interface:
  display_name: "Suede Competitor Profiling"
  short_description: "Research competitors and turn public evidence into profiles"
  default_prompt: "Use $suede-competitor-profiling on [target]. The user wants competitor research, a competitive landscape, or structured profiles built from competitor URLs. Work through positioning, pricing, messaging, and where they are weak, ground every recommendation in evidence the user can check, and return the decisions, the reasoning, and what to measure next."
policy:
  allow_implicit_invocation: true

{
  "skill_name": "suede-competitor-profiling",
  "evals": [
    {
      "id": 1,
      "prompt": "Profile these three competitors for us: https://competitor1.com, https://competitor2.com, https://competitor3.com. We need this for sales enablement and to find positioning gaps.",
      "expected_output": "Should check for product-marketing.md first, then inspect the tools actually available in the current session rather than assuming Firecrawl or DataForSEO exists. Should run the full research process: Phase 1 public-site evidence through an available authorized fetch/map capability or browser/manual fallback, optional Phase 2 SEO and market data through an available authorized provider or user export, and Phase 3 synthesis. Should save raw data to competitor-profiles/raw/<slug>/<YYYY-MM-DD>/ with scrapes/, seo/, reviews/ subfolders before synthesizing. Should produce one markdown file per competitor following the profile template (At a Glance, Positioning & Messaging, Product & Features, Pricing, Customers & Social Proof, SEO & Content Strategy, Strengths & Weaknesses, Competitive Implications). Should produce a _summary.md after individual profiles with comparison table, positioning map, key takeaways, gaps and opportunities. Should parallelize independent reads only when supported and use consistent provider metrics across all three for comparability.",
      "assertions": [
        "Checks for product-marketing.md",
        "Checks current tool availability and uses manual fallback when needed",
        "Runs public evidence, optional quantitative data, and synthesis phases",
        "Saves raw data to competitor-profiles/raw/ with date subfolder",
        "Produces individual profile per competitor",
        "Produces _summary.md after individual profiles",
        "Uses consistent metrics across competitors",
        "Parallelizes independent reads only when supported"
      ],
      "files": []
    },
    {
      "id": 2,
      "prompt": "We have 12 competitors. Profile all of them.",
      "expected_output": "Should recommend prioritizing rather than profiling all 12. Should suggest profiling the top 5 first based on domain overlap or market similarity (handling-multiple-competitors guidance). Should default to quick scan mode for a list this size, not deep profile. Should explain the difference: quick scan covers homepage + pricing plus one consistent provider overview and ranked-keyword summary when an authorized source or user export is available; deep profile adds reviews, technology signals, and backlink detail when available. Should offer deep profile only if user requests or for 3 or fewer competitors. Should ask which competitors are highest priority if the list should be narrowed.",
      "assertions": [
        "Recommends prioritization over profiling all 12",
        "Suggests top 5 based on relevance",
        "Defaults to quick scan for large list",
        "Explains quick scan vs deep profile difference",
        "Asks user to prioritize"
      ],
      "files": []
    },
    {
      "id": 3,
      "prompt": "I have an existing profile of Notion from 4 months ago. Should I update it or start fresh?",
      "expected_output": "Should explain profile updating process from the Updating Profiles section. Should recommend updating rather than starting fresh — preserves history and enables diffing. Should explain what to refresh: pricing page first (most volatile), SEO metrics only through the same currently available provider and matching parameters, and changelog evidence for product changes. Should update the Generated date. Should add a Change Log section at the bottom noting what changed since last profile. Should save new raw data to a new <YYYY-MM-DD> folder rather than overwriting prior data.",
      "assertions": [
        "Recommends updating over starting fresh",
        "Lists what to refresh and keeps SEO provider parameters consistent",
        "Mentions adding Change Log section",
        "Says to save raw data to new date folder",
        "Says never overwrite prior date's data"
      ],
      "files": []
    },
    {
      "id": 4,
      "prompt": "What pages should I scrape for a competitor profile?",
      "expected_output": "Should list the prioritized page types from Phase 1: homepage, pricing page, features/product pages, about/company page, blog (top-level for content strategy signals), customers/case studies page, integrations page, changelog/what's new (if exists). Should explain what to extract from each: homepage (headline, value prop, primary CTA, social proof, target audience signals), pricing (tiers, prices, feature breakdown, billing options, free tier/trial details), features (categories, key capabilities, how they describe each feature), about (founding story, team size, funding, mission, HQ), customers (named customers, logos, industries, case study themes), integrations (count, key integrations, categories), changelog (release velocity, recent focus areas, product direction signals). Should mention optional review scraping (G2, Capterra, Product Hunt, TrustRadius).",
      "assertions": [
        "Lists all key page types in priority order",
        "Specifies what to extract from each page type",
        "Includes changelog as product direction signal",
        "Mentions optional review scraping",
        "Uses an available map/fetch capability or browser/manual fallback"
      ],
      "files": []
    },
    {
      "id": 5,
      "prompt": "I want a profile but I don't care about SEO data — just pricing, positioning, and customer logos. Can you skip the DataForSEO calls?",
      "expected_output": "Should accept the scoped request and skip Phase 2. Should run Phase 1 through an available authorized page-fetch capability or browser/manual capture of homepage, pricing, and customer pages, then Phase 3 synthesis. Should explain that without SEO data, the profile won't include provider domain metrics, organic traffic estimates, ranked keywords, referring domains, or top organic pages — but the positioning, pricing, and customer sections will be complete. Should produce an abbreviated profile flagging the SEO section as 'not collected per user request' rather than leaving placeholders. Should still save raw page evidence to disk for reuse.",
      "assertions": [
        "Skips optional quantitative SEO data as requested",
        "Runs Phase 1 and Phase 3",
        "Explains what's missing without SEO data",
        "Flags SEO section as skipped, not blank",
        "Still saves raw data"
      ],
      "files": []
    },
    {
      "id": 6,
      "prompt": "Should I trust the customer logo wall on the competitor's homepage as evidence of who their customers are?",
      "expected_output": "Should apply the 'Facts Over Opinions' and 'Honest Assessment' principles. Should explain that customer logos are a positioning claim, not necessarily an accurate customer breakdown — companies often show their best-known logos regardless of share of revenue. Should recommend cross-referencing: check case studies for actual usage details, search for press releases naming customers, look at customer reviews on G2/Capterra/TrustRadius for company name signals, check their LinkedIn for posts about customers. Should note: if they claim '10,000 customers' but have weak traffic/backlink profile, the claim should be flagged in the profile. Should distinguish between named customers (verifiable claims) and 'industries served' (positioning statement). Always include the date the data was pulled.",
      "assertions": [
        "Treats logos as positioning claim, not customer breakdown",
        "Recommends cross-referencing case studies and reviews",
        "Mentions checking traffic/backlink profile against claim scale",
        "Distinguishes verifiable named customers from claims",
        "Notes including date pulled"
      ],
      "files": []
    }
  ]
}

