@rubytech/create-siteoffice-code 0.1.256

package/payload/platform/plugins/projects/references/retrospective.md

@@ -0,0 +1,71 @@
+# Retrospective
+
+Extract operational knowledge from a completed project. The goal is to accumulate institutional learning that makes future projects better — shorter timelines, fewer surprises, better estimates, stronger processes.
+
+This is not a performance review. It's a knowledge extraction exercise. The focus is on what was surprising, what assumptions were wrong, and what the business now knows that it didn't know before.
+
+## Process
+
+### Reconstruct the Timeline
+
+Read the project's Task node and its notes. The structured lifecycle notes (`[PROJECT:START]`, `[PROJECT:PHASE]`, `[PROJECT:COMPLETE]`) provide the skeleton. Fill in the timeline:
+
+- When did each phase start and end?
+- Where were the delays? What caused them?
+- What went faster than expected? Why?
+- Were the original estimates accurate? If not, by how much and in which direction?
+
+### Identify Learnings
+
+For each phase of the project, ask:
+
+- **What was surprising?** — anything that didn't match expectations, positively or negatively
+- **What assumption was wrong?** — beliefs that were disproved by reality (e.g., "materials take 2 weeks" when they actually took 3)
+- **What would you do differently?** — concrete changes to approach, process, or tools
+- **What worked well?** — approaches worth repeating on future similar projects
+
+Focus on learnings that are transferable to future projects, not one-off observations about this specific project.
+
+### Persist Learnings
+
+For each actionable learning, write it to the graph so it can be surfaced on future similar projects:
+
+Use `memory-write` to create an entity with:
+- **labels:** `["DefinedTerm"]`
+- **properties:**
+  - `name`: Short description of the learning (e.g., "Kitchen refit material lead times")
+  - `description`: Full learning with context (e.g., "Materials for a kitchen refit consistently take 3 weeks, not 2. Factor in supplier delays and partial deliveries. Always confirm lead times directly with the supplier rather than relying on catalogue estimates.")
+  - `category`: `"project-learning"`
+- **relationships:** `[{ targetId: "{project task ID}", type: "ABOUT" }]`
+
+The `ABOUT` relationship links the learning to the source project. The embedding on the entity enables `memory-search` to surface it when a future project has a similar description.
+
+### Present the Summary
+
+Summarise the retrospective for the user:
+
+- **Project:** Name and duration
+- **Outcome:** Completed/partial/abandoned, with task completion stats
+- **Key learnings:** The 3-5 most important things learned, each in one sentence
+- **Applied to graph:** How many learnings were persisted and what they cover
+- **Recommendation:** One concrete action for the next similar project
+
+Mark the retrospective complete: `[PROJECT:PHASE] Retrospective — {n} learnings captured`.
+
+## Cross-Project Learning
+
+When starting a new project, `memory-search` with the project description will surface relevant learnings from past projects (because learnings are DefinedTerm entities with embeddings). Present these to the user during the Plan phase:
+
+"Based on past projects, here's what I've learned that might be relevant:
+- {learning 1} (from {source project})
+- {learning 2} (from {source project})"
+
+The user decides whether to act on prior learnings. They are inputs to planning, not constraints.
+
+## When to Use
+
+- After a project sprint completes (the Learnings phase of a Full tier sprint loads this reference)
+- "What did we learn from the Henderson project?"
+- "Let's do a retro on the kitchen refit"
+- "Before we start the next one, what should we keep in mind?"
+- On request at any time for any completed project

package/payload/platform/plugins/projects/references/review.md

@@ -0,0 +1,51 @@
+# Deliverable Review
+
+Quality review of completed work against the original brief. When a project has produced deliverables and someone needs to confirm they meet the standard before handoff, sign-off, or client delivery.
+
+This is not a progress check — it's a quality gate. The work should be substantially complete before entering review mode.
+
+## Process
+
+### Establish the Brief
+
+Retrieve the original brief, spec, or agreement that defines what was promised. This may be:
+- The locked execution plan from a sprint (if the work came from a structured project)
+- A quote or proposal sent to a client
+- A verbal agreement captured in task notes or memory
+- A regulatory requirement or compliance checklist
+
+If no written brief exists, construct one from the available evidence and confirm it with the user before proceeding.
+
+### Review Each Deliverable
+
+For every item in the brief:
+
+- **Delivered as promised** — the deliverable meets the agreed specification. State what confirms this.
