aigroup-workflow 1.0.1 → 1.1.1

package/skills/jarvis/engineering-team/c-level-advisor/competitive-intel/references/ci-playbook.md

@@ -1,237 +0,0 @@
-# Competitive Intelligence Playbook
-
-## OSINT Sources for Competitor Tracking
-
-### Free, Reliable Sources
-
-**Company & Product:**
-- **Their website** — pricing page (archive.org for history), product changelog, careers page
-- **G2 / Capterra / Trustpilot** — customer reviews; filter by recency; read 1-star reviews carefully
-- **LinkedIn** — job postings signal roadmap; company page for headcount trend; employees for leaks
-- **GitHub** — open source activity; what they're building; engineering team size; tech stack
-- **Crunchbase / PitchBook** (free tier) — funding history, investors, team changes
-- **BuiltWith** — tech stack they use; signals about infrastructure maturity
-
-**Messaging & Positioning:**
-- **Facebook Ad Library** — see their current ad copy and creative; what messages they're testing
-- **Google Keyword Planner** — which keywords they're bidding on
-- **SEMrush / Ahrefs** (free trial or limited) — their organic keywords, backlink profile
-- **Wayback Machine** — homepage evolution over time; when positioning shifted
-- **Their blog** — content strategy reveals priorities and ICP assumptions
-
-**News & Events:**
-- **TechCrunch, VentureBeat** — funding announcements, major launches
-- **Twitter/X / LinkedIn** — CEO + founders; direct signals about strategy
-- **Podcast appearances** — founders talk more openly on podcasts than press releases
-- **Job descriptions** — "Senior Engineer - Payments" means they're building payments
-
-### Paid (Worth It for Tier-1 Competitors)
-- **G2 Buyer Intent** — which prospects are researching your competitor right now
-- **Bombora** — intent data for account-level research signals
-- **PitchBook** — funding, investors, valuation estimates
-- **Klue / Crayon / Kompyte** — dedicated CI platforms that aggregate automatically
-
-### Primary Research (Best Signal)
-- **Win/loss interviews** — the single highest-signal source (see below)
-- **Talk to churned customers** — why did they switch? To whom?
-- **Talk to their customers** — LinkedIn outreach; honest conversations
-- **Industry events** — competitor presentations reveal roadmap; talk to attendees
-- **Former employees** — LinkedIn; respectful outreach; no NDA violations
-
----
-
-## Competitive Battlecard Format
-
-A battlecard is a 1-page (or single screen) document for sales reps to reference before and during calls.
-
-**Design principles:**
-- Written for a rep with 2 minutes to prep, not a product manager
-- Action-oriented: tells reps what to SAY, not just what to know
-- Updated monthly at minimum; never more than 90 days old
-
-### Battlecard Structure
-
-```
-COMPETITOR: [Name]
-Last updated: [Date] | Owner: [Name]
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-
-THE 30-SECOND SUMMARY
-[One paragraph. Who they are, who they sell to, why they win.]
-
-THEIR STRENGTHS (know these — don't dismiss them)
-• [Strength 1] — what customers actually love about them
-• [Strength 2]
-• [Strength 3]
-
-THEIR REAL WEAKNESSES (from win/loss data, not assumptions)
-• [Weakness 1] — source: [customer quote / win/loss theme]
-• [Weakness 2]
-• [Weakness 3]
-
-OUR DIFFERENTIATED ADVANTAGES
-• [Advantage 1] — proof point: [metric/customer/case study]
-• [Advantage 2] — proof point:
-• [Advantage 3] — proof point:
-
-COMMON OBJECTIONS + RESPONSES
-"They have [feature] and you don't."
-→ [Response. Acknowledge, reframe, redirect.]
-
-"They're cheaper."
-→ [Response with ROI angle or TCO comparison.]
-
-"They're more established / bigger."
-→ [Response. Size isn't always advantage; use to your benefit.]
-
-TRAP-SETTING QUESTIONS (ask these early to shift the eval criteria)
-• "How important is [your differentiator] to your team?"
-• "Have you looked at [pain point they create]?"
