Competitor research
Research substrate
When to run
Invoke when the user asks for: competitor analysis for X, battlecard research for X, competitive landscape for [market], compare X vs Y, what's [competitor] doing?. Do NOT invoke for: qualifying a company, product messaging only, researching the user's own company, or single-feature questions (answer directly).
Three run modes — pick by cadence and depth needed:
- First run (~90 min) —
/competitor-research [competitor]. New competitor, no existing dossier. Phases 1–3 (or 1–4 for aggregate).
- Quick scan (~30 min, weekly) —
/competitor-research --quick [competitor] or /loop 1w. Refreshes fast-moving data only (news, Clay, G2, internal sources). Updates "Recent changes" header — sections without changes stay untouched.
- Deep refresh (~90 min, monthly) —
/competitor-research --refresh [competitor] or /loop 1M. Full 13-dimension cycle with TrustPilot monitor and Phase 4 aggregate (if 2+ competitors refreshed this cycle).
Full cadence + refresh discipline → the premium reference. Visual phase map → the premium reference.
The Iron Law: no data point without source. Every claim cites a URL + access date or is marked [Not available]. Estimates need explicit confidence + reasoning. "Fast + wrong = useless."
Inputs
Required:
competitor name — exact company/product name (e.g., Linear, Lovable).
website URL — competitor's site (e.g., linear.app).
Recommended (improve quality):
client context — current positioning sharpens the comparative angle.
specific questions — focus areas (e.g., "deep dive on their pricing model and outbound motion").
research mode — single deep dive (default) or comparison matrix (3–6 competitors).
If competitor name is ambiguous (e.g., "Cursor", "Base", "Linear"), confirm with the user before starting. If website URL is missing, ask — don't guess.
Steps
- Confirm scope and disambiguate → the premium reference. Verify name + URL, select run mode, lock disambiguation.
- Pre-flight optional MCPs → check Clay, Granola, Google Drive, CRM, Notion availability per the premium reference ("Optional internal intel sources"). For each available, queue the corresponding queries; for each missing, skip silently.
- Research 13 dimensions → the premium reference. Order: Company → Product → ICP → Pricing → Reviews → Content → Launches → SEO/AEO → Technographics → Openings → GTM → LinkedIn/Social → Paid advertising. Each dimension has tool fallbacks (Ahrefs → Serper → manual; Apify → Firecrawl → manual). Frameworks + scoring → the premium reference ("Core frameworks").
- TrustPilot customer monitor (deep refresh only, customer-facing competitors only) → run inside Step 2.5 per the Phase 2 file. Score top 10–15 customers 🟢/🟡/🔴.
- Synthesize and assign confidence → the premium reference. Assign
[VERIFIED]/[INFERRED]/[ESTIMATED]/[UNAVAILABLE] per claim, write 2–3-paragraph executive summary, document data gaps with follow-up actions.
- Aggregate analysis (only if 2+ competitors researched for same client) → the premium reference. Build threat matrix, feature parity table, credibility audit, 3–5 strategic recommendations. Save as
MMYY-aggregate-insights.md in client's competitors folder.
- Apply attribution standard — inline
(Source: X) per claim (not the verbose [VERIFIED: url, date] block); consolidate full URLs + access dates + confidence in the Sources & data quality table at the end of the document. Quality threshold: ≥50% Verified, ≤20% Estimated.
- Write to client folder per output template → the premium reference ("Inline canonical, v2.7" — 13 dimensions, TrustPilot sub-section, Recent changes header, Sources & data quality table). For matrix mode → the premium reference ("Compact alternative"). Search query patterns per dimension → the premium reference. Common source URL patterns → the premium reference.
- Self-evaluate against quality gates → the premium reference. Run completeness, evidence-quality, and guardrail checks before declaring "done".
- Push to Notion (Competitor Research Database) and Google Docs (
client_folder/context/competitor-research/) per the push targets in frontmatter. For refresh mode, update the existing Notion page rather than creating a duplicate.