# Profile Templates

Ready-to-use templates for competitor profile sections and the summary document.

## Contents
- Evidence Markers (read first — every template below uses them)
- Deep Profile Template
- Quick Scan Template
- Summary Comparison Table
- Positioning Map
- Competitive SWOT
- Profile Update Changelog

---

## Evidence Markers

Every filled field in every template below carries one of four markers, so a
reader can tell at a glance what is observed and what is reasoned. This is the
mechanism behind "fact, inference, and unknowns kept separate" — without it a
profile reads as uniformly authoritative regardless of where each line came from.

| Marker | Use for | Example |
|--------|---------|---------|
| `[fact: url, date]` | Anything read directly off a public page or review source | `$49/mo [fact: acme.com/pricing, 2026-03-04]` |
| `[provider estimate: provider, market, device, date]` | Any third-party metric — traffic, authority, keyword counts | `41k/mo [provider estimate: DataForSEO, US, desktop, 2026-03-04]` |
| `[inference]` | Anything reasoned from evidence rather than stated | `Mid-market ops teams [inference]` |
| `[unknown]` | Looked for, not found | `Team size: [unknown]` |

Two terminal states are legitimate and must not be filled with a guess:
`[unknown]` (searched, not found) and `not collected` (out of scope for this
depth level, or no authorized provider available). Never substitute an estimate
for either.