-• "What happens to your workflow when [their known limitation occurs]?"
-
-WHEN WE WIN
-• [Segment or scenario where we almost always beat them]
-• [Use case where we're clearly stronger]
-
-WHEN WE LOSE (be honest)
-• [Scenario where they're genuinely better — don't fight these battles]
-• [Segment where they have structural advantages]
-
-DO NOT SAY
-• Don't claim [X] — it's not true and they'll call it out
-• Don't say [Y] — prospect will already know it and it sounds desperate
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-```
-
----
-
-## Win/Loss Analysis Framework
-
-### Why Most Companies Do This Wrong
-- They survey instead of interview (surveys get polite answers)
-- The AE conducts it (too emotionally invested; prospect won't be candid)
-- They do it 6 months after the decision (memory fades)
-- They look for confirmation of what they believe
-
-### The Right Process
-
-**Timing:** Within 30 days of deal closed/lost/churned.
-**Interviewer:** Customer success, product, or external researcher. Never the AE.
-**Duration:** 30 minutes (budget 45).
-**Incentive:** $100 gift card gets you 80% acceptance. Worth it.
-
-**Interview Guide:**
-
-*Opening:*
-"I'm [name] from [company]. I'm not in sales — I'm trying to understand what drove your decision so we can improve. There's nothing you can say that will change the outcome. I just want honest feedback."
-
-*Core questions:*
-1. "Can you walk me through your evaluation process from the beginning?"
-2. "Who were the key stakeholders involved in the decision?"
-3. "What were the 3 most important criteria you were evaluating against?"
-4. "Which vendors did you seriously consider?"
-5. "Where did [company] fall short of your expectations?" (For losses)
-   OR "What tipped the decision in [company]'s favor?" (For wins)
-6. "Was price a factor? How significant?"
-7. "What would have had to be different for you to choose [us / the other option]?"
-8. "Any advice for our team on how we handled the process?"
-
-**Data aggregation:**
-- Tag every response: [criterion], [competitor mentioned], [product gap], [sales process], [price], [trust/credibility]
-- Monthly rollup: top 5 win reasons, top 5 loss reasons, competitor win rate
-- Share with: CEO, CRO, CPO, CMO — not just sales
-
----
-
-## Competitive Positioning Map Construction
-
-A positioning map shows where you sit relative to competitors on 2 dimensions that BUYERS care about.
-
-### Step 1: Choose Your Axes
-- Pick dimensions that actually drive purchase decisions in your segment
-- At least one axis should be where you win
-- Avoid generic axes ("feature-rich vs. simple" tells you nothing)
-
-**Good axis pairs:**
-- Implementation time (days vs. months) × Customization depth
-- Price point × Enterprise readiness
-- Automation level × Human-in-the-loop control
-- Time-to-value × Total cost of ownership
-
-**Bad axes:**
-- Quality (too vague)
-- "Innovation" (unmeasurable)
-- Any axis where all competitors cluster in the same spot
-
-### Step 2: Place Competitors Objectively
-- Use customer quotes and win/loss data to justify placement
-- Don't place competitors where you WANT them — where they ACTUALLY are
-- If you're unsure, ask 5 customers to place them
-
-### Step 3: Find and Name Your White Space
-- Where is there a position no competitor holds?
-- Is that white space there because it's valuable (opportunity) or worthless (avoid)?
-- Can you credibly occupy it?
-
-### Step 4: Test Your Positioning
-- Show the map to 5 prospects: "Does this match your perception?"
-- Show it to 5 lost prospects: "Where would you place [the winner] and us?"
