate)
- Company stage (early-stage, growth, established, public) — only if relevant to the sector
- Preferred sectors or industries (if
industry_historyshows concentration, confirm rather than ask open-ended) - Sectors to avoid (with nuance: absolute or accepts partial exposure?)
- Product/service type (own product, internal platform, consulting, services) — adapt to field
Sector-specific focus
- Area of specialization within the field (the agent proposes based on CV, user confirms or refines)
- Tools/methodologies the user wants to keep using vs open to learn
- Type of impact desired in first 6 months (adapt to role type)
Deal-breakers
- Graduated deal-breakers (the agent presents an empty list, the user adds their own). Never pre-load deal-breakers like "junior" or any role level. Each user defines their own.
How the agent decides what to ask
- For each topic above, check if the CV already provides a clear answer
- If clear → skip the question, save the inferred value with confidence note
- If unclear or missing → ask the question
- If the topic only applies to certain career stages (management questions) → skip if not applicable
- Present questions in blocks of 4, multi-select where applicable
Save to users.data.job_preferences as JSONB with weights:
node scripts/db.js "UPDATE users SET data = jsonb_set(data, '{job_preferences}', '<json>'::jsonb) WHERE id = <user_id>" --write
Step 3: Current situation and expectations
Ask th
阅读完整来源 ↗