- Offer iteration prompts post-delivery → the premium reference. If user signals approval (
"great research", quick approval), offer to save the output as a reference example under the premium reference.
What good looks like
Evaluations (binary pass/fail before declaring "done")
- ≥3 sources per major claim (revenue, funding, team size, pricing).
- ≥50%
[VERIFIED] confidence; ≤20% [ESTIMATED].
- Threat level set on every competitor:
PRIMARY / ENTERPRISE TIER / DIRECT ICP / STEALTH WATCH / LOW / DEFUNCT.
- Inline
(Source: X) on every key data point (no verbose [VERIFIED: url, date] blocks inline).
- Sources & data quality table at end-of-document with URLs + access dates + confidence per dimension.
- Data-gaps section non-empty if any dimension is incomplete or
[UNAVAILABLE].
- All 13 dimensions present (or marked
[Not available] / [Requires premium tool] explicitly).
- Recent-changes header present in
--quick and --refresh modes; "Last refreshed" date updated.
- Output title is
# Competitor research: [Name] exactly — no aliases like "competitive intelligence analysis" or "Competitive Intelligence Report".
- Premium-tool limitations noted explicitly (Ahrefs absent → Serper or manual, BuiltWith absent → "Not available", JS-walled ad libraries → manual check noted).
Scheduling (recurring runs)
/loop 1w /competitor-research --quick [competitor-name] # weekly quick scan, set-and-forget
/loop 1M /competitor-research --refresh [competitor-name] # monthly deep refresh, review-and-approve
/schedule create --name "competitor-[name]-weekly" --cron "0 9 * * 1" --prompt "/competitor-research --quick [name]"
/schedule create --name "competitor-[name]-monthly" --cron "0 9 1 * *" --prompt "/competitor-research --refresh [name]"
For multiple competitors in parallel: /competitor-research --refresh --all spawns one subagent per competitor in the premium reference.
Sourced patterns — person-level competitor profiling
Standard /competitor-research profiles the company (11 dimensions covering positioning, pricing, features, content, GTM, team, funding, etc.). For deeper buyer-side intelligence, add a person-level layer that profiles the named decision-maker / champion / founder behind the competitor:
- Founder / CEO behavioral profile. Public-content cadence (LinkedIn, X, podcast appearances), preferred narratives, hiring-page tells (what roles they're scaling), customer-conversation patterns (testimonials they highlight, objections they pre-empt). Read for positioning intent — founders telegraph strategy in public.
- Champion persona at the buying account. Who actually drives the buy at their target accounts? Title patterns, tenure patterns, pain-point language (lifted from their case studies). This is the ICP-buyer side of the equation, not just the ICP-company side.
- Departure / hiring signals. Recent senior departures at the competitor = signal of internal tension; recent senior hires = signal of investment lane. Both inform competitive timing.
- Social-graph cluster. Who are they engaging with on LinkedIn? Who endorses them publicly? Builds a map of allied / adjacent companies that may be partnership or co-marketing candidates.
Use when the standard 11-dimension company profile isn't enough — typically for direct-competitor showdowns or accounts where the champion person is the deal-maker (mid-market and below).