-- Adjust until map matches buyer reality, not internal perception
-
----
-
-## Intelligence Sharing Across Roles
-
-### What Each Role Needs and When
-
-**CRO (Sales):**
-- Needs: Battlecards, win rates by competitor, competitor objections + responses
-- Cadence: Updated battlecards monthly; triggered updates on major competitor moves
-- Format: 1-pager per competitor in CRM, linked from deal record
-
-**CMO (Marketing):**
-- Needs: Messaging shifts, new claims, ad spend signals, keyword battles
-- Cadence: Quarterly positioning review, triggered on major launches
-- Format: Positioning brief with recommended response to messaging shifts
-
-**CPO (Product):**
-- Needs: Feature gap analysis, competitor roadmap signals (job postings, changelog), what we lose to
-- Cadence: Monthly feature gap update, triggered on major launches
-- Format: Feature comparison matrix + gap prioritization recommendation
-
-**CTO (Engineering):**
-- Needs: Tech stack signals, infrastructure approaches, scale they've achieved
-- Cadence: Quarterly
-- Format: Technical comparison notes, relevant for architectural decisions
-
-**CEO:**
-- Needs: Summary of threat landscape, recommended responses, board-level narrative
-- Cadence: Monthly 1-pager + quarterly deep dive
-- Format: 1-page brief: who moved, what it means, what we do
-
-### The Single Source of Truth Rule
-All competitive intel in one place. Suggest:
-- Notion database per competitor: profile, battlecard, changelog, win/loss notes
-- Slack channel: `#competitive-intel` for real-time triggered alerts
-- Monthly digest email to leadership
-
-If it lives only in Slack, it disappears. If it lives only in a wiki that nobody reads, it doesn't matter. Combine both.
-
----
-
-## How to Track Without Obsessing
-
-**Set up the system, then let it run:**
-- Google Alerts for competitor names + CEO names
-- LinkedIn Saved Searches for their job postings
-- Klue/Crayon if budget allows (automated aggregation)
-- Monthly 60-minute competitive review meeting (not 4 hours)
-
-**What to do when competitor makes a big move:**
-1. Read the announcement objectively
-2. Talk to 3 customers: "Did you see this? What do you think?"
-3. Assess: does this change any buying criteria in your deals?
-4. If yes: update battlecard and positioning within 1 week
-5. If no: log it, move on
-
-**The test:** After reviewing a competitor move, do you feel urgency to ship something? If yes, you're reacting. The right feeling is "noted — let's see if customers care."

package/skills/jarvis/engineering-team/c-level-advisor/competitive-intel/templates/battlecard-template.md

@@ -1,99 +0,0 @@
-# Sales Battlecard Template
-
-**COMPETITOR:** [Name]
-**Last updated:** [YYYY-MM-DD] | **Owner:** [Name]
-**Win rate vs this competitor:** [X]% | **Deals tracked:** [N]
-
----
-
-## 30-Second Summary
-[Who they are. Who they target. Why they win. What they're known for. 3-4 sentences max.]
-
----
-
-## Their Strengths
-*Know these. Don't dismiss them. Prospects have already heard their pitch.*
-
-- **[Strength]:** [What customers genuinely love; source if available]
-- **[Strength]:** [Specific capability or trait]
-- **[Strength]:** [Brand, market position, or ecosystem advantage]
-
----
-
-## Their Real Weaknesses
-*From win/loss data only — not wishful thinking.*
-
-- **[Weakness]:** "[Customer quote]" — seen in [N] deals
-- **[Weakness]:** [Documented limitation with evidence]
-- **[Weakness]:** [Implementation, support, or pricing issue]
-
----
-
-## Our Differentiated Advantages
-*Must be real and provable. Each needs a proof point.*
-
-- **[Advantage]:** [Proof: metric / customer quote / case study]
-- **[Advantage]:** [Proof]
-- **[Advantage]:** [Proof]
-
----
-
-## Common Objections + Responses
-
-**"They have [feature X] and you don't."**
-> [Acknowledge. Reframe to your strength. Redirect to outcome.
-> "You're right that they have X. What we've found is that customers who care most about X tend to also care about [Y], where we're significantly stronger. Can I show you [specific example]?"]
-
-**"They're cheaper."**
-> [Don't fight on price. Reframe to TCO or ROI.
-> "They are lower in initial cost. Most customers find the total cost over 12 months is actually comparable when you factor in [implementation time / support costs / integrations]. Want to walk through that?"]
-
-**"They've been around longer / they're more established."**
-> [Reframe tenure as potential liability or irrelevance.