+- **Delivered with deviation** — the deliverable exists but differs from what was agreed. Describe the difference and whether it's acceptable.
+- **Not delivered** — the deliverable is missing. Determine whether it was intentionally deferred, forgotten, or blocked.
+- **Over-delivered** — work was done beyond what was promised. Note whether this adds value or represents scope creep.
+
+### Quality Assessment
+
+Beyond checking against the brief, assess overall quality:
+- Is the work client-ready? Would you be comfortable handing this to the end recipient?
+- Are there obvious errors, omissions, or rough edges?
+- Does the work reflect the agreed standard of care for this type of deliverable?
+- If this work will be built upon later, is the foundation solid?
+
+### Verdict
+
+Summarise the review:
+- **Pass** — all deliverables meet the brief, quality is acceptable. Ready for handoff.
+- **Conditional pass** — most deliverables meet the brief, but specific items need attention before handoff. List them.
+- **Fail** — significant gaps between what was promised and what was delivered. List every gap and what's needed to resolve it.
+
+Record the verdict in the project task notes: `[PROJECT:PHASE] Review — {Pass/Conditional/Fail}: {summary}`.
+
+## When to Use
+
+- "Can you check the documents before I send them to the client?"
+- "Review the quote package for the Henderson project"
+- "Is everything ready for handoff?"
+- "Check if we've done everything we promised"
+- "The work is done — review it against the original spec"

package/payload/platform/plugins/projects/references/sprint.md

@@ -0,0 +1,168 @@
+# Project Sprint
+
+A structured workflow for executing a scoped unit of business work — a client project, a renovation, a product launch, an operational improvement. The sprint ensures nothing falls through the cracks: every deliverable is checked against what was agreed, every deviation is surfaced, and every project produces a structured record and accumulated learnings.
+
+## Adaptive Tiers
+
+Not every project needs the same level of structure. Select the tier based on the project's complexity, risk, and duration.
+
+| Tier | When to use | Phases |
+|------|-------------|--------|
+| Quick | Simple, low-risk work: fix a leak, send an invoice, single deliverable with no dependencies | Scope, Execute, Done |
+| Standard | Medium complexity: multi-step work with some dependencies and a client-facing deliverable | Plan, Execute, Verify, Debrief |
+| Full | Complex projects: multi-week, multiple dependencies, significant risk, multiple stakeholders | Plan, Challenge Premise, Lock Execution, Execute, Verify, Plan Conformity, Debrief, Deliverable Review, Learnings |
+
+When the user's intent is ambiguous, suggest a tier and let them adjust. If a Quick sprint reveals unexpected complexity mid-execution, offer to upgrade to Standard.
+
+---
+
+## Quick Tier
+
+### Scope
+
+Understand what needs doing. Confirm the deliverable, the deadline (if any), and who it's for. Create the parent Task with `[PROJECT:START]` and a single child task for the work.
+
+### Execute
+
+Do the work. Track progress via task notes. Check `work-ready` if there are any dependencies. Mark the child task complete when done.
+
+### Done
+
+Confirm the deliverable is complete. Mark the parent Task complete with `[PROJECT:COMPLETE]`. If there's a follow-up, create a new task for it.
+
+---
+
+## Standard Tier
+
+### Plan
+
+Understand the project scope: what are the deliverables, who are they for, what's the deadline, what are the dependencies. Create the parent Task and child tasks for each work item. Link dependencies via `BLOCKS` and related entities via `AFFECTS`.
+
+Check for prior learnings: call `memory-search` with a description of the project to surface relevant learnings from past similar work. If learnings exist, factor them into the plan — adjust timelines, flag known risks, apply lessons learned.
+
+### Execute
+
+Work through the child tasks in dependency order. Before starting each task, check `work-ready` to confirm no blockers or AFFECTS conflicts. Append progress notes as work progresses. If a blocker is discovered mid-execution, create a new child task for it and link via `BLOCKS`.
+
+Record phase transitions: `[PROJECT:PHASE] Execute — starting {task name}`.
+
+### Verify
+
+Walk through each deliverable against the acceptance criteria agreed in the Plan phase. For each deliverable:
+- Is it complete?
+- Does it meet the agreed standard?
+- Are there any outstanding items?
+
+Use domain-appropriate verification (see Domain Verification below).
+
+Flag any deliverable that was promised but not delivered, or delivered differently than agreed.
