opencode-skills-collection 3.1.12 → 3.1.14

package/bundled-skills/marketing-plan/references/team-and-agency-model.md

@@ -0,0 +1,278 @@
+# Team and Agency Model — Hire for Strategy, Outsource Execution
+
+The marketing operations stack (Section 11 of every plan) describes *what* gets done. This doc describes *who does it* — the operating principle, the org shape, the first hire, the agency model, and how it evolves as the company scales.
+
+Excerpted and adapted from *Founding Marketing* by Corey Haines.
+
+## The principle
+
+**Strategy lives in-house. Execution can — and often should — be outsourced.**
+
+Two failure modes are common when founders ignore this:
+
+1. **Hire junior tactician first.** Founder hits a milestone, raises a round, hires a junior to "do marketing" (run ads, write blogs, post on social). Six months later: scattered tactics, no coherent strategy, disappointing results.
+2. **Hire expensive agency for strategy.** Burns cash while the internal team struggles to execute on recommendations they don't fully understand. Strategic insight gathers dust; tactical needs go unmet.
+
+The traditional advice — "hire full-time for competitive advantages, only use agencies for commoditized work" — made sense when marketing moved slowly and talent stayed for decades. That world is gone. Full-time hires take months to ramp and years to develop deep expertise. The best agencies and contractors deliver results immediately, with cross-industry pattern recognition you couldn't build in-house affordably.
+
+## What stays in-house
+
+The strategic heart of the marketing operation. Specifically:
+
+- **Strategic direction and vision** — the "why" behind every move
+- **Customer and market understanding** — only comes from daily immersion in the business
+- **Positioning and deep market knowledge** — represents the company's unique place in the market
+- **Core product and service delivery** — the heart of the value proposition
+- **Long-term institutional knowledge** — the compound interest of experience
+
+These are not delegatable. An external partner can sharpen the articulation, but the underlying conviction must come from the team.
+
+## What's safe to outsource
+
+External expertise shines in specific contexts:
+
+- **Best-in-class implementation of specialized skills** (paid media operators, technical SEO, video production, designers)
+- **Burst capacity** — launch sprints, campaign cycles, one-off content production
+- **Well-defined strategies** — when the scope, deliverables, and success metrics are clear
+- **Fresh eyes on old problems** — external perspective when the team is too close to see clearly
+
+The trick is *defining* what's being outsourced. Vague briefs ("help us with marketing") produce vague results. Specific briefs ("ship 20 RSAs across 4 ad groups by month-end with the CTR benchmarks in the brief") produce shippable work.
+
+## The three core functions
+
+Every marketing engine has three primary functions. Whether you have a team of 1 or 50, the functions exist — even if one person owns several.
+
+### Growth Marketing — the demand engine
+
+- Optimizes campaigns
+- Manages the funnel
+- Operates distribution channels
+- Runs the marketing tech stack
+- Data-driven; constantly testing and measuring
+
+Drives quantitative outcomes: leads, signups, paid traffic, conversion rate, CAC.
+
+### Product Marketing — the story engine
+
+- Transforms product benefits into compelling messages
+- Powers product launches
+- Equips the sales team
+- Owns pricing and packaging communication
+- Bridges what's built and why people should care
+
+Drives positioning quality, message-market fit, launch impact, sales enablement.
+
+### Content Marketing — the trust engine
+
+- Maintains the brand voice
+- Manages the editorial calendar
+- Produces content that reaches and teaches the audience
+- Proves impact through customer stories
+- Shapes industry conversations through thought leadership
+- Supports sales with closing content
+
+Drives organic traffic, brand affinity, thought leadership, trust signals.
+
+These three functions are interconnected. Growth without story is performance with no positioning. Story without distribution is a great pitch nobody hears. Trust without demand capture is brand affinity that doesn't compound into revenue.
+
+## The first marketing hire
+
+The most consequential decision in building the marketing engine isn't about channels or technology — it's who leads.
+
+**The first marketing hire should be a strategist, not a tactician.** Counterintuitive when there's a mountain of tactical work to ship. Essential for sustainable growth.
+
+### Look for π-shaped, not T-shaped
+
+The standard advice is to hire a **T-shaped marketer**: broad knowledge across many areas, deep in one. That's fine for a tactical IC role.
+
+For the first strategic hire, look for **π-shaped**: two deep skill sets, plus broad surface-level competency across the rest. The two depths create unique leverage through their combination.