-> "Their longevity means they have a lot of technical debt and a big customer base that pulls their roadmap in every direction. Our customers tell us that's exactly why they chose us — we move faster and we're laser-focused on [their specific use case]."]
-
-**"[Competitor] is already used by [big customer they respect]."**
-> [Name-drop your wins in their segment.
-> "We work with [comparable logo]. Want me to connect you with their [role] to ask how they made the decision?"]
-
----
-
-## Trap-Setting Questions
-*Ask early in discovery to establish criteria that favor you.*
-
-- "How important is [your key differentiator] to your workflow?"
-- "What happens when [their known limitation] occurs? Has that been an issue before?"
-- "How long does your team typically take to onboard a new tool?"
-- "Who manages the integration work — do you have dedicated engineering resources for that?"
-- "What does your current vendor do when you need support?"
-
----
-
-## When We Win
-- [Scenario or segment where we consistently beat them]
-- [Use case that plays to our strengths]
-- [Buyer profile that prefers us]
-
-## When We Lose (Be Honest)
-- [Scenario where they genuinely win — don't fight here]
-- [Segment where their strengths matter more than ours]
-
----
-
-## Do NOT Say
-- ❌ Don't claim [X] — it's not accurate and they'll check
-- ❌ Don't attack [Y] — it backfires and makes us look insecure
-- ❌ Don't say "we're better" without specifics — be concrete
-
----
-
-## Recent Intel
-*Last 90 days only. Older than 90 days: archive.*
-
-- [Date]: [What happened — funding, product launch, pricing change, key hire]
-- [Date]: [Customer feedback from win/loss interview]
-- [Date]: [Any notable market move]
-
----
-
-*Battlecards are only useful if current. If this is >90 days old, flag to [owner] for update.*

package/skills/jarvis/engineering-team/c-level-advisor/context-engine/SKILL.md

@@ -1,134 +0,0 @@
----
-name: "context-engine"
-description: "Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context during conversations, and enforces privacy/anonymization rules before external API calls."
-license: MIT
-metadata:
-  version: 1.0.0
-  author: Alireza Rezvani
-  category: c-level
-  domain: orchestration
-  updated: 2026-03-05
-  frameworks: context-loading, anonymization, context-enrichment
----
-
-# Company Context Engine
-
-The memory layer for C-suite advisors. Every advisor skill loads this first. Context is what turns generic advice into specific insight.
-
-## Keywords
-company context, context loading, context engine, company profile, advisor context, stale context, context refresh, privacy, anonymization
-
----
-
-## Load Protocol (Run at Start of Every C-Suite Session)
-
-**Step 1 — Check for context file:** `~/.claude/company-context.md`
-- Exists → proceed to Step 2
-- Missing → prompt: *"Run /cs:setup to build your company context — it makes every advisor conversation significantly more useful."*
-
-**Step 2 — Check staleness:** Read `Last updated` field.
-- **< 90 days:** Load and proceed.
-- **≥ 90 days:** Prompt: *"Your context is [N] days old. Quick 15-min refresh (/cs:update), or continue with what I have?"*
-  - If continue: load with `[STALE — last updated DATE]` noted internally.
-
-**Step 3 — Parse into working memory.** Always active:
-- Company stage (pre-PMF / scaling / optimizing)
-- Founder archetype (product / sales / technical / operator)
-- Current #1 challenge
-- Runway (as risk signal — never share externally)
-- Team size
-- Unfair advantage
-- 12-month target
-
----
-
-## Context Quality Signals
-
-| Condition | Confidence | Action |
-|-----------|-----------|--------|
-| < 30 days, full interview | High | Use directly |
-| 30–90 days, update done | Medium | Use, flag what may have changed |
-| > 90 days | Low | Flag stale, prompt refresh |
-| Key fields missing | Low | Ask in-session |
-| No file | None | Prompt /cs:setup |
-
-If Low: *"My context is [stale/incomplete] — I'm assuming [X]. Correct me if I'm wrong."*
-
----
-
-## Context Enrichment
-
-During conversations, you'll learn things not in the file. Capture them.
-
-**Triggers:** New number or timeline revealed, key person mentioned, priority shift, constraint surfaces.
