القائمة
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.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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>".
| name | init |
| description | 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. |
The Spine (.spine/) is the shared memory every andreas-skill reads and writes.
This skill creates it.
.spine/ already exists, report what's
there and ask whether to refresh specific files rather than overwriting.package.json, pyproject.toml,
go.mod, Cargo.toml, etc.) and config to infer language, framework, test
runner, and the install/test/typecheck/build commands..spine/context.md.spine/conventions.md.spine/journal.md.spine/decisions/ (empty, with a .gitkeep)
Seed each from this skill's templates/, filling in detected values. Leave
<placeholders> only where you genuinely lack information, and flag them.align fire for every
non-trivial request in this repo — the gate ships with the Spine, not just
with the plugin. Two artifacts, both merged into what already exists (never
clobber):
.claude/settings.json — merge in the UserPromptSubmit hook from
templates/settings.gate.json. It self-gates
on .spine/ existing, so it stays silent in a checkout where the Spine was
removed. If the file already has a hooks.UserPromptSubmit array, append
this entry; don't duplicate it if an identical Spine-gate command is
already present.CLAUDE.md — append the block from
templates/claude-gate.md (create CLAUDE.md if
absent). It's wrapped in opening/closing spine:contracting-gate markers;
if the opening marker is already present anywhere in the file, the block is
installed — leave it, don't add a second copy.conventions.md commands and the
context.md architecture map; correct anything wrong before finishing.
Mention that the contracting gate is now active..spine/, .claude/settings.json, and CLAUDE.md so
the memory and the gate are shared with the team.npx spine-dashboard (read-only).context.md, conventions.md, journal.md, decisions/..spine/): .claude/settings.json (contracting-gate
hook), CLAUDE.md (contracting-gate instruction)..claude/settings.json and CLAUDE.md — they
routinely hold unrelated config the user cares about.