+
+#### High-leverage combinations
+
+**Product Marketing + Growth Marketing**
+- Owns positioning *and* drives distribution
+- Crafts the message *and* gets it to market
+- No gap between planning and doing
+- Best for technical products or complex sales
+
+**Product Marketing + Content Marketing**
+- Translates product into compelling stories
+- Owns voice and positioning together
+- Creates content that compounds
+- Best for thought-leadership or education-driven markets
+
+**Growth Marketing + Content Marketing**
+- Builds the demand engine and the content that fuels it
+- Closes the loop between SEO/social distribution and conversion
+- Best for content-led growth motions
+
+The wrong shape for a first hire: deep paid media specialist alone, deep SEO specialist alone, deep designer alone. These are tactical depths; they need a strategic owner above them.
+
+### Title and progression — don't inflate
+
+A common mistake: making the first marketing hire a "CMO" or "VP." Creates problems when you actually need to scale the org, because there's no headroom above them.
+
+The right progression:
+
+| Title | Scope |
+|---|---|
+| **Manager** | Individual contributor, co-manages freelancers |
+| **Lead** | Senior IC, manages freelancers/agencies |
+| **Director / Head** | Manages ICs and vendors |
+| **VP** | Manages Directors |
+| **Chief (CMO)** | Manages VPs |
+
+The first hire is almost always **Marketing Manager** or **Marketing Lead**. They should be able to:
+
+- Define positioning — not just describe what you do, but why it matters
+- Identify best channels — from data, not intuition
+- Create the messaging framework — consistency across touchpoints
+- Build the marketing engine — systems that scale beyond any individual
+- Manage external resources — get the most from agencies and contractors
+
+Both strategic *and* hands-on. Comfortable setting direction and rolling up sleeves. Most importantly: a **builder** — creates processes, frameworks, and systems that scale beyond their individual capacity.
+
+## The marketing engine — three components
+
+Think of the marketing organization as an engine. Each part has a specific role; the magic is in how they work together.
+
+### The Fuel — Strategy
+
+What powers everything else. Without good fuel, even the best engine sputters.
+
+- Product marketing creates positioning (foundation of all communication)
+- Content marketing develops stories (features → benefits that resonate)
+- Brand marketing establishes identity (memorable and meaningful)
+
+Quality of the fuel determines efficiency. Poor positioning, weak stories, inconsistent branding waste energy regardless of execution.
+
+### The Engine — Execution
+
+Where strategy turns into action.
+
+- Growth marketing drives distribution (right message to the right people)
+- Demand gen creates opportunities (attention → interest)
+- Operations maintains systems (everything running smoothly)
+
+Needs to be well-maintained and properly tuned. Right processes, tools, people in place to execute consistently.
+
+### The Dashboard — Analytics
+
+How you know if you're heading in the right direction.
+
+- Metrics track performance (measuring what matters)
+- Attribution shows what works (cause and effect)
+- Data informs decisions (evidence over opinion)
+
+Without good instrumentation, flying blind. Need both leading and lagging indicators.
+
+## Working with agencies — selection framework
+
+Not all agencies are created equal. Ranked from most appropriate for early-stage to least:
+
+### Individual contractors
+- **Most flexible** — adapt quickly to changing requirements
+- **Direct relationship** — no account-management layer
+- **Often most cost-effective** — pay for pure expertise
+- **Best for** specific skills (paid media op, technical SEO, video editor, designer)
+
+For most pre-Series-A companies, this is the right answer for nearly all outsourced work.
+
+### Small niche agencies
+- **Specialized expertise** — deep knowledge in specific areas
+- **Personal attention** — often working directly with senior team
+- **Often founder-led** — experienced practitioners calling the shots
+- **Clear focus** — they know what they're good at
+- **Best for** specialized needs with some complexity (full SEO program, lifecycle email program, brand identity work)
+
+### Small generalist agencies
+- **Broader capabilities** — handle multiple needs
+- **More resources** — team approach to problems
+- **Multiple skill sets** — cross-functional
+- **Usually more expensive** — paying for convenience
+- **Best for** companies needing broader support and willing to pay for the simplicity of fewer relationships
+
+### Large agencies (not recommended for most startups)
+- Long contracts, high minimums, junior account teams, slow turnaround
+- Useful only when the brand spend is large enough to command senior attention
+
+## Setting agencies up for success
+
+The difference between a successful and failed agency relationship usually comes down to structure and management.
+
+### Before starting
+
+- **Define clear objectives** — what specific outcomes are we seeking?
+- **Set realistic timelines** — when do we need to see results?
