spine

Use when verified work is ready to land — turns it into a clean branch, commits, and a pull request whose body is drawn from the Spine (criteria, decisions, evidence). Refuses to ship work that hasn't passed verify. Reads the Spine; writes the shipped status back to it.

Use right after a VC meeting to turn raw memory into a structured debrief — a signal read (interest vs. hesitation vs. pushback), the open diligence queue with draft answers, a send-ready follow-up email, and a clear recommended next step. Run within 24 hours; the follow-up email degrades fast. Use when asked to "debrief the meeting", "how did the pitch go", "write the follow-up email", or "what do I do after the meeting with <fund>".

Use to see the whole raise at a glance and to produce an investor-ready dossier — scans the .spine/raise/ namespace, builds a pipeline status tracker (every fund's scores, stage, and next action), and assembles a consolidated dossier suitable for sharing with an investor or advisor. Use when asked to "show the pipeline", "raise status", "track the funds", "what's stale", or "generate the investor report".

Use to analyse a VC term sheet — benchmarks every clause against current market norms, flags founder-unfriendly terms, scores founder-friendliness out of 100, and produces a ranked negotiation priority list with suggested pushback language. Informational only, not legal advice. Use when asked to "analyse this term sheet", "review the term sheet", "is this term sheet fair", or "what should I negotiate".

Use to turn a fund dossier into ready-to-send outreach — a cold email, a warm-intro request your contact can forward, and a LinkedIn DM, each built on the fund's own thesis language, plus a fund-specific one-pager. Refuses to draft for a no-go fund. Drafts only — it never sends. Use when asked to "draft outreach for <fund>", "write the intro email", "cold email this VC", or "make a one-pager for <fund>".

Use to prepare for pitching — full-spectrum prep in one skill. With no fund, it runs the stress-test: ten lethal questions a hostile VC would ask (know what to defend) and ten strongest signals a champion would champion (know what to lead with). With a fund, it builds a timed meeting plan with segment scripts, preemptive answers to that fund's diligence questions, and red-flag rebuttals. Use when asked to "prep me to pitch", "stress-test my pitch", "destroy my startup", "what are my strongest signals", or "prep for the meeting with <fund>".

Use to research the VC landscape and build a ranked pipeline of funds to target — produces 15–20 funds in three tiers (pursue now, warm up first, monitor) with a fit rationale and a contact angle for each. Run before vetting and matching individual funds. Use when asked to "build a target list", "which VCs should we approach", "find funds for us", or "research the VC landscape".

Use before pitching anyone to find out whether you're actually fundable yet — pressure-tests the idea (real demand, sharp ICP, narrow wedge) and scores fund-readiness, naming exactly what's missing and what to fix first. The honest "should we even raise" gut-check. Use when asked "are we ready to raise", "are we fundable", "is this worth funding", or "what's missing before we pitch".

Use to synthesise everything known about the startup and its fund pipeline into a full fundraising strategy memo — raise parameters, sequencing, a milestone map, a month-by-month timeline, risks, and this week's next actions. Run after the profile, readiness, pipeline, and any fund dossiers exist. Use when asked to "build a fundraising strategy", "how should we run this raise", "what's our raise plan", or "sequencing strategy".

Use to deeply analyse whether a specific VC fund fits your startup — spawns four parallel research sub-agents (thesis, portfolio, people, deal), scores the fit across eight dimensions out of 100, and writes a complete fund dossier with the warm-intro path, perks, and a pursue/warm-up/no-go verdict. Run after raise-vet clears the fund. Use when asked to "analyse this fund", "does this VC fit us", "research a fund", or "should we pitch this investor".

Use to vet a VC fund's legitimacy before spending real research on it — a cheap background check that answers "is this fund actually real and active, or a zombie?" Runs eight evidence-based checks and writes a stub fund dossier with a legitimacy score. Run before raise-match. Use when asked to "vet a fund", "check if a VC is legit", "is this fund still active", or "screen this investor".

Use to bootstrap the fundraising track in a repo — creates the .spine/raise/ namespace and seeds profile.md (the startup profile) through a short interview. Run once before any other raise-* skill. Use when a project decides it needs funding, or when asked to "set up fundraising", "start a raise", or "create the startup profile".

Use to bootstrap the .spine/ project-memory store in a repo before using the other skills. Detects the stack and seeds context.md, conventions.md, and journal.md. Run once per repo.

Use before building any feature or change to interrogate intent until both you and the user are certain the context is right. Runs an extensive, multi-dimensional interview, then gates on an explicit confidence score and a context playback the user must confirm. Prevents building the wrong thing. Proactively invoke this (do NOT start building) whenever the user requests a non-trivial feature, change, or fix. Writes the agreed intent and criteria to .spine/journal.md.

Use after align and before build to turn acceptance criteria into a concrete architecture — module boundaries, interfaces, data flow — recorded as ADRs and an architecture map in the Spine. Greenfield-first; also designs features within an existing codebase. Use when starting a new project, making upfront architectural decisions, or designing a non-trivial feature.

Use at the end of a work session to distill what happened back into the .spine/ store so the next session starts informed instead of cold. Updates context and conventions, records decisions as ADRs, and compacts the journal.

Use when adding a new skill to the spine repo — scaffolds a conventions-compliant SKILL.md, wires it into plugin.json, the README, and the skill index, and runs the validator until green. Meta-tooling that dogfoods spine's own contribution rules so extensions land correctly the first time.

Use when something is broken — a failing test, a bug, an error, behavior that regressed. Drives a disciplined investigate → reproduce → root-cause → fix loop, checks the Spine for prior art, and records the root cause so the failure mode isn't repeated. Iron law — no fix without a confirmed root cause.

Use when work is supposedly complete, before claiming it is done or merging. Checks the change against the acceptance criteria by running tests, typecheck, and review — and reports evidence, never bare assertions. Reads criteria from the Spine.

Use to implement a feature or bugfix as small TDD vertical slices that follow the repo's conventions. Produces working, tested code one slice at a time. Reads acceptance criteria and conventions from the Spine.