+
+### Debrief
+
+Produce a structured record:
+- **What was done:** Each deliverable and its outcome
+- **What changed:** Any deviations from the original plan and why
+- **What's next:** Immediate follow-up actions, if any
+- **Known limitations:** Anything intentionally deferred or incomplete
+
+Mark the parent Task complete with `[PROJECT:COMPLETE]`.
+
+---
+
+## Full Tier
+
+### Plan
+
+Same as Standard Plan, but more thorough: map all stakeholders, identify risks, estimate timeline for each work item, and define acceptance criteria for every deliverable.
+
+### Challenge Premise
+
+Before locking in the execution plan, challenge the scope:
+- Is this the right work to do right now? Could a different framing yield a better outcome?
+- What would happen if this project didn't happen? Is the pain real or hypothetical?
+- Are we solving the root cause or a symptom?
+- Is the scope right-sized? Too ambitious for the timeline? Too conservative for the opportunity?
+
+Surface any concerns and resolve them before proceeding.
+
+### Lock Execution
+
+Finalise the execution plan: confirm the task list, dependency order, timeline, resource requirements, and acceptance criteria. This is the agreement — Phase 6 (Plan Conformity) will check the outcome against this.
+
+Record the locked plan in the parent Task notes: `[PROJECT:PHASE] Execution locked — {n} tasks, estimated {timeline}`.
+
+### Execute
+
+Same as Standard Execute, with additional discipline:
+- At each session start, report project health (RAG signal from the PLUGIN.md)
+- Surface risks proactively — if a task is trending overdue, flag it before it becomes critical
+- When a blocker is discovered, assess its impact on the overall timeline
+
+### Verify
+
+Same as Standard Verify, plus:
+- Verify graph state — correct entities created or modified, relationships intact
+- Verify communication log — messages sent, confirmations received (if applicable)
+- Run domain-appropriate verification
+
+### Plan Conformity
+
+Compare every item in the locked execution plan against what was actually delivered. Every plan item must appear in exactly one category:
+
+- **Implemented as planned** — delivered as agreed, with evidence
+- **Deviated** — delivered differently than planned. State what changed and why.
+- **Omitted** — not delivered. State why it was dropped or deferred.
+- **Added** — delivered but not in the original plan. State why it was necessary.
+
+Silent omissions — items that were in the plan but neither delivered nor flagged — are the failure mode this phase exists to prevent. If deviations or omissions are found, present them for acknowledgement before proceeding.
+
+### Debrief
+
+Same as Standard Debrief, plus:
+- **Change log:** For every deliverable, what was done, why, and what it means
+- **Dependency resolution:** Were all blockers resolved? Any still outstanding?
+- **Completion checklist:** Every requirement from the plan with pass/fail status
+
+### Deliverable Review
+
+Review each deliverable against the original brief (not the execution plan — the brief that initiated the project). Check for completeness, accuracy, and client-readiness. Flag anything that was promised in the brief but not delivered, or delivered differently.
+
+### Learnings
+
+Extract operational knowledge from the project. Load `references/retrospective.md` via `plugin-read` and follow that process. This produces persistent learnings that inform future projects.
+
+---
+
+## Domain Verification
+
+The verification phase should feel relevant to the business domain. Use the `businessType` property on the `LocalBusiness` node to select appropriate verification prompts. If no businessType is set, use the general prompts.
+
+### Trades (plumbing, electrical, building, renovation)
+- Has the work been physically completed to standard?
+- Are all materials accounted for?
+- Has the client inspected and approved?
+- Are there any snagging items?
+- Is the site left clean and safe?
+- Has the warranty or guarantee period been communicated?
+
+### Estate Agency (property sales, lettings, management)
+- Are all required documents complete and accurate? (EPC, floor plan, particulars, contracts)
+- Are photographs professional and current?
+- Has the listing been posted to all agreed portals?
+- Have all parties been notified of progress?
+- Are compliance requirements satisfied? (anti-money laundering, right to rent)
+- Is the file complete for audit?
+
+### Professional Services (consulting, accounting, legal, design)
+- Has the deliverable been reviewed against the statement of work?
+- Has the client signed off or provided written acceptance?
+- Are all project files organised and accessible?
+- Has the final invoice been issued?
+- Are intellectual property and confidentiality obligations met?
+- Have handover notes been prepared for ongoing work?
+
+### General (no specific businessType or unknown)
+- Is each deliverable complete against its acceptance criteria?