---

## Deep Profile Template

The full profile for a deep-profile run. One markdown file per competitor at
`competitor-profiles/[competitor-name].md`.

```markdown
# [Competitor Name] — Competitor Profile

**URL**: [website]
**Generated**: [date]
**Depth**: [quick scan / deep profile]
**Evidence markers**: [fact: url, date] · [provider estimate: provider, market, device, date] · [inference] · [unknown]

---

## At a Glance

| Metric | Value |
|--------|-------|
| Tagline | [value] [fact: url, date] |
| Founded | [value] [fact: url, date — or unknown] |
| Headquarters | [value] [fact: url, date — or unknown] |
| Team size | [value] [fact: url, date — or inference — or unknown] |
| Funding | [value] [fact: url, date — or unknown] |
| Provider domain metric | [value] [provider estimate: provider, market, device, date — or not collected] |
| Est. organic traffic | [monthly] [provider estimate: provider, market, device, date — or not collected] |
| Referring domains | [count] [provider estimate: provider, date — or not collected] |
| Organic keywords | [count] [provider estimate: provider, market, date — or not collected] |

---

## Positioning & Messaging

**Primary value proposition**: [headline + subheadline] [fact: homepage url, date]

**Target audience**: [who they're speaking to] [inference — from the copy cited above]

**Positioning angle**: [e.g. "simplicity-first," "enterprise-grade," "all-in-one"] [inference]

**Key messaging themes**:
- [theme 1] [fact: source page url, date]
- [theme 2] [fact: source page url, date]
- [theme 3] [fact: source page url, date]

---

## Product & Features

### Core capabilities
- [capability 1] — [description] [fact: url, date]
- [capability 2] — [description] [fact: url, date]
- ...

### Notable differentiators
- [what they emphasize as unique] [fact: url, date]

### Integrations
- [count] [fact: url, date — or unknown] integrations
- Key: [top 5-10] [fact: url, date]

### Product direction signals
- [read off changelog / recent releases] [inference — cite the changelog url and date]

---

## Pricing

| Tier | Price | Key Inclusions |
|------|-------|---------------|
| [Free/Starter] | [price] [fact: pricing url, date] | [what's included] |
| [Pro/Growth] | [price] [fact: pricing url, date] | [what's included] |
| [Enterprise] | [price] [fact: pricing url, date — or unknown if "contact us"] | [what's included] |

**Billing**: [monthly/annual, annual discount] [fact: pricing url, date]
**Free trial**: [yes/no, duration] [fact: pricing url, date]
**Notable**: [pricing quirks — per-seat, usage-based, hidden costs] [fact or inference]

---

## Customers & Social Proof

**Named customers**: [notable logos] [fact: url, date]
**Industries**: [primary industries served] [inference — from the logos and case studies cited]
**Case study themes**: [what outcomes they highlight] [fact: url, date]
**Review ratings**:
- G2: [rating] ([count] reviews) [fact: g2 url, date — or not collected]
- Capterra: [rating] ([count] reviews) [fact: capterra url, date — or not collected]

---

## SEO & Content Strategy

**Organic strength**:
- Estimated monthly organic traffic: [number] [provider estimate: provider, market, device, date — or not collected]
- Organic keywords (top 10): [count] [provider estimate: provider, market, date — or not collected]
- Organic traffic value: $[estimated] [provider estimate: provider, market, date — or not collected]

**Top organic pages** (by estimated traffic):
1. [page URL] — [keyword] — [est. traffic] [provider estimate: provider, date]
2. [page URL] — [keyword] — [est. traffic] [provider estimate: provider, date]
3. [page URL] — [keyword] — [est. traffic] [provider estimate: provider, date]

**Content strategy signals**:
- Blog post frequency: [estimate] [inference — from the blog index url and date]
- Primary content types: [guides, comparisons, templates, etc.] [fact: blog url, date]
- Content focus areas: [topics they invest in] [inference]

**Backlink profile**:
- Referring domains: [count] [provider estimate: provider, date — or not collected]
- Top referring sites: [list 5] [provider estimate: provider, date — or not collected]
- Link acquisition pattern: [growing/stable/declining] [inference — or not collected]

---

## Strengths & Weaknesses

### Strengths
- [strength 1] [fact: url, date — or inference from a cited capture]
- [strength 2] [fact: url, date — or inference from a cited capture]
- [strength 3] [fact: url, date — or inference from a cited capture]

### Weaknesses
- [weakness 1] [fact: url, date — or inference from a cited capture]
- [weakness 2] [fact: url, date — or inference from a cited capture]
- [weakness 3] [fact: url, date — or inference from a cited capture]

---

## Competitive Implications for [Your Product]

**Where they're strong vs. us**: [areas where this competitor has an advantage] [inference]

**Where we're strong vs. them**: [areas where you have an advantage] [inference]

**Opportunities**: [gaps in their offering or positioning we can exploit] [inference]

**Threats**: [areas where they're improving or gaining ground] [inference]

---

## Raw Data Sources

Built from `competitor-profiles/raw/[competitor-slug]/[YYYY-MM-DD]/`.

- Homepage scraped: [date]
- Pricing page scraped: [date]
- SEO data pulled: [date, provider, market, device]
- Review data pulled: [date, sources]
```