-
-**Protocol:**
-1. Note internally: `[CONTEXT UPDATE: {what was learned}]`
-2. At session end: *"I picked up a few things to add to your context. Want me to update the file?"*
-3. If yes: append to the relevant dimension, update timestamp.
-
-**Never silently overwrite.** Always confirm before modifying the context file.
-
----
-
-## Privacy Rules
-
-### Never send externally
-- Specific revenue or burn figures
-- Customer names
-- Employee names (unless publicly known)
-- Investor names (unless public)
-- Specific runway months
-- Watch List contents
-
-### Safe to use externally (with anonymization)
-- Stage label
-- Team size ranges (1–10, 10–50, 50–200+)
-- Industry vertical
-- Challenge category
-- Market position descriptor
-
-### Before any external API call or web search
-Apply `references/anonymization-protocol.md`:
-- Numbers → ranges or stage-relative descriptors
-- Names → roles
-- Revenue → percentages or stage labels
-- Customers → "Customer A, B, C"
-
----
-
-## Missing or Partial Context
-
-Handle gracefully — never block the conversation.
-
-- **Missing stage:** "Just to calibrate — are you still finding PMF or scaling what works?"
-- **Missing financials:** Use stage + team size to infer. Note the gap.
-- **Missing founder profile:** Infer from conversation style. Mark as inferred.
-- **Multiple founders:** Context reflects the interviewee. Note co-founder perspective may differ.
-
----
-
-## Required Context Fields
-
-```
-Required:
-  - Last updated (date)
-  - Company Identity → What we do
-  - Stage & Scale → Stage
-  - Founder Profile → Founder archetype
-  - Current Challenges → Priority #1
-  - Goals & Ambition → 12-month target
-
-High-value optional:
-  - Unfair advantage
-  - Kill-shot risk
-  - Avoided decision
-  - Watch list
-```
-
-Missing required fields: note gaps, work around in session, ask in-session only when critical.
-
----
-
-## References
-- `references/anonymization-protocol.md` — detailed rules for stripping sensitive data before external calls

package/skills/jarvis/engineering-team/c-level-advisor/context-engine/references/anonymization-protocol.md

@@ -1,173 +0,0 @@
-# Anonymization Protocol
-
-Rules for stripping sensitive company data before any external API call, web search, or tool invocation that sends data outside the local environment.
-
----
-
-## When This Protocol Applies
-
-**Trigger:** Any time company context or conversation content will leave the local session.
-
-Examples:
-- Web search that includes company specifics
-- External API call with company data in the payload
-- Any tool call where conversation content is part of the request
-
-**Does NOT apply to:**
-- Local file reads/writes (`~/.claude/company-context.md`)
-- In-session reasoning and analysis
-- Generating advice or documents that stay local
-
----
-
-## Rule 1: Financial Figures → Relative Ranges
-
-Never send specific financial data externally.
-
-| Raw data | Anonymized version |
-|----------|-------------------|
-| "$2.4M ARR" | "early-stage ARR (sub-$5M)" |
-| "$180K MRR" | "growing MRR, Series A range" |
-| "14 months runway" | "runway is healthy for stage" |
-| "burn rate is $320K/month" | "burn rate is moderate for stage" |
-| "raised $8M Series A" | "Series A company" |
-| "customer LTV is $4,200" | "LTV is above industry average for segment" |
-| "CAC is $680" | "CAC is in a sustainable range" |
-
-**Rule:** No dollar amounts. No month counts for runway. Use stage-relative descriptors.
-
----
-
-## Rule 2: Customer Names → Anonymized Labels
-
-Never send customer or client names externally.
-
-| Raw data | Anonymized version |
-|----------|-------------------|
-| "Acme Corp is our biggest customer" | "Customer A (largest account)" |
-| "we're working with NHS England" | "a large public-sector customer" |
-| "BMW, Volkswagen, and Stellantis" | "three major automotive OEMs" |
-| "10 enterprise customers including..." | "10 enterprise customers" |
-
-**Rule:** Use "Customer A/B/C" for named accounts, or describe by segment without naming.