+- Has the recipient confirmed receipt and satisfaction?
+- Are there any outstanding actions or follow-ups?
+- Is the project file complete — communications, documents, decisions recorded?

package/payload/platform/plugins/prompt-optimiser/.claude-plugin/plugin.json

@@ -0,0 +1,8 @@
+{
+  "name": "prompt-optimiser",
+  "description": "Prompt optimiser. Turns a rough draft, vague idea, or task description into a single finished, copy-pasteable prompt tuned for Opus 4.7 adaptive thinking in the chat app (claude.ai, Mac, iOS) — no placeholders, content baked in when supplied or a self-contained ask when not, ending with the literal `Think before answering` closing line. Triggers on requests to write, rewrite, optimise, sharpen, or polish a prompt. Ships one skill: prompt-optimiser.",
+  "version": "0.1.0",
+  "author": {
+    "name": "Rubytech LLC"
+  }
+}

package/payload/platform/plugins/prompt-optimiser/PLUGIN.md

@@ -0,0 +1,14 @@
+---
+name: prompt-optimiser
+surface: platform
+description: "Prompt optimiser. Turns a rough draft, vague idea, or task description into a single finished, copy-pasteable prompt tuned for Opus 4.7 adaptive thinking in the chat app (claude.ai, Mac, iOS) — no placeholders, content baked in when supplied or a self-contained ask when not, ending with the literal `Think before answering` closing line. Triggers on requests to write, rewrite, optimise, sharpen, or polish a prompt. Ships one skill: prompt-optimiser."
+skills:
+  - skills/prompt-optimiser/SKILL.md
+metadata: {"platform":{"always":true,"embed":["admin"],"pluginKey":"prompt-optimiser"}}
+---
+
+# Prompt Optimiser
+
+Core skill plugin. Provides the `prompt-optimiser` skill: given any rough prompt, half-formed idea, or task description, it returns a single high-quality prompt designed to run inside the chat app on Opus 4.7 with adaptive thinking — not the API.
+
+The output is always one fenced code block, final and free of template placeholders: content is baked in when the operator supplied it, or the prompt is written self-contained with an explicit "ask me for X" close when only a task class was described. Every produced prompt ends with the literal closing line that nudges Opus 4.7 toward maximum reasoning.

package/payload/platform/plugins/prompt-optimiser/skills/prompt-optimiser/SKILL.md

@@ -0,0 +1,318 @@
+---
+name: prompt-optimiser
+description: Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for Opus 4.7 (with adaptive thinking) inside the chat app — claude.ai, the Mac app, the iOS app — NOT the API. Use this skill whenever the user wants to write, rewrite, optimize, improve, sharpen, or polish a prompt for the chat app. Trigger phrases include "rewrite this prompt", "make this a better prompt", "optimize this prompt", "turn this into a prompt", "help me prompt this", "draft a prompt that...", "I want to ask...", or whenever the user pastes a draft prompt and asks for improvements. Also trigger when the user describes a task they plan to send into the chat app and clearly wants a reusable, well-structured prompt rather than a direct answer. The output is always a single, copy-pasteable prompt in a code block that the user sends as-is — never a template with placeholders.
+---
+
+# Prompt optimiser
+
+You turn whatever the user gives you — a rough draft, a vague idea, a task description, a paragraph of context — into a single high-quality prompt designed to run inside the chat app on Opus 4.7 with adaptive thinking.
+
+This is for the **chat app** (claude.ai, Mac, iOS), not the API. The user is going to paste a single message into chat. There is no system prompt, no `effort` parameter, no tool config to tune. The prompt itself has to do all the work.
+
+## Which mode are you in? (read this first)
+
+This skill is invoked two ways, and they want opposite outputs. Decide which one applies before doing anything else.
+
+**In-session restatement mode.** You are invoking this skill on the current turn's own user prompt — triggered by the standing prompt-optimiser directive — so that you can act on a sharper reading of what was just asked. The output is for *you*, the working agent, not for a human to paste anywhere. Produce a plain restated task and nothing else:
+
+- Restate what the user is actually asking for: the goal, the constraints they stated, and the format or scope if they gave one. Turn vague wording into concrete intent, grounded only in what they wrote plus the conversation context you already hold.
+- Write it as plain prose or a short bulleted brief. No fenced code block. No role line, no XML tags, no length-cap ceremony unless the user asked for one.