---

## Quick Scan Template

Abbreviated profile for when speed matters more than depth. Same evidence
markers as the deep profile, so the two stay comparable.

```markdown
# [Competitor Name] — Quick Profile

**URL**: [website]
**Generated**: [date]
**Evidence markers**: [fact: url, date] · [provider estimate: provider, market, device, date] · [inference] · [unknown]

## At a Glance

| Metric | Value |
|--------|-------|
| Tagline | [value] [fact: homepage url, date] |
| Target audience | [value] [inference — from the copy cited above] |
| Pricing starts at | [lowest paid tier] [fact: pricing url, date] |
| Free tier/trial | [yes/no + details] [fact: pricing url, date] |
| Provider domain metric | [value] [provider estimate: provider, market, device, date — or not collected] |
| Est. organic traffic | [monthly] [provider estimate: provider, market, device, date — or not collected] |
| Organic keywords (top 10) | [count] [provider estimate: provider, market, date — or not collected] |
| Referring domains | [count] [provider estimate: provider, date — or not collected] |

## Positioning

**Headline**: "[exact homepage headline]" [fact: homepage url, date]
**Subheadline**: "[exact subheadline]" [fact: homepage url, date]
**Positioning angle**: [1-2 sentence summary of how they position] [inference]

## Pricing Summary

| Tier | Price | Notable Inclusions |
|------|-------|-------------------|
| [tier] | [price] [fact: pricing url, date] | [key items] |
| [tier] | [price] [fact: pricing url, date] | [key items] |

## Key Takeaway

[2-3 sentences: what makes this competitor notable, where they're strong, where they're weak]
```

---

## Summary Comparison Table

Use after profiling all competitors to create a side-by-side view.

```markdown
# Competitive Landscape Summary

**Generated**: [date]
**Your product**: [name]
**Competitors profiled**: [count]

## Side-by-Side Comparison

| Dimension | [Your Product] | [Competitor 1] | [Competitor 2] | [Competitor 3] |
|-----------|---------------|----------------|----------------|----------------|
| **Tagline** | [yours] | [theirs] | [theirs] | [theirs] |
| **Target audience** | [yours] | [theirs] | [theirs] | [theirs] |
| **Positioning** | [angle] | [angle] | [angle] | [angle] |
| **Starting price** | $[X]/mo | $[X]/mo | $[X]/mo | $[X]/mo |
| **Free tier** | [yes/no] | [yes/no] | [yes/no] | [yes/no] |
| **Domain rank** | [score] | [score] | [score] | [score] |
| **Est. organic traffic** | [number] | [number] | [number] | [number] |
| **Referring domains** | [count] | [count] | [count] | [count] |
| **G2 rating** | [score] | [score] | [score] | [score] |
| **Key strength** | [one-liner] | [one-liner] | [one-liner] | [one-liner] |
| **Key weakness** | [one-liner] | [one-liner] | [one-liner] | [one-liner] |
```

---

## Positioning Map

Visual representation of where competitors sit along two key dimensions. Choose the two axes most relevant to your market.

