Buys well — specifying need, running competitive sourcing, negotiating, and category strategy before a contract exists. Use this to run an RFP or vendor selection, negotiate a purchase, consolidate spend across a category, decide between single and multiple suppliers, or bring uncontrolled spending under management.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
This is everything before signature: deciding what to buy, from whom, and on what terms.
operations:vendor-management takes over afterward — performance, renewals, exit.
Most bad purchases are decided before any supplier is contacted, when a requirement is written as a product someone already wanted. Specify the outcome and the constraints; let suppliers propose how.
Separate genuine requirements from preferences, and be honest about which is which. A requirements list that only one supplier satisfies is a purchase order with extra steps, and everyone involved knows it.
Involve the people who will live with the choice. Procurement that optimizes price against a specification the users did not agree to produces a cheap thing nobody uses.
Price is set by the credible presence of an alternative, not by negotiating skill. The single most effective act in sourcing is having a real second option — and being willing to take it.
Run a fair process: same information to every bidder, same questions answered for all, scoring agreed before responses arrive. Scoring invented afterward reliably rediscovers the preferred supplier.
Where genuine competition is impossible — an incumbent with switching costs, a sole source — acknowledge it rather than staging a process. Then negotiate on the things still open: term length, renewal caps, service levels, exit assistance.
The quoted figure is a fraction of what you will spend. Model implementation, integration, training, the internal effort to run it, and what leaving costs.
Watch for cost that arrives later by design: per-seat pricing that grows with headcount, usage pricing with no cap, renewal uplifts, and support tiers that turn out to be mandatory. Ask what this costs in year three, and get the answer in the contract.
Aggregate spend before negotiating it. The same category bought independently by four teams is four weak negotiating positions and usually four overlapping tools.
Segment by leverage: high-spend commodity categories reward consolidation and hard negotiation;
low-spend specialist ones are not worth the process cost. Concentrating everything on one supplier
buys a discount and sells an exit — see operations:business-continuity-and-resilience before
deciding that trade.
Route the resulting terms through legal-risk:contract-review, and anything touching customer data
through legal-risk:privacy-and-data-protection before signature rather than after.
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.
Procure-to-pay: Coupa, SAP Ariba, Zip, Precoro, and similar. At smaller scale a request form plus the accounting system's purchase orders does the same work.
Spend visibility: Ramp, Brex, Vertice, and similar, read against the ledger.
Vendor risk lives in the GRC tooling, not here — but the intake form is where the security and privacy review has to be triggered, or it never happens.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.