+- Do not end with "Think before answering". Do not ask the user to paste anything — you already have the content and the context.
+- Do not invent requirements or add scope the user did not ask for. If the prompt was already clear, say so in one line and restate it tightly.
+- The restated brief is bound by the three doctrines (see `/doctrine`): precise/concise/plain, no speculation, observability-first. If the user's wording carries a speculative claim or skips an observability step the doctrines require, the restatement corrects it rather than echoing the slip.
+- End the restated brief with this exact sentence as its own final line: "Delegate this task to the appropriate specialist." Apply on every restatement, without exception. The owning specialist is identified from the AGENTS.md roster loaded alongside this seat — the closing line is the trigger, not the classifier (Task 529).
+
+Then do the work from the restated task. Everything below this section is for the other mode and does not apply — stop reading here.
+
+**Chat-app prompt mode.** The user explicitly asked you to write, rewrite, or optimise a prompt they will paste into the chat app. That is the rest of this document: a single finished, copy-pasteable prompt in a code block ending in "Think before answering". Read on.
+
+## Two hard rules
+
+These two rules override everything else in this skill. Read them, then re-read them.
+
+### Rule 1 — No placeholders. Ever.
+
+Never produce a prompt that contains `[paste X here]`, `[your content]`, `{topic}`, `<your_input_here>`, `[INSERT Y]`, `___`, or any other template variable the user is expected to fill in. The user must be able to copy your output, paste it into chat, hit send, and have a working interaction. If the prompt requires content the user hasn't provided yet, the prompt itself must handle that — see Rule 2.
+
+If you catch yourself typing square brackets around a noun, stop. That's a placeholder. Rewrite.
+
+### Rule 2 — Ship a finished prompt no matter what the user gave you.
+
+Two cases:
+
+**Case A — the user gave you real content** (a draft they wrote, code, a document, a list of items, a specific question, an actual product description). Bake that content directly into the optimized prompt. The whole thing — content and instructions — goes inside the code block. The user copies, pastes, sends. Done.
+
+**Case B — the user only described a class of task** ("I want a prompt to triage my emails", "help me prompt Claude to review my code", "give me a prompt for writing LinkedIn posts about my launches"). Write the prompt as a complete, self-contained instruction that works on its own. End the instruction by either:
+- Asking Claude to ask the user for the specific inputs it needs ("Before drafting, ask me to share the product name, audience, and a link."), or
+- Phrasing the task so the user will naturally provide the input in their next chat turn ("I'm going to paste a batch of emails next. For each one, do the following...").
+
+Either way: no brackets, no fill-in-the-blank, no template syntax. The prompt is final.
+
+## What you output
+
+A single fenced code block containing the optimized prompt. Nothing else. No preamble like "Here's your prompt:". No trailing explanation of what you changed.
+
+The prompt must end with this exact line as its final line:
+
+```
+Think before answering
+```
+
+That line is non-negotiable. It is the user's signal to push Opus 4.7's adaptive thinking toward deeper reasoning inside the chat app, where API-side `effort` controls aren't available.
+
+## Why these principles work
+
+Opus 4.7 reads prompts more literally than older models, calibrates its own thinking and length to perceived complexity, and rewards prompts that are specific, structured, and motivated. The cookbook below is distilled from Anthropic's own Opus 4.7 prompting guidance. Each rule has a reason. Treat the reasons as the point — apply them with judgment, don't paste them mechanically.
+
+## The rewrite workflow
+
+Work through these in your head before writing the prompt. You don't need to surface them.
+
+1. **Identify the goal.** What does the user actually want produced? A document? A decision? Code? A list? An analysis? Name it concretely.
+2. **Identify the audience and use.** Who reads the output, and what will they do with it? This drives tone and format.
+3. **Decide: Case A or Case B.** Did the user provide the actual content, or just describe a class of task? This decides whether you bake content in or write a self-contained instruction (see Rule 2).
+4. **Spot the gaps.** Audience, format, length, constraints, examples, edge cases — note which are missing.
+5. **Fill the gaps with reasonable assumptions.** The user told you not to ask questions. Make the most useful, most defensible assumption and move on. Keep it grounded in what they wrote.
+6. **Pick a structure.** Single-paragraph instruction for simple tasks. XML tags for anything with multiple sections.
+7. **Write the prompt.** Apply the principles below.
+8. **End with the closing line.**
+9. **Scan for brackets.** Before you finalize, re-read your output looking for `[`, `{`, or `<...your...>`-style placeholders. Kill any you find.
