Covers the employment rules that carry real penalties — exempt and non-exempt classification, overtime and hours, employee versus contractor status, work authorization and recordkeeping, accommodation requests, and the notices and retention obligations that go with them. Use this to classify a role, review a contractor arrangement, respond to an accommodation request, work out what records to keep and for how long, or sanity-check a practice you inherited.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
This is the area where a well-intentioned decision made quickly costs the most later, because the mistakes are cheap to make, invisible for years, and expensive per-employee once found.
This structures the questions and the common failure patterns. Employment law varies by country, state and locality, changes often, and turns on specific facts — get a qualified employment adviser before acting on a classification, a termination, or a policy that applies to everyone.
Exempt versus non-exempt determines whether someone is owed overtime. It turns on what the person actually does day to day and on a salary threshold, not on being salaried, having a senior title, or preferring it that way. A misclassified role accrues unpaid overtime quietly and for everyone in it.
Employee versus contractor turns on control and independence — who decides how, when and where the work is done, who supplies the tools, whether the person serves other clients, and how integrated the work is with the business. A signed contractor agreement does not settle it. The common pattern that fails is a long-term contractor who works your hours, on your equipment, under your direction, on core work.
Reclassify when the facts change. A contractor who has become a de facto employee does not stay a contractor because nobody revisited it.
Non-exempt time has to be recorded, including work done outside scheduled hours. Answering messages after hours is time worked, and an organization that expects it while not recording it has created an unpaid-hours exposure with an audit trail in its own chat logs.
Rules on breaks, rest periods, split shifts, on-call time and travel time vary sharply by jurisdiction and are the ones most often missed by a policy written for headquarters and applied everywhere.
Verify work authorization consistently for everyone, on the same timeline, using the same process. Inconsistency is itself the problem: applying extra scrutiny to some candidates is a discrimination exposure independent of the underlying check.
Keep personnel records separate by type. Medical and accommodation information, immigration verification, and investigation files belong in separate confidential files rather than in the general personnel file — access to each is a different question.
When someone requests an accommodation — for disability, religion, or pregnancy in most regimes — what is owed is an interactive process: understand the limitation, discuss options, and either provide something workable or document why every option was an undue burden.
Most failures are procedural rather than substantive. The request was handled informally by a manager, no record was kept, and there is nothing to show that the process happened.
Required postings and notices, retention periods for payroll, hiring and leave records, and mandatory reporting all have specific durations and formats. None of them is interesting and all of them are checked first in a dispute, because they are the cheapest thing to check.
Set retention by the longest applicable requirement, and suspend disposal entirely when litigation or an investigation is reasonably anticipated.
references/sources.md in this skill lists the outside authorities that settle the questions
here — what each one is authoritative for, and what you may do with it. Check them before
answering on anything they cover, and cite what you used. Most are free to read and not free
to reproduce; the use note on each is binding.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Designs and audits who can reach what — authentication, authorization models, privileged access, service credentials, and joiner-mover-leaver process. Use this to design a permissions model, run an access review, reduce standing privilege, handle offboarding, set up SSO or MFA, manage service and machine credentials, or diagnose why permissions have sprawled.
日本語の概要は準備中です。原文の説明を表示しています。
Concentrates marketing and sales effort on a named set of accounts rather than on volume — qualifying whether the model fits your economics at all, building the account list and the buying group inside each, tiering effort against account value, coordinating so the account experiences one campaign rather than several, and measuring account progression instead of leads. Use this to decide whether to run an account-based program, build one, or work out why an existing one produces activity and no pipeline.
日本語の概要は準備中です。原文の説明を表示しています。
Gets new users from signup to first real value — signup flow, onboarding, time-to-value, and the early experience that determines whether someone becomes a user or a lapsed account. Use this to design or fix signup and onboarding, diagnose why signups do not convert to active use, reduce time-to-value, or decide what a new user must accomplish first.
日本語の概要は準備中です。原文の説明を表示しています。
Designs orchestrator-and-subagent hierarchies for a repository — splitting agents by exclusive write surface, pairing every producer with an independent auditor, and enforcing the split with a script that runs in CI. Use this whenever the user wants to set up, expand, audit, or fix a multi-agent or subagent structure for a codebase; asks how to divide work between agents; wants agent charters, roles, or a surface map written; or is hitting agents that collide on the same files, review their own work, or drift from their remit. Also use when sizing a roster or deciding whether a new agent is justified.
日本語の概要は準備中です。原文の説明を表示しています。
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory exposure, or when deciding whether an AI system is fit for a consequential decision.
日本語の概要は準備中です。原文の説明を表示しています。
Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or build-versus-buy decision, produce a research brief, or assemble evidence for a decision. Also use when comparing options that need a structured, evidence-based verdict rather than an opinion.
日本語の概要は準備中です。原文の説明を表示しています。