-
----
-
-## Rule 3: Revenue Figures → Percentage Changes or Stage Descriptors
-
-Revenue trajectory is safer than absolute numbers.
-
-| Raw data | Anonymized version |
-|----------|-------------------|
-| "growing from $1M to $2M ARR" | "2x revenue growth year-over-year" |
-| "revenue dropped from $500K to $430K" | "revenue declined ~15% in the period" |
-| "hit $10M ARR last quarter" | "crossed a significant ARR milestone" |
-| "doing $50K MRR" | "pre-Series A revenue, strong growth trajectory" |
-
-**Rule:** Percentages and directional signals (growing / declining / flat) are safe. Absolutes are not.
-
----
-
-## Rule 4: Employee Names → Roles Only
-
-Never send individual names externally.
-
-| Raw data | Anonymized version |
-|----------|-------------------|
-| "Our CTO, Sarah Chen, is struggling" | "our CTO is struggling with the transition" |
-| "James is the best performer on the team" | "our strongest performer is in the engineering lead role" |
-| "we're about to let go of Michael" | "we're about to make a leadership change" |
-| "the founding team is me, Alex, and Priya" | "a three-person founding team" |
-
-**Exception:** Publicly known executives (CEO of a public company, named in press releases) can be referenced by name. If in doubt, use role.
-
----
-
-## Rule 5: Investor Names → Generic Descriptors
-
-| Raw data | Anonymized version |
-|----------|-------------------|
-| "Sequoia led our round" | "a top-tier VC led our round" |
-| "our lead investor is pushing for an exit" | "pressure from investors toward exit" |
-| "Y Combinator alumni" | "accelerator alumni" |
-
-**Exception:** YC, Techstars, and similar well-known accelerators are commonly referenced and safe if the founder has publicly disclosed. When in doubt, omit.
-
----
-
-## Rule 6: Location → Country or Region
-
-| Raw data | Anonymized version |
-|----------|-------------------|
-| "Berlin-based startup" | "European startup" |
-| "we're in San Francisco" | "US-based startup" |
-| "expanding to Munich and Vienna" | "expanding in the DACH region" |
-
-**Exception:** Location is less sensitive than financials. Use judgment — if it's on their website, it's fine.
-
----
-
-## Anonymization Decision Tree
-
-```
-Before sending data externally:
-
-1. Does it include a specific dollar amount?
-   → YES: Replace with range or relative descriptor
-   
-2. Does it include a person's name?
-   → YES: Replace with role only (unless publicly known)
-   
-3. Does it include a company or customer name?
-   → YES: Replace with "Customer A" or segment descriptor
-   
-4. Does it include specific headcount or runway months?
-   → YES: Replace with range (1–10, 10–50) or "healthy/tight/critical"
-   
-5. Does it include proprietary data, roadmap, or unreleased product info?
-   → YES: Do not include. Reference only generically ("product expansion planned")
-   
-6. Is it publicly available information?
-   → YES: Safe to send as-is
-```
-
----
-
-## Required vs Optional Anonymization
-
-### Required (always strip before external calls)
-- Revenue figures (absolute)
-- Burn rate (absolute)
-- Runway (specific months)
-- Customer names
-- Employee names
-- Investor names (unless public)
-- Funding amounts (unless public)
-
-### Optional (use judgment based on sensitivity)
-- Industry vertical (usually fine)
-- Company stage (usually fine)
-- Team size ranges (usually fine)
-- Geographic region (usually fine)
-- General challenge category (usually fine)
-
----
-
-## What to Do If You're Unsure
-
-Default to stricter anonymization. The cost of over-anonymizing is slightly less useful external results. The cost of under-anonymizing is a privacy breach.
-
-When in doubt: **remove it**.
-
----
-
-## Audit Log (Internal Only)
-
-When running external calls with company context, note internally:
-```
-[EXTERNAL CALL: {tool/API used}]
-[ANONYMIZED: {fields stripped}]
-[RETAINED: {fields kept and why}]
-```
-
-This is for internal reasoning only — never included in output to the founder.