aesthetic-instrument
great_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two faces divided by MEANING (Geist speaks,…
Domain-knowledge primer for the HR & recruiting vertical (ATS, onboarding, workforce scheduling, engagement). Applied by architect/pm during spec authoring so they aren't naive about hiring pipelines, the admitted offer→onboard data-carry gap, EEO/I-9 compliance, and
$ npx -y skills add avelikiy/great_cto --skill vertical-hr-recruiting --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/vertical-hr-recruitingContext preview
The summary Claude sees to decide when to auto-load this skill.
Domain-knowledge primer for the HR & recruiting vertical (ATS, onboarding, workforce scheduling, engagement). Applied by architect/pm during spec authoring so they aren't naive about hiring pipelines, the admitted offer→onboard data-carry gap, EEO/I-9 compliance, and
name: vertical-hr-recruiting description: Domain-knowledge primer for the HR & recruiting vertical (ATS, onboarding, workforce scheduling, engagement). Applied by architect/pm during spec authoring so they aren't naive about hiring pipelines, the admitted offer→onboard data-carry gap, EEO/I-9 compliance, and shift-coverage rules. Stops the four products from being specced as generic CRUD when the domain has hard legal and workflow constraints. when_to_use: | Apply when: - architect writes ARCH-*.md for ats / onboarding / workforce-scheduling / engagement - pm decomposes any of these four products into tasks and needs domain entities - a spec touches candidates, requisitions, offers, I-9, shifts, or EEO data Do NOT apply for products outside the HR/recruiting vertical. effort: low allowed-tools: Read, Write, Grep, Glob paths: - "docs/architecture/**" - "docs/plans/**" - "docs/design/**"
The incumbents (Workable, BambooHR, Greenhouse, Lever, Zoho Recruit, Manatal) have trained buyers to expect a hiring pipeline that *works*. A generic CRUD app fails the moment it meets EEO law, I-9 timing, or the offer→onboard handoff. **Read this before speccing any of the four products — the domain has hard constraints, not just forms.**
vacuum. Reqs have an approval workflow (hiring manager → finance/HR).
`withdrawn`). Stages are **configurable per req** — engineering and sales hire differently.
person in your talent pool who may map to many applications over time. Don't conflate them.
scores. Reduces bias and legal exposure vs freeform notes.
reporting, **segregated from hiring decisions** (see §2).
candidate; fill = req closed). Different denominators; report both correctly.
go unstaffed below a threshold.
is unsolved: data gets *re-entered* between the ATS and the HR/onboarding system. The whole onboarding product wedge is **carry the candidate's data forward — zero re-entry.**
self-identified race/gender into the screen/interview UI is an anti-discrimination liability. Store it segregated; surface it only in aggregate compliance reports.
consistent record. Freeform-only interview notes are a disparate-impact landmine.
review of documents) **within 3 business days of start.** Onboarding tasks tied to I-9 carry a hard deadline, not a soft reminder.
just because slots are filled — it must respect minimum coverage, overtime (FLSA), predictive-scheduling / fair-workweek laws (advance-notice in some jurisdictions), and break rules.
with a budget/headcount check, not a checkbox.
customer wants a take-home or panel stage. Stages must be **configurable per req.**
the hiring manager sees is a legal-risk bug, not a UX choice. Segregate it.
scratch *is* the gap incumbents have. If onboarding starts from a blank form, you built the incumbent's weakness, not our wedge.
Section 1 / Section 2 split, it's non-compliant.
flag, and no swap-approval flow is a toy, not a workforce tool.
| Entity | Must include | Why | |---|---|---| | **Requisition** | approval state, headcount, stage config | hiring is per-req; stages vary | | **Candidate** | stage history, scorecards, EEO (segregated store) | audit trail + bias defense; EEO must not leak into decision view | | **Offer → Onboarding** | carries candidate data forward (no re-entry) | this IS the wedge; the handoff is the gap | | **OnboardingTask** | deadline field (I-9 3-day timing) | compliance is time-bound, not soft | | **Shift** | coverage rules, overtime flag, swap/approval state | a schedule must be *valid*, not just full |
| product | archetype | wedge | the one domain thin
You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.
Repo: avelikiy/great_cto
great_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two faces divided by MEANING (Geist speaks,…
Catalogue of known SDLC anti-patterns that great_cto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect…
Analyze images, websites, and Figma files to extract their design and generate a `design.md` with token system, component inventory, and reconstruction notes.…
Shared review framework that every domain reviewer (pci, oracle, gov, edtech, healthcare, mlops, etc.) MUST follow. Defines the output artifact (TM-{slug}.md),…
Structured idea generation + multi-LLM debate for the product-owner stage. Diverge (generate genuinely different bets), debate (a 4-persona panel on 4 models…
Run the great_cto controlled Codex lifecycle with controller-owned writes, verifier evidence, human gates and optional artifact release.