### Common Axis Pairs

| Market Type | X-Axis | Y-Axis |
|-------------|--------|--------|
| SaaS tools | Simple → Complex | Cheap → Expensive |
| Developer tools | Low-code → Code-first | Individual → Team |
| B2B platforms | SMB-focused → Enterprise-focused | Point solution → Platform |
| Content tools | Template-driven → Custom | Self-serve → Managed |

### Format

```markdown
## Positioning Map

**Axes**: [X-axis label] vs. [Y-axis label]

                    [Y-axis high label]
                           │
                           │
          [Competitor A]   │    [Competitor B]
                           │
    ───────────────────────┼───────────────────────
    [X-axis low]           │           [X-axis high]
                           │
          [Your Product]   │    [Competitor C]
                           │
                    [Y-axis low label]

### Interpretation
- [1-2 sentences about what the map reveals]
- [where the whitespace / opportunity is]
```

---

## Competitive SWOT

Per-competitor SWOT relative to your product.

```markdown
## SWOT: [Competitor] vs. [Your Product]

### Strengths (theirs vs. ours)
- [Where they genuinely outperform us — be honest]

### Weaknesses (theirs vs. ours)
- [Where they fall short compared to us — with evidence]

### Opportunities (for us)
- [Gaps in their offering we can exploit]
- [Segments they're ignoring]
- [Messaging angles they're missing]

### Threats (from them)
- [Areas where they're improving fast]
- [Features they're building that overlap with us]
- [Market moves that could shift perception]
```

---

## Profile Update Changelog

Append to the bottom of any profile when updating it.

```markdown
---

## Change Log

| Date | What Changed | Source |
|------|-------------|--------|
| [date] | Pricing increased from $X to $Y | Pricing page recapture |
| [date] | Launched [feature] | Changelog recapture |
| [date] | Provider domain metric changed from X to Y | Same-provider refresh with matching market and device |
| [date] | Added [integration] | Integrations page recapture |
```

# Conditional Research Access for Competitor Profiling

This reference maps research needs to capabilities. It does not declare that
Firecrawl, DataForSEO, a browser, a search provider, or any other connector is
installed, connected, authorized, or callable.

## Contents
- Availability and Authorization Gate
- Public-Site Evidence
- Optional SEO and Market Metrics
- Execution Order
- Failure and Fallback Rules

## Availability and Authorization Gate

Before selecting a tool:

1. Inspect the tools actually exposed in the current session.
2. For a relevant connector, confirm the intended account or workspace,
   authorization, current schema, pricing or quota impact, and read-only scope.
3. Use the exact callable name and arguments returned by current tool
   discovery. Do not construct calls from the example names in this file.
4. If no appropriate tool is available, use the browser-neutral/manual
   fallback below or analyze a user-supplied export.
5. Never bypass login, paywalls, bot controls, site terms, privacy controls, or
   rate limits. Platform-specific access requires a connected platform and the
   user's authorization.

## Public-Site Evidence

### Map or discover URLs

**Need:** Find homepage, pricing, product, about, customer, integration, blog,
and changelog URLs.

**Connected-tool route:** Use a currently exposed site-map or crawl capability
after reading its schema. Some Firecrawl connections expose names such as
`firecrawl_map`; treat that as a discovery hint, not a guaranteed command.

**Manual fallback:** Open the public homepage, follow primary navigation,
inspect a public sitemap when accessible, or use ordinary public search. Record
the exact URL and access date for every page selected.

### Capture one page

**Need:** Preserve visible positioning, pricing, proof, and product text.

**Connected-tool route:** Use a currently exposed single-page fetch, scrape, or
extract capability. Some Firecrawl connections expose names such as
`firecrawl_scrape` or `firecrawl_extract`; first confirm that exact tool and its
schema are available.