+- **Establish communication channels** — how do we stay aligned?
+- **Agree on metrics** — what defines success?
+- **Document processes** — how do we work together?
+
+### During engagement
+
+- **Regular check-ins** — weekly tactical, monthly strategic
+- **Clear feedback loops** — both ways, positive and constructive
+- **Data sharing** — give them what they need to succeed
+- **Performance reviews** — measure against agreed metrics
+- **Strategy alignment** — ensure they're moving with the business
+
+### Red flags
+
+- **Scope creep beyond core expertise** — trying to do too much
+- **High team turnover** — losing institutional knowledge
+- **Missed deadlines** — failing to deliver as promised
+- **Poor communication** — lack of proactive updates
+- **Unclear reporting** — can't demonstrate value
+
+The best agency relationships feel like partnership: they understand the business, care about success, bring expertise you couldn't build in-house affordably. Takes work on both sides — clear expectations, open communication, mutual respect.
+
+## Scaling the model by stage
+
+The right ratio of internal to external resources isn't static. It evolves with stage, needs, and market conditions.
+
+### Early stage (pre-product-market-fit)
+
+**Mode:** discovery and iteration
+
+- **Internal:** 1–2 strategic hires leading the charge (often the founder + one π-shaped marketer)
+- **External:** specialized contractors for execution (no long-term commitment)
+- **Agency relationships:** project-based, testing approaches before bigger investments
+- **North star:** solid foundation while keeping fixed costs low
+
+### Growth stage (post-PMF, scaling what works)
+
+**Mode:** optimization
+
+- **Internal:** small but mighty core strategic team that owns marketing direction
+- **External:** balanced mix of contractors and agencies, each chosen for specific expertise
+- **Agency relationships:** deeper, longer-term — partners who grow with you
+- **North star:** double down on channels and approaches that have proven successful
+
+### Scale stage (multi-channel, multi-segment)
+
+**Mode:** coordination
+
+- **Internal:** larger strategic team focused on coordination and oversight (not execution)
+- **External:** specialized agencies, each bringing deep expertise in specific areas of the mix
+- **Trusted contractor network:** flexibility for variable workloads and special projects
+- **North star:** finding efficiencies, improving processes, maximizing return
+
+The metaphor: a symphony orchestra. The internal team conducts. External partners play their instruments with expertise.
+
+## How this informs the plan
+
+| Section | What to include |
+|---|---|
+| **3 (Current state)** | Team composition — every person who touches marketing, what they own. Identify where the team is π-shaped vs. T-shaped vs. tactical-only. Flag gaps. |
+| **9 (90-day roadmap)** | If the team is missing the strategic owner, the first move is the first marketing hire (Lead or Manager). If the team has strategy but no execution capacity, the first move is the first contractor or specialized agency. |
+| **10 (12-month outlook)** | Map team evolution against funding-stage capability unlocks (see `funding-stage-unlocks.md`). When does the second hire come in? When does an agency relationship deepen? |
+| **11 (Marketing operations stack)** | RACI is more honest with this model: "owned by" = internal strategic role; "executed by" = internal IC, contractor, or agency. The plan should make it explicit who does what. |
+| **13 (Open decisions)** | If "first marketing hire" is open, name it as a top-three decision. If "in-house vs agency" for a specific function is open, frame the tradeoff using this doc's heuristics. |
+
+## Operational guardrails
+
+- **Don't title-inflate the first hire.** It paints the org into a corner.
+- **Don't outsource positioning.** Even the best agency can articulate it back to you, but only if the conviction came from the team.
+- **Don't full-time hire for a six-month sprint.** Use a contractor. The hidden cost of full-time is the months of ramp + the awkwardness of letting them go if the work doesn't compound.
+- **Don't agency-hire to delay a strategy conversation.** Agencies execute; they don't replace strategic owners. If the internal team can't tell the agency what to do, the agency can't help.
+- **Don't measure team size as a success metric.** Measure output, not headcount. A 4-person team with the right π-shaped leader and great external partners out-performs a 15-person team without strategic clarity.

package/bundled-skills/mdpr-skill/SKILL.md

@@ -0,0 +1,233 @@
+---
+name: mdpr-skill
+description: "Review MDPR Markdown presentation workflows with semantic hints, visual checks, and deterministic renderer boundaries."