+
+## Core principles to apply
+
+### Be clear and direct
+State the task explicitly. Specify the desired output format and any hard constraints up front. If you want above-and-beyond effort, say so — Opus 4.7 won't infer it from a vague brief. "Create an analytics dashboard" is weaker than "Create an analytics dashboard with as many relevant features and interactions as possible — go beyond the basics for a fully-featured implementation."
+
+### Cap the length explicitly
+Opus 4.7 sizes its answer to whatever it infers the task needs, so an uncapped instruction produces unpredictable length. When the user has any length preference — or when a tight output is plainly better — name a hard cap, and a unit where one helps. "Summarize this report" drifts; "Summarize this in exactly 5 bullets, each under 15 words, each starting with an action verb" lands. Choose the cap that serves the goal; don't impose one where length should float (a short story, an open-ended analysis).
+
+### Explain the why
+When you give an instruction, briefly explain the reason. "Avoid ellipses, because the output will be read aloud by a TTS engine that mispronounces them" lands far better than "Never use ellipses." Opus 4.7 generalizes well from explanations and follows reasoned instructions more faithfully.
+
+### Tell Claude what to do, not what to avoid
+Positive framing outperforms negative framing. "Write in flowing prose paragraphs" beats "don't use bullet points."
+
+### Match prompt style to desired output style
+If you want prose, write the prompt in prose. If you want minimal markdown in the output, use minimal markdown in the prompt. Style leaks through.
+
+### Use XML tags when sections multiply
+When the prompt mixes instructions, context, examples, and input, wrap each in its own descriptive tag — `<instructions>`, `<context>`, `<examples>`, `<input>`. Nest naturally where there's hierarchy. This is the single highest-leverage structuring move for complex prompts. For simple one-shot prompts, skip it; XML on a haiku request is overkill.
+
+### Give Claude a role when it sharpens behavior
+A one-line role assignment ("You are a senior product strategist at a B2B SaaS company") tightens tone and frame. Don't force a role onto every prompt — only when it meaningfully steers the output.
+
+### Use examples for format, tone, or structure
+If the user has any preference about *how* the output should look, include 2–4 examples in `<example>` tags (or wrap multiple in `<examples>`). Examples beat description for steering format. Make them relevant, diverse, and structured. Skip examples when the task is so generic that examples would over-constrain.
+
+### Put long inputs on top, the question on the bottom
+If the prompt includes a long document, transcript, or data dump that the user provided, place it at the top. Anthropic's own testing shows up to ~30% quality lift from this ordering on long-context tasks.
+
+### Ask for grounding in long-document tasks
+For analysis or Q&A over long inputs, instruct Claude to first pull relevant quotes into `<quotes>` tags, then answer based on those quotes. This dramatically reduces drift and hallucination.
+
+### Be literal about scope
+Opus 4.7 doesn't silently generalize. If you want an instruction applied broadly, say "apply this to every section, not just the first one." If you want Claude to take action rather than suggest, use imperative verbs ("Edit the function to..." not "Could you suggest improvements to..."). Suggestion-flavored phrasing produces suggestions.
+
+### Self-check for high-stakes outputs
+For code, math, claims, or anything where errors matter, append a verification instruction near the end: "Before you finish, re-read your answer and check it against the criteria above." This catches errors reliably.
+
+## Domain-specific moves
+
+These are sharp tools for specific task types. Apply only when relevant.
+
+**Frontend / design.** Opus 4.7 has a strong default house style (warm cream backgrounds, serif type, terracotta accents) that's wrong for most products. If the user is asking for a design, either (a) specify a concrete alternative palette, type system, and structure in detail, or (b) instruct the model to propose 3–4 distinct visual directions before building, so the user picks one. Generic instructions like "make it clean and minimal" don't break the default.
+
+**Code review.** Tell the model its job at the finding stage is coverage, not filtering: "Report every issue you find, including ones you're uncertain about or consider low-severity. Include confidence and severity for each finding so a downstream filter can rank them." Avoid soft language like "only flag important issues" — Opus 4.7 takes that literally and under-reports.
+
+**Research / analysis.** Encourage hypothesis-tracking: "Develop several competing hypotheses as you gather information. Track confidence levels in your notes. Self-critique your approach periodically." This produces more rigorous synthesis than a flat "research X" prompt.
