job-post-builder
Builds end-to-end hiring packets — job post, structured interview guide with scoring rubric, and offer letter template — from a hiring brief. Triggers on: "help me hire", "we're hiring for", "write a job post", "job description", "JD", "open role", "create a job ad", "interview questions", "scoring rubric", "draft an offer letter", "send an offer", "make a hiring packet", or any request to recruit for a position. When in doubt, trigger — covers the full hiring workflow from job post through DocuSign envelope creation via browser. Does NOT screen or rank applicants.
What this skill does
# Job Post Builder Produces a complete hiring packet — job post, interview guide, and offer letter — from a brief conversation about the role. Optionally routes the offer letter to DocuSign via Claude in Chrome. --- ## Quick start Invoke when a user says they need to hire someone or produce any hiring document. The skill walks a 6-phase workflow: gather context → research the market → write the job post → draft the interview guide → assemble the offer letter → (optionally) route to DocuSign. **Example trigger:** > "We're hiring a senior product manager. Can you put together the job post and > interview questions?" --- ## Workflow 1. **Gather role context** — Ask for role title, responsibilities, qualifications, location, comp, interview process, and offer delivery preference (Word doc vs. DocuSign). Source: conversation / AskUserQuestion. 2. **Research comparable posts** — Search Google Drive / Desktop for existing JDs and templates; run web search for 3–5 live postings for this role. Sources: file MCP, web search. 3. **Write the job post** — Draft a market-informed job description using `references/job-post-structure.md`. Output: `[Role]-Job-Post.docx` via docx skill. 4. **Draft interview guide + scoring rubric** — Build a stage-by-stage guide using `references/interview-guide-structure.md`. Output: `[Role]-Interview-Guide.docx` via docx skill. 5. **Assemble offer letter** — Build offer letter with bracketed placeholders using `references/offer-letter-template.md`. Output: `[Role]-Offer-Letter.docx` via docx skill. 6. **Route to DocuSign (if requested)** — Use Claude in Chrome to navigate DocuSign, upload the offer letter, configure the envelope, and save a draft. Requires explicit user approval before the envelope is sent. --- ## Approval gates This skill performs externally-visible actions in Phase 6. The following rules apply: - **Never send a DocuSign envelope without approval.** Save the envelope as a draft and return the URL. The user must review and confirm before Claude clicks Send. - **Never send the Gmail fallback email without approval.** If the DocuSign browser flow fails, draft the fallback email and show it to the user before sending. - **Never publish the job post.** Produce the .docx file only. Posting to any job board is the user's responsibility. Phase 6 will not advance past "Save as draft" without the user explicitly confirming they have reviewed the envelope and want it sent. --- ## Phase 1 — Understand the Role Before researching or writing anything, gather enough context to do it well. Ask the user (via conversation or AskUserQuestion) for: - **Role title** — exact title they want to post - **Team / function** — who this person reports to and works with - **Key responsibilities** — 3–5 things this person will own day-to-day - **Must-have qualifications** — hard requirements (years of experience, specific skills, credentials) - **Nice-to-have qualifications** — preferred but not required - **Location / remote policy** — on-site, hybrid, or fully remote; location if relevant - **Compensation range** — salary band if they have one (flag that this needs HR/legal sign-off) - **Existing JD or template?** — ask if there's a prior version in Google Drive or on their Desktop to use as a starting point - **Offer letter delivery preference** — ask how they'd like the offer letter delivered: - *Send directly via DocuSign* — skill opens DocuSign in Chrome, uploads the letter, sets up the envelope, and saves a draft for review before sending - *Just the Word doc* — skill saves the offer letter as a .docx and stops there; the user handles routing themselves - **Interview process** — ask how their hiring process is structured: - How many rounds/stages are there? - Who conducts each stage? (e.g. recruiter, hiring manager, peer, skip-level, panel) - What is each stage meant to assess? (e.g. culture fit, technical depth, cross-functional collaboration) - Is there a take-home exercise or work sample at any stage? This is critical — the interview guide will be organized by stage, and each stage gets its own question set. If the user doesn't know yet, suggest a sensible default based on the role level and company size, and confirm before proceeding. Example default for a mid-senior IC role: | Stage | Interviewer | Focus | |---|---|---| | Phone screen | Recruiter | Communication, baseline fit, logistics | | Hiring manager interview | HM | Scope, ownership, role-specific depth | | Peer interview | Team member | Collaboration, working style | | Skills/case exercise | Senior IC | Relevant technical or domain depth | | Final / culture interview | Skip-level or exec | Values, long-term trajectory | Capture the delivery preference in Phase 1 so the right Phase 5/6 path is clear before any writing starts. If the user already indicated a preference (e.g. "send it to DocuSign"), extract it from their message rather than asking again. If the user has already provided most of this in their message, extract it and confirm before moving on rather than asking redundant questions. One focused clarifying question is better than a long form. --- ## Phase 2 — Research Comparable Posts Good job posts are grounded in what the market actually says for this role. Do both of the following in parallel: **A. Check existing files first** Search Google Drive and Desktop for prior JDs, offer letter templates, or interview guides the user may already have. Use file search tools with terms like the role title, "job description", "JD", "offer letter", "interview". If found, read them and use them as the baseline — preserving any existing language, structure, or requirements the user has established. **B. Web search for comparable posts** Search for current job postings for this role at comparable companies. Good sources include LinkedIn, Greenhouse, Lever, Workday, and company career pages. Look for 3–5 real postings and note: - Common responsibilities listed for this role - Qualifications that appear consistently (these are table stakes) - How companies describe the role's impact/scope - Any language patterns that make postings feel compelling vs. generic Use this research to pressure-test the user's requirements (are they missing something standard? asking for something unusual?) and to make the job post feel current and market-aware. --- ## Phase 3 — Write the Job Post Read `references/job-post-structure.md` for the full recommended structure and writing guidance. **If an existing job post or JD was found in Phase 2:** Use it as the structural template — mirror its section names, tone, ordering, and any boilerplate the user has established (e.g. company description, benefits blurb, how-to-apply language). The user's format is the source of truth. Compare it against `references/job-post-structure.md` and surface any missing components in a single question before writing: > "Your existing JD has a responsibilities section and requirements list, but I > didn't see an opening hook or a description of what success looks like in year one. > Want me to add those, or keep it to your current format?" Only add the missing components if the user confirms. **If no existing job post was found:** Build from scratch using `references/job-post-structure.md` as the full template. **Either way:** - Lead with impact, not just tasks - Be honest about what's hard — candidates who self-select in are better fits - Use inclusive language; avoid jargon that implicitly filters for in-group candidates - Keep the required qualifications list tight — every line is a reason someone doesn't apply - If compensation isn't provided, omit the range rather than invent one Save as `[Role]-Job-Post.docx` using the docx skill. Read `docx/SKILL.md` before generating the file. --- ## Phase 4 — Draft Interview Questions + Scoring Rubric Read `references/interview-guide-structure.md` for the full recomme
Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".