+category: productivity
+risk: safe
+source: community
+source_repo: ch040602/mdpr-skill
+source_type: community
+date_added: "2026-07-01"
+author: ch040602
+tags: [mdpr, presentations, markdown, powerpoint, codex, visual-review, agent-hints]
+tools: [claude, cursor, gemini, codex, antigravity]
+license: "MIT"
+license_source: "https://github.com/ch040602/mdpr-skill/blob/main/LICENSE"
+---
+
+# mdpr-skill
+
+## Overview
+
+Use this skill as the optional agent companion for
+[MDPR](https://github.com/ch040602/MdPr), a deterministic
+Markdown-to-presentation runtime. MDPR owns parsing, layout, theming,
+validation, and final PPTX/HTML/PDF rendering. This skill helps an agent review
+MDPR workflows, propose weak semantic hints, and explain visual findings without
+taking control of slide geometry.
+
+The upstream skill source is
+[`ch040602/mdpr-skill`](https://github.com/ch040602/mdpr-skill), which includes
+schemas, review commands, compatibility artifacts, visual evidence examples, and
+MDPR boundary documentation.
+
+## When to Use This Skill
+
+- Use when the user asks about MDPR, `mdpresent`, Markdown-to-PPTX, or
+  Markdown presentation review.
+- Use when generated MDPR artifacts need semantic, narrative, accessibility, or
+  visual review notes.
+- Use when the user wants Codex-style presentation workflow hints while keeping
+  MDPR as the deterministic renderer.
+- Use when comparing MDPR output against image-only deck generators such as a
+  codex-ppt style workflow.
+- Use when a reusable theme or style-pack proposal should be expressed as an
+  approval-bound MDPR candidate instead of direct final slide edits.
+
+## Core Boundary
+
+- Let MDPR own parsing, slide splitting, recipes, layout, coordinates,
+  geometry, typography, colors, z-order, arrows, effects, exact icon assets,
+  renderer object IDs, and final PPTX objects.
+- Keep agent output semantic, evidence-based, and schema-valid.
+- Express fixes as Markdown cleanup, MDPR rulebook changes, config changes,
+  deterministic policy changes, or approval-bound proposals.
+- Preserve the ability to build the same deck with all agent hints disabled.
+- Do not mutate source Markdown unless the user explicitly asks for a cleaned
+  source draft.
+
+## How It Works
+
+### Step 1: Identify the MDPR Surface
+
+Classify the user's request before producing advice:
+
+- `semantic hints`: compact intent, grouping, importance, and icon-keyword
+  suggestions.
+- `review report`: visual or narrative concerns grounded in rendered evidence,
+  manifests, or validation reports.
+- `layout intent`: high-level layout goals from a summarized template catalog,
+  never concrete placeholder coordinates.
+- `theme candidate`: reusable token and style-pack proposal for later MDPR
+  approval/import gates.
+- `codex-ppt compatibility`: feature mapping and comparison notes only; do not
+  turn MDPR into a full-slide image renderer.
+
+### Step 2: Ground Every Finding
+
+Reference available evidence such as:
+
+- source Markdown path or heading text
+- MDPR manifest summaries
+- rendered preview image paths
+- validation report IDs
+- source notes or citation metadata
+- schema names such as `agent-hint.json`, `review-report.json`, or
+  `mdpr-theme-candidate-v1`
+
+If evidence is missing, say what artifact is needed instead of inventing a
+pass/fail result.
+
+### Step 3: Keep Hints Weak
+
+Allowed hints:
+
+- slide or section intent
+- content grouping
+- relative importance
+- icon-search keywords
+- accessibility or citation review notes
+- generated-image candidate briefs when an icon would be too small or too
+  semantically ambiguous
+
+Disallowed hints:
+
+- final coordinates, sizes, z-order, geometry, or object IDs
+- exact colors, typography, arrows, effects, or icon asset choices
+- final layout IDs or placeholder IDs
+- pass/fail validation decisions not backed by MDPR validation
+
+### Step 4: Route Fixes to MDPR-Owned Changes
+
+When repeated issues appear, recommend a deterministic follow-up surface:
+
+- Markdown cleanup
+- MDPR rulebook change
+- MDPR config/profile change
+- MDPR theme-pack registration
+- MDPR validation improvement
+- approval-bound deck-local override or style-pack candidate
+
+## Useful Local Commands
+
+Run these only when the upstream `mdpr-skill` CLI is available in the current
+workspace and the referenced input files exist.