+
+**Creative writing.** Specify voice, audience, length, constraints, and provide one or two example sentences in the target voice if the user has them. Generic "write a blog post" yields generic prose.
+
+**Document creation (slides, reports).** Ask for design intentionality: "Include thoughtful visual hierarchy, considered typography, and engaging structure." Opus 4.7 produces strong first-pass document design when invited to.
+
+## Output format
+
+Always exactly this:
+
+````
+```
+[the optimized prompt — final, no placeholders, content baked in if provided
+or self-contained with an explicit "ask me for X" close if not]
+
+Think before answering
+```
+````
+
+No text before the code block. No text after. No "here you go." No "I added X and Y." Just the prompt.
+
+If the user explicitly asks "what did you change?" *after* they have the prompt, then explain in a follow-up turn. Until they ask, stay silent.
+
+## Examples
+
+These show the no-placeholder rule in action. Notice none of them contain `[paste X here]` or any other template variable.
+
+### Example 1 — Case B (user described a task class, no content given)
+
+**User input:**
+> I want a prompt to summarize my emails
+
+**Your output:**
+
+````
+```
+You are an executive assistant helping me triage email. I'm about to share a batch of emails with you in my next message.
+
+For each email, produce:
+- **Sender + subject** in one line
+- **Summary** — 1-2 sentences, neutral tone, no fluff
+- **Action required** — one of: reply needed, FYI only, schedule, delegate, ignore
+- **Priority** — high / medium / low, based on sender importance and urgency cues
+
+Group the output into three sections in this order: high priority, medium priority, low priority. Within each section, sort by action-required first (reply needed → schedule → delegate → FYI → ignore).
+
+Skip any email that's clearly automated marketing or notification spam — list its sender and subject under a final "Filtered out" section so I can verify.
+
+When you're ready, ask me to paste the emails.
+
+Think before answering
+```
+````
+
+The prompt ends by inviting the user to paste content in the next turn. No `[paste emails here]` block. The user sends this as-is and Claude responds with "Ready when you are — paste the batch."
+
+### Example 2 — Case B (rough draft prompt, no product details given)
+
+**User input:**
+> can you fix this prompt: "write a linkedin post about my new product launch, make it engaging and not too salesy"
+
+**Your output:**
+
+````
+```
+You are writing a LinkedIn post for me announcing a product launch. The audience is mid-to-senior B2B operators on LinkedIn — they've seen every launch post template and are skeptical of marketing language.
+
+Before you draft, ask me for:
+- The product's name
+- What it does, in plain language
+- Who it's for
+- The 1-2 reasons I built it that aren't obvious from the description
+- A link or destination for the call to action
+
+Once I've answered, write one post that:
+- Opens with a concrete hook in the first 2 lines (a tension, a number, or an unexpected observation — not "I'm excited to announce").
+- Tells a short story or shares a specific insight that led to the product, before naming it.
+- Names what the product does in one plain sentence. No adjectives like "revolutionary", "game-changing", or "powerful".
+- Closes with one clear next step (link, DM, comment) — not a generic "let me know what you think".
+- Sits between 150 and 220 words. Short paragraphs, one idea per line break. No emojis. No hashtags except up to two at the very end if they're genuinely relevant.
+
+Match the voice of someone who's built the thing themselves and is talking to peers, not pitching to strangers.
+
+Think before answering
+```
+````
+
+Instead of a `<product_details>` block with `[paste details here]`, the prompt explicitly tells Claude to gather the details by asking. Self-contained, ready to send.
+
+### Example 3 — Case B (technical task, no code given)
+
+**User input:**
+> I need claude to review my python code for bugs
+
+**Your output:**
+
+````
+```
+You're going to review Python code I share with you. Your job at the finding stage is coverage, not filtering — assume a separate pass will rank findings later.
+
+When I paste the code, report every issue you find, including ones you're uncertain about or consider low-severity. For each finding, include:
+- **Location** — file and line number(s)
+- **Issue** — what's wrong, in one sentence
+- **Why it matters** — the concrete failure mode (incorrect output, crash, security risk, race condition, etc.)
+- **Confidence** — high / medium / low
+- **Severity** — high / medium / low
+- **Suggested fix** — a minimal change that addresses the issue
+
+Cover at minimum: logic errors, off-by-one and boundary issues, mutable default arguments, exception handling gaps, race conditions and concurrency issues, resource leaks (files, connections, locks), input validation at trust boundaries, and any deviation from the code's apparent intent.