**Manual fallback:** Open the public page and save the relevant visible text or
notes as markdown. Record omitted dynamic sections and access limitations.

### Find reviews or offsite mentions

**Need:** Locate current review pages, launch discussions, press, and other
public corroboration.

**Connected-tool route:** Use a current authorized search capability if one is
exposed. A name such as `firecrawl_search` may exist in some installations but
must be discovered before use.

**Manual fallback:** Use ordinary public search and open the result directly.
Do not scrape account-only review content without connected, authorized access.

## Optional SEO and Market Metrics

Quantitative SEO data is optional. Provider metrics are estimates, not first-
party traffic truth. Record provider, market, device, database, access date,
date window, and metric definition so competitors remain comparable.

If a DataForSEO or similar connector is currently available and authorized,
discover its exact callable names and schemas at runtime. Common capability
labels in some deployments include:

| Research need | Possible capability label | Capture |
|---------------|---------------------------|---------|
| Domain/backlink overview | `backlinks_summary` | Provider rank, backlinks, referring domains, spam indicator |
| Referring-domain detail | `backlinks_referring_domains` | Referring domain, provider rank, link count |
| Organic domain overview | `dataforseo_labs_google_domain_rank_overview` | Ranked-keyword count, estimated traffic, estimated value |
| Ranked keywords | `dataforseo_labs_google_ranked_keywords` | Keyword, position, volume, ranking URL |
| Site keyword ideas | `dataforseo_labs_google_keywords_for_site` | Keyword, volume, competition, CPC estimate |
| Organic competitors | `dataforseo_labs_google_competitors_domain` | Domain, overlap, position metrics |
| Domain intersection | `dataforseo_labs_google_domain_intersection` | Shared keyword and each domain's position |
| Relevant pages | `dataforseo_labs_google_relevant_pages` | Page and provider-estimated traffic/keywords |
| Technology detection | `domain_analytics_technologies_domain_technologies` | Observed technologies by category |
| Individual backlinks | `backlinks_backlinks` | Source, target, anchor, provider rank |
| Bulk rank comparison | `backlinks_bulk_ranks` | Same provider rank across the submitted domains |

These labels are not an API contract. If the available provider uses different
names or fields, use the current discovered schema. If no provider is
available, accept a current CSV/JSON export from the user or mark the relevant
section `not collected`.

## Execution Order

### Quick scan

1. Discover URLs with an available mapping capability or manual navigation.
2. Capture homepage and pricing evidence with an authorized fetch or manually.
3. If a quantitative provider or user export is available, collect one
   consistent domain overview and backlink summary.
4. Save raw evidence, then synthesize an abbreviated profile.

### Deep profile

1. Capture homepage, pricing, feature, about, customer, integration, and
   changelog evidence.
2. Collect the same available SEO metrics for each competitor; skip the entire
   comparison dimension when consistent inputs are unavailable.
3. Add public reviews and offsite corroboration through an authorized search
   capability or manual browsing.
4. Save every raw response, export, or manual capture with source and date.
5. Synthesize only after separating verified facts, provider estimates,
   inferences, and unknowns.

### Multiple competitors

Parallelize independent reads only when the current tool supports concurrency
and its quota allows it. Use identical sources and parameters across
competitors. Build individual profiles before the cross-competitor summary.

## Failure and Fallback Rules

| Issue | Action |
|-------|--------|
| Named example tool is absent | Do not call it; use another exposed capability or the manual fallback |
| Page is blocked or requires login | Record the limitation; do not bypass access controls |
| JavaScript page does not render in a fetch | Use an available browser when authorized, or capture only verifiable public evidence manually |
| Pricing URL is not obvious | Inspect navigation, public sitemap, and likely public paths; report if still unverified |
| SEO provider returns no data | Record `insufficient provider data`; do not convert absence into zero |
| Providers use incompatible metrics | Do not compare the values directly; choose one consistent provider or mark unavailable |
| Rate or quota limit is reached | Stop additional calls, name the limit, prioritize the smallest useful evidence set |
| Review access is restricted | Use another public source or omit the review dimension with a limitation note |