+
+```bash
+node bin/mdpr-skill.js hint --source-sha256 <64hex> --out .mdpresent/proposals/agent-hint.json
+node bin/mdpr-skill.js review --manifest dist/mdpresent-manifest.json --out .mdpresent/review/review-report.json
+node bin/mdpr-skill.js narrative --markdown deck.md --manifest dist/mdpresent-manifest.json --out .mdpresent/review/narrative-review.json
+node bin/mdpr-skill.js layout-intent --layout-catalog template-layout-catalog.json --out .mdpresent/review/layout-intent.json
+node bin/mdpr-skill.js accessibility --markdown deck.md --audience "executive review" --out .mdpresent/review/accessibility-review.json
+```
+
+## Examples
+
+### Review a Rendered MDPR Deck
+
+1. Read the source Markdown, manifest summary, rendered image list, and any
+   validation report.
+2. Separate source-content problems from renderer/rulebook problems.
+3. Report only evidence-backed visual concerns.
+4. Recommend deterministic MDPR fixes when the same issue repeats.
+
+```markdown
+Finding: Slide 4 has weak visual hierarchy between the metric and explanation.
+Evidence: rendered/slide-04.png, manifest slide id `s4`, heading "Revenue Mix".
+MDPR-owned fix: adjust the metric-card recipe spacing rule or choose a
+deterministic layout profile with stronger numeric emphasis.
+```
+
+### Propose a Theme Candidate
+
+1. Treat the source design as a visual system, not content to copy.
+2. Extract reusable tokens, semantic layout blueprints, decoration grammar, and
+   best-fit scenarios.
+3. Emit an approval-bound `mdpr-theme-candidate-v1`.
+4. Keep `mdprOwnsFinalLayout`, `mdprOwnsFinalThemeBinding`, and
+   `noRawUseInAgentHints` true.
+
+```json
+{
+  "schema": "mdpr-theme-candidate-v1",
+  "source": "rendered reference set approved by user",
+  "useCases": ["executive review", "research update"],
+  "constraints": {
+    "mdprOwnsFinalLayout": true,
+    "mdprOwnsFinalThemeBinding": true,
+    "noRawUseInAgentHints": true
+  }
+}
+```
+
+### Compare with codex-ppt Style Workflows
+
+Use codex-ppt only as a capability reference or image-only baseline. Preserve
+the output-model distinction: codex-ppt style workflows may produce full-slide
+images, while MDPR defaults to editable PPTX/HTML/PDF with deterministic
+validation.
+
+```markdown
+Comparison note: codex-ppt style output may optimize for a single rasterized
+slide image. MDPR should instead preserve editable slide objects and route
+visual improvements through recipes, themes, and validation policies.
+```
+
+## Best Practices
+
+- Do: Prefer concise semantic hints over restating the source.
+- Do: Keep review notes actionable for MDPR maintainers.
+- Do: Call out missing evidence before making quality claims.
+- Do: Treat LLM judgment as triage only; MDPR validation remains the release
+  gate.
+- Avoid: Turning generated asset prompts into final asset selections.
+- Avoid: Recommending raw colors, coordinates, or renderer object IDs from
+  agent judgment alone.
+
+## Limitations
+
+- This skill does not replace MDPR runtime validation.
+- This skill does not generate final slide coordinates or final PPTX objects.
+- This skill does not make MDPR depend on an LLM.
+- This skill should not be used to copy private deck designs or proprietary
+  slide content.
+
+## Common Pitfalls
+
+- **Problem:** Treating mdpr-skill output as final slide layout.
+  **Solution:** Keep hints semantic and let MDPR choose final layout, geometry,
+  and renderer objects.
+
+- **Problem:** Reporting visual issues without evidence.
+  **Solution:** Link each finding to source Markdown, a manifest entry, rendered
+  previews, validation reports, or another concrete artifact.
+
+- **Problem:** Copying codex-ppt image-only behavior into MDPR.
+  **Solution:** Use image-only generators as comparison baselines while
+  preserving MDPR's editable PPTX/HTML/PDF output model.
+
+## Security & Safety Notes
+
+- Review only files the user has provided or authorized.
+- Do not fetch private references, credentials, or paid assets without explicit
+  permission.
+- Do not include secrets, API keys, or private source content in generated
+  review reports or theme candidates.
+- Treat all CLI commands as local workspace commands; confirm input paths exist
+  before running them.
+
+## Related Skills
+
+- `@frontend-slides` - Use for browser-native HTML presentation generation.
+- `@2slides-ppt-generator` - Use for hosted API-based presentation generation.
+- `@office-productivity` - Use for broader document, spreadsheet, and slide
+  workflow coordination.