+
+Do not filter for importance at this stage. It's better to surface a finding that gets filtered out later than to silently drop a real bug.
+
+After listing findings, end with a single-paragraph overall assessment of code quality and the top 3 highest-severity issues to fix first.
+
+Ask me to paste the code when you're ready.
+
+Think before answering
+```
+````
+
+### Example 4 — Case A (real content provided, no follow-up needed)
+
+**User input:**
+> rewrite this so it's clearer: "Hey can you help me figure out whether to take the offer from Stripe vs the one from Anthropic. Stripe is paying 280k base + 60k bonus + 100k stock per year vesting over 4. Anthropic is 250k base + 0 bonus but 800k stock vesting over 4 with 1yr cliff. I care most about long term equity upside, work I'd be excited about, and not having to relocate. Stripe wants me in SF 3 days a week, Anthropic is fully remote."
+
+**Your output:**
+
+````
+```
+I'm deciding between two job offers and want your help thinking it through carefully.
+
+**My priorities, in order:**
+1. Long-term equity upside
+2. Work I'd be excited about
+3. Avoiding relocation
+
+**Offer A — Stripe**
+- $280k base
+- $60k annual bonus
+- $100k/year stock, vesting over 4 years
+- Hybrid: in SF 3 days a week
+
+**Offer B — Anthropic**
+- $250k base
+- No annual bonus
+- $800k stock, vesting over 4 years with a 1-year cliff
+- Fully remote
+
+Walk me through:
+1. The total expected compensation under each, year-by-year over 4 years, including a sensitivity range on equity outcomes (say: bear / base / bull cases for each company).
+2. How each offer scores against my three priorities, ranked.
+3. The non-obvious risks of each (what each offer's structure says about the company's confidence, how cliffs and vesting interact with my optionality, what the relocation requirement implies about future flexibility).
+4. Your overall recommendation and the single biggest reason it could be wrong.
+
+Be direct. Don't hedge with "it depends on what you value" — I told you what I value.
+
+Think before answering
+```
+````
+
+The user gave the actual numbers and constraints. They're baked in. No `[insert offer details]` block. The prompt is done.
+
+### Example 5 — simple task
+
+**User input:**
+> write me a haiku about coffee
+
+**Your output:**
+
+````
+```
+Write a haiku about coffee. Follow the traditional 5-7-5 syllable structure. Aim for a single concrete image rather than a general statement about coffee — something a reader could picture. Avoid clichés like "morning steam" and "liquid gold".
+
+Think before answering
+```
+````
+
+Notice the simple task doesn't get XML tags, a role, or a sectioning — and there's nothing to bake in. Apply structure proportional to the task; over-engineering a haiku prompt is its own failure mode.
+
+## Edge cases
+
+**The user pastes a prompt and asks "is this good?"** They want it rewritten regardless. Treat it as a rewrite request and return the optimized version in a code block. No commentary.
+
+**The user gives you a Claude system prompt or API-style prompt with parameters.** Strip out API-only mechanics (effort levels, thinking config, tool definitions), translate the intent into a single user-message prompt for the chat app, and end with the closing line.
+
+**The user wants the prompt to ask Claude to do many small things.** Combine into a single coherent prompt with clear sections rather than a numbered list of micro-tasks. Opus 4.7 handles long, well-structured asks well.
+
+**The user's input is already excellent.** Tighten where you can, add the closing line, return it. Don't add ceremony for its own sake.
+
+**The user input is in a language other than English.** Write the optimized prompt in the same language. Keep the closing line in English exactly as specified — that wording is what triggers the desired behavior in the chat app.
+
+**You're tempted to write a `<context>` or `<input>` block expecting the user to fill it.** Don't. That's Rule 1. Either bake the actual content in (Case A) or tell Claude to ask the user for it (Case B).

package/payload/platform/plugins/replicate/.claude-plugin/plugin.json

@@ -0,0 +1,17 @@
+{
+  "name": "replicate",
+  "description": "Image generation via Replicate — three models for different production needs.",
+  "version": "0.1.0",
+  "author": {
+    "name": "Rubytech LLC"
+  },
+  "mcpServers": {
+    "replicate": {
+      "type": "stdio",
+      "command": "node",
+      "args": [
+        "${CLAUDE_PLUGIN_ROOT}/mcp/dist/index.js"
+      ]
+    }
+  }
+}