メニュー
Apply and enforce the systemprompt.io brand voice, style guide, and messaging pillars across all content. Always load identity first. Use when reviewing content for brand consistency, drafting content, or checking terminology compliance.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Maintains the living marketing strategy doc at /var/www/html/systemprompt-web/reports/marketing/marketing-strategy-master.md. Never rewrites wholesale — writes diffs. Contains objectives, 30/60/90 targets, channel hypotheses in flight, dead hypotheses, winning tactics, and funnel snapshots. Load marketing-identity first.
Deterministically audit and optimise a published documentation page. Runs a 10-section quality audit, applies 5 rewrite rules for structure, terminology, link health, and completeness. Reads website analytics and GSC data per doc URL, produces a 75-point score delta (100 with analytics), commits changes, and updates the per-doc report. Load identity and brand-voice first.
Deterministically audit and optimise a published feature page on the register ladder: struggling-moment heroes with zero implementation jargon, mechanism evidence relocated to section bodies and dropdowns in the HashiCorp / Stripe / Tailscale register. Runs an 11-section quality audit plus register-ladder checks (hero jargon count, homepage narrative echo, struggling-moment opener, identifier-enumeration, established-not-indie voice) and applies 6 rewrite rules: claim verification, conversion clarity, brand discipline, and Technical-Marketing Synthesis (ten sub-checks: outcome headlines, jargon payoff scoped to sections/dropdowns, numbers with context, feature-to-outcome binding, narrative-vs-reference separation, skeptic test, named surfaces over coined metaphors, dropdown alignment, no Rust internals in narrative, dense sentences no filler). Penalises metaphor-stacking and marketing adjectives. Reads website analytics and GSC data per feature URL, produces a 90-point score delta (115 with analytics), commit
Deterministically audit and optimise a published guide. Runs a 14-section quality audit, applies 7 rewrite rules for value density, brand discipline, search-intent alignment, and CTR. Reads 28-day GSC query data per URL, produces a 100-point score delta across 11 dimensions, commits changes, and updates the per-guide report. Handles guides without GSC data. Load identity and brand-voice first.
Daily CRM and funnel measurement. Pulls GitHub Traffic API for systemprompt-core and systemprompt-template (14d retention, MUST run daily), website analytics via systemprompt CLI, and external feedback signals. Emits 1d/7d/31d funnel deltas and a dated report. Source of truth for every hypothesis metric.
Daily SEO briefing. Analyses content traffic, engagement, and search performance across published guides using internal analytics and Google Search Console. Generates actionable reports with S-### hypotheses. Designed for daily /loop. Load identity first.
| name | brand-voice |
| description | Apply and enforce the systemprompt.io brand voice, style guide, and messaging pillars across all content. Always load identity first. Use when reviewing content for brand consistency, drafting content, or checking terminology compliance. |
| metadata | {"version":"3.0.0","git_hash":"a5b0f4d"} |
Source of truth for tone, style, and language across all systemprompt.io content. Always load the systemprompt Identity skill first for product definition, ICP, and strategic positioning.
Load identity before this skill. This skill governs how we sound. The identity skill governs what we say and to whom.
systemprompt's voice belongs to Edward: a technical founder who has been building in the AI infrastructure space and speaks from direct experience. Not a company broadcasting. Not a marketing team. A person who understands the governance problem because he has watched organizations struggle with it firsthand.
The voice carries authority on AI governance without being academic. It is the CTO's peer, not their vendor.
Speaking to CISOs and security leaders (enterprise security, ICP 1): Defence-in-depth framing. Compliance and audit language. Reference SIEM, SOC, RBAC naturally. The tone is a security engineer presenting a control to the CISO, not a vendor pitching a product. Technical precision matters more than narrative. Lead with what is provable, not what is promised. No marketing superlatives.
Speaking to CTOs and engineering leaders (mid-market, ICP 2): Peer-to-peer. Technical confidence. Focus on governance, observability, standards, and the build-vs-buy calculus. No hand-holding. Enablement and productivity framing, grounded in specific capabilities (skill marketplace, usage dashboard, cost attribution).
Speaking to SaaS partners (white-label, ICP 3): Business opportunity framing. Focus on what their customers are asking for, the cost of building it themselves, and the speed of deployment. Revenue and competitive advantage language.
Speaking to individual users (ICP 4): Warmer, more accessible. Focus on ownership, portability, and getting started. But still authoritative, never cute or casual.
Never invent statistics, quotes, anecdotes, customer stories, personal narratives, or specific examples. This includes made-up "I built...", "I learned...", or "When I was..." stories. Never fabricate analogies presented as real experiences.
Use generic, clearly hypothetical examples ("A 200-person SaaS company rolling out Claude...") or placeholders:
[INSERT: specific example from Edward][INSERT: customer quote or observation][INSERT: specific metric or data point]On any platform. In any context. Ever.
Use commas, periods, parentheses, or restructure the sentence instead.
Banned: revolutionize, game-changer, unlock, supercharge, seamlessly, harness the power of, the future of, next-generation, cutting-edge, paradigm shift, disrupt, empower, leverage (as verb), transform (without specifics), reimagine.
Every piece of content should reinforce systemprompt.io's position as the only AI infrastructure you actually own. Not memory. Not persistence. Not plugin management. Ownership first, then what owning it gives you: control, observability, enforcement, standards.
Use these phrases when they are accurate. They are tested, specific, and grounded in the actual product. Vary them. If the same phrase appears more than once in a single piece of content, find an alternative.
Enterprise security context (ICP 1):
Mid-market enablement context (ICP 2):
Cross-ICP (always appropriate):
Same binary. Same features. Different story. Use this table to calibrate framing before drafting.
| ICP | Lead with | Proof points | Emotional register |
|---|---|---|---|
| 1: Enterprise Security | Defence, compliance, audit | SIEM integration, 35+ secret patterns, air-gap, RBAC, 16 event hooks | Rigorous, measured, precise |
| 2: Mid-Market | Enablement, productivity, cost | Usage dashboard, shared skills, cost attribution, role-based distribution | Practical, peer-to-peer, direct |
| 3: SaaS White-Label | Revenue, competitive advantage | White-label deployment, branded gateway, source-available | Business opportunity, strategic |
| 4: Individual Users | Ownership, portability | Free tier, no lock-in, your data, your skills | Warmer, accessible, still authoritative |
Do not mix ICP frames in a single piece of content. A blog post targeting CISOs should not detour into skill marketplace features. A LinkedIn post about Claude Code standardisation should not lead with SIEM integration.