agentleFS
galiprandigaliprandi/job-seeker/.agents/skills/onboarding/SKILL.md

onboarding

Skill136 starsChanged 3 days agoMITView on GitHub

Initial environment setup. Browser, logins, DB, user data, profile, strategy.

  • Reads credentials
  • Installs packages

106 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use paywalls, popups and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CesarjoquinSkill

    paywalls

    When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," "in-app pricing," "free users won't upgrade," "trial to paid conversion," or "how do I get users to pay." Use this for any in-product moment where you're asking users to upgrade. Distinct from public pricing pages (see cro) — this focuses on in-product upgrade moments where the user has already experienced value. For pricing decisions, see pricing.

    Also in 20 projects that use this

  • CesarjoquinSkill

    popups

    When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," "overlay," "collect emails with a popup," "exit popup," "scroll trigger," "sticky bar," or "notification bar." Use this for any overlay or interrupt-style conversion element. For forms outside of popups, see cro. For general page conversion optimization, see cro.

    Also in 19 projects that use this

  • coreyhaines31Skill

    marketing-council

    When the user wants several expert takes on a marketing decision, or asks what a famous marketer would say about it: a simulated board (Seth Godin, David Ogilvy, April Dunford, Byron Sharp, and more), each grounded in their documented frameworks, where they disagree, and a recommendation. To execute, hand off to the relevant skill.

    Also in 13 projects that use this

  • roerohanSkill

    prospecting

    When the user wants to find, qualify, and build a list of prospects to reach out to — across B2B SaaS, general B2B, or local small businesses. Also use when the user mentions "prospecting," "build a prospect list," "find prospects," "find leads," "lead gen list," "find SaaS companies that," "find B2B companies," "find local businesses," "ICP-fit accounts," "who should we go after," "outbound list," "target account list," "find clients near me," "businesses without websites," "prospect research," "qualified leads," "find my first customers," "early adopters," "design partners," "beta users," or "who has this problem." Use this for the list-building and qualification phase. For writing the outbound copy after the list is built, see cold-email. For deep competitive research on specific accounts, see competitor-profiling.

    Also in 17 projects that use this

  • martinbattaglia-commitsSkill

    marketing-loops

    When the user wants to set up a recurring, self-running marketing workflow — a repeatable loop an AI agent runs on a cadence (weekly, daily, on a trigger) rather than a one-off task. Also use when the user mentions 'marketing loop,' 'recurring marketing workflow,' 'automate my marketing,' 'marketing on autopilot,' 'weekly marketing review,' 'ad fatigue check,' 'content refresh loop,' 'churn watch,' 'ranking drop alert,' 'always-on marketing,' 'marketing automation workflow,' or 'run this every week.' Use this to pick, adapt, and schedule an ongoing marketing loop that orchestrates the other marketing skills. For one-off marketing ideas, see marketing-ideas. For the experimentation loop specifically, see ab-testing.

    Also in 10 projects that use this

  • roerohanSkill

    emails

    When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," "lifecycle emails," "trigger-based emails," "email funnel," "email workflow," "what emails should I send," "welcome series," or "email cadence." Use this for any multi-email automated flow. For cold outreach emails, see cold-email. For in-app onboarding, see onboarding.

    Also in 19 projects that use this

  • +5 more from Cesarjoquin

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 6 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 90 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Verify node and npx

    line 12
  2. Very specific:

    If no preference exists, default to headed_logins_only.

    line 29
  3. Very specific:

    Ask for email. Navigate to provider login (Gmail → accounts.google.com, Outlook → outlook.live.com).

    line 34
  4. Distinctive:

    Option B: Bring your own connection string: If the user already has a Postgres DB (Neon, Supabase, Railway, local, etc.), they paste the …

    line 41
  5. Distinctive:

    Ask for user's name

    line 46
  6. Very specific:

    Create users table and insert record via the db CLI (scripts/db.js):

    line 47
  7. Distinctive:

    Check if profiles need updating (inconsistent data across sites).

    line 62
  8. Distinctive:

    If junior/mid: "Are you open to roles above your current level, or only same-level matches?"

    line 74
  9. Distinctive:

    If senior+ with management: "Would you accept IC roles or only Manager?"

    line 75
  10. Very specific:

    If no strategy is set, default to selective.

    line 85
  11. Distinctive:

    Polish is suggested at the end of onboarding: After strategy is defined, the agent proactively suggests aligning the CV and LinkedIn …

    line 109

“Common” is measured: kept by at least 6 in 10 of the 90 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Onboarding

Steps

Phase 1: Technical setup

  1. Verify node and npx
  2. .gitignore: .browser-profile/, .env, node_modules/
  3. npm init -y && npm install pg && npm install --save-dev @types/pg
  4. Ask user about browser visibility preference. Present these options and save the answer to preferences before opening any browser:

    • headless — Headless always. The agent works without showing the browser. Manual login/2FA remains headed (Gold Rule 5)
    • headed — Headed always. The user sees everything the agent does on screen
    • headed_logins_only — Headed only for logins/2FA, headless for everything else (default)
    • ask_each_time — The agent asks before each browser session whether the user wants to see it or not

    Save the preference:

    node scripts/db.js "INSERT INTO preferences (user_id, category, key, value, confidence, source) VALUES (<user_id>, 'tooling', 'browser_mode', '<chosen_value>', 1.0, 'explicit_statement') ON CONFLICT (user_id, category, key) DO UPDATE SET value = EXCLUDED.value, updated_at = NOW()" --write

    The agent must respect this preference in all flows that use the browser. Load it at every pre-flight:

    node scripts/db.js "SELECT value FROM preferences WHERE user_id = <user_id> AND category = 'tooling' AND key = 'browser_mode' AND status = 'active'"

    If no preference exists, default to headed_logins_only.

Phase 2: Browser and logins

  1. Open browser respecting the preference from step 4. For manual login it's always headed (Gold Rule 5). Use the wrapper (see AGENTS.md "Browser session"): node .agents/skills/browser-automation/scripts/browser.js open <url> --headed
  2. Ask for email. Navigate to provider login (Gmail → accounts.google.com, Outlook → outlook.live.com). Fill email with fill, click Next, wait for manual auth + 2FA
  3. Validate session: navigate to inbox, confirm URL doesn't redirect to login

Phase 3: Database setup

  1. Database setup. Neon is the default recommended option. Present the options in this order:

    • Option A (recommended): Create a free DB on Neon. The agent navigates to console.neon.tech, logs in with Google (reuses session), creates a "New project", names it job-seeker, selects nearest region, and reads the connection string (Show password + eval to extract)
    • Option B: Bring your own connection string. If the user already has a Postgres DB (Neon, Supabase, Railway, local, etc.), they paste the connection string directly

    Neon is presented as the default because it's free, serverless, and requires zero local setup. The agent should not wait for the user to ask about Neon, it should offer it proactively.

  2. Save connection string to .env as DATABASE_URL
  3. Ask for user's name
  4. Create users table and insert record via the db CLI (scripts/db.js):
    node scripts/db.js "CREATE TABLE IF NOT EXISTS users (id SERIAL PRIMARY KEY, name TEXT NOT NULL, email TEXT NOT NULL UNIQUE, data JSONB DEFAULT '{}')" --write
    node scripts/db.js "INSERT INTO users (name, email, data) VALUES ('<name>', '<email>', '{}'::jsonb) ON CONFLICT (email) DO UPDATE SET name = EXCLUDED.name" --write

Phase 4: LinkedIn

  1. Navigate to linkedin.com/login. Wait for manual auth + 2FA
  2. Validate session: navigate to linkedin.com/feed/
  3. Save LinkedIn profile URL to users.data.linkedin_profile via db CLI:
    node scripts/db.js "UPDATE users SET data = jsonb_set(data, '{linkedin_profile}', '\"<url>\"') WHERE id = <user_id>" --write
  4. Collect user info from all logged-in sites (LinkedIn, Gmail/Google): name, photo, phone, email. Save to users.data as JSONB via db CLI (jsonb_set). Useful for aligning profiles on other job platforms
  5. Check if profiles need updating (inconsistent data across sites). Report to user
  6. Close browser

Phase 5: Profile (CV-first)

  1. Ask for CV (URL or PDF). This is the first step of the profile flow (see profile skill, Step 1). The agent extracts experience, sector, profile, and infers career stage from the CV.
  2. Run the gap questionnaire (profile skill, Step 2). The agent generates only the questions the CV doesn't answer, adapted to the inferred career stage. Management questions only if applicable. No hardcoded deal-breakers.
  3. Ask about current situation and expectations (profile skill, Step 3). Employment status, urgency, salary, work mode, availability for interviews.

Phase 6: Strategy

  1. Define strategy (see strategy skill). Now that the agent has the full profile (CV + gaps + situation), it proposes a strategy level informed by everything above. Questions are adapted to the user's career stage:

    • If junior/mid: "Are you open to roles above your current level, or only same-level matches?"
    • If senior+ with management: "Would you accept IC roles or only Manager?"

    Save to DB:

    # Save level to preferences
    node scripts/db.js "INSERT INTO preferences (user_id, category, key, value, confidence, source) VALUES (<user_id>, 'workflow', 'strategy_level', '<level>', 1.0, 'explicit_statement') ON CONFLICT (user_id, category, key) DO UPDATE SET value = EXCLUDED.value, updated_at = NOW()" --write
    # Save detailed parameters to users.data.strategy
    node scripts/db.js "UPDATE users SET data = jsonb_set(data, '{strategy}', '<json>'::jsonb) WHERE id = <user_id>" --write

    The strategy JSON should contain all parameters (see AGENTS.md "Strategy levels" for the schema per level). If the user customizes any parameter, override the default for that level. If no strategy is set, default to selective.

Phase 7: Polish suggestion

  1. Suggest aligning CV and LinkedIn profile to the job target. After the strategy is defined, the agent compares the user's current CV and LinkedIn profile against the defined job target and identifies gaps (missing keywords, misaligned titles, underrepresented skills, weak LinkedIn headline). Present the analysis and offer to run the polish skill. If the user accepts, run polish. If not, remind them once at the end of onboarding.

Phase 8: Wrap up

  1. Voice and style capture (profile skill, voice phase). Infer tone and style from LinkedIn sent messages and Gmail sent emails. Confirm with user. Save to users.data.style_profile.
  2. Platform assignment (profile skill, platforms phase). Cross-reference profile vs PLATFORMS.md, assign tiers, save to users.data.platforms. Don't ask the user.
  3. Summary. Present a summary of everything that was set up: browser mode, DB, profile, strategy, polish status, platforms. One line per item.

Rules

  • Full autonomy. Only ask for intervention to: data that can't be inferred, manual login, 2FA
  • Email login first, LinkedIn second
  • Validate session after each login
  • .env not tracked
  • Custom schema: only create tables when needed
  • JSONB for semi-structured data in users.data
  • Single user (repo owner)
  • Browser mode preference is set in step 4 and stored in preferences table. All subsequent flows must load and respect it. Manual login/2FA is always headed regardless of preference (Gold Rule 5)
  • CV is requested before strategy. The profile (CV analysis + gap questionnaire + situation) informs the strategy questions. Never ask strategy questions before having the CV
  • Neon is the default DB option. Present it proactively as the recommended choice. Don't wait for the user to ask
  • Polish is suggested at the end of onboarding. After strategy is defined, the agent proactively suggests aligning the CV and LinkedIn profile to the job target. Never skip this step
  • Questions adapt to career stage. The agent infers career stage from the CV and adapts strategy questions accordingly. Never ask "IC or Manager?" to a junior

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.