1---2name: competitor-research3description: Runs a 13-dimension dossier on a B2B SaaS competitor (product, ICP, pricing, reviews, content, launches, SEO/AEO, GTM, social, paid) with confidence levels, cited sources and a data-gaps list. Use when asked for competitor analysis, a competitive landscape or X vs Y.4metadata:5 source: https://skillmd.com/skills/matteotitta/competitor-research6---78# Competitor research910## Research substrate1112## When to run1314Invoke when the user asks for: `competitor analysis for X`, `battlecard research for X`, `competitive landscape for [market]`, `compare X vs Y`, `what's [competitor] doing?`. Do **NOT** invoke for: qualifying a company, product messaging only, researching the user's own company, or single-feature questions (answer directly).1516Three run modes — pick by cadence and depth needed:1718- **First run** (~90 min) — `/competitor-research [competitor]`. New competitor, no existing dossier. Phases 1–3 (or 1–4 for aggregate).19- **Quick scan** (~30 min, weekly) — `/competitor-research --quick [competitor]` or `/loop 1w`. Refreshes fast-moving data only (news, Clay, G2, internal sources). Updates "Recent changes" header — sections without changes stay untouched.20- **Deep refresh** (~90 min, monthly) — `/competitor-research --refresh [competitor]` or `/loop 1M`. Full 13-dimension cycle with TrustPilot monitor and Phase 4 aggregate (if 2+ competitors refreshed this cycle).2122Full cadence + refresh discipline → the premium reference. Visual phase map → the premium reference.2324**The Iron Law:** no data point without source. Every claim cites a URL + access date or is marked `[Not available]`. Estimates need explicit confidence + reasoning. "Fast + wrong = useless."2526## Inputs2728**Required:**2930- `competitor name` — exact company/product name (e.g., `Linear`, `Lovable`).31- `website URL` — competitor's site (e.g., `linear.app`).3233**Recommended (improve quality):**3435- `client context` — current positioning sharpens the comparative angle.36- `specific questions` — focus areas (e.g., "deep dive on their pricing model and outbound motion").37- `research mode` — `single deep dive` (default) or `comparison matrix` (3–6 competitors).3839If competitor name is ambiguous (e.g., "Cursor", "Base", "Linear"), confirm with the user before starting. If website URL is missing, ask — don't guess.4041## Steps42431. **Confirm scope and disambiguate** → the premium reference. Verify name + URL, select run mode, lock disambiguation.442. **Pre-flight optional MCPs** → check Clay, Granola, Google Drive, CRM, Notion availability per the premium reference ("Optional internal intel sources"). For each available, queue the corresponding queries; for each missing, skip silently.453. **Research 13 dimensions** → the premium reference. Order: Company → Product → ICP → Pricing → Reviews → Content → Launches → SEO/AEO → Technographics → Openings → GTM → LinkedIn/Social → Paid advertising. Each dimension has tool fallbacks (Ahrefs → Serper → manual; Apify → Firecrawl → manual). Frameworks + scoring → the premium reference ("Core frameworks").464. **TrustPilot customer monitor** (deep refresh only, customer-facing competitors only) → run inside Step 2.5 per the Phase 2 file. Score top 10–15 customers 🟢/🟡/🔴.475. **Synthesize and assign confidence** → the premium reference. Assign `[VERIFIED]/[INFERRED]/[ESTIMATED]/[UNAVAILABLE]` per claim, write 2–3-paragraph executive summary, document data gaps with follow-up actions.486. **Aggregate analysis** (only if 2+ competitors researched for same client) → the premium reference. Build threat matrix, feature parity table, credibility audit, 3–5 strategic recommendations. Save as `MMYY-aggregate-insights.md` in client's competitors folder.497. **Apply attribution standard** — inline `(Source: X)` per claim (not the verbose `[VERIFIED: url, date]` block); consolidate full URLs + access dates + confidence in the **Sources & data quality** table at the end of the document. Quality threshold: ≥50% Verified, ≤20% Estimated.508. **Write to client folder** per output template → the premium reference ("Inline canonical, v2.7" — 13 dimensions, TrustPilot sub-section, Recent changes header, Sources & data quality table). For matrix mode → the premium reference ("Compact alternative"). Search query patterns per dimension → the premium reference. Common source URL patterns → the premium reference.519. **Self-evaluate against quality gates** → the premium reference. Run completeness, evidence-quality, and guardrail checks before declaring "done".5210. **Push** to Notion (Competitor Research Database) and Google Docs (`client_folder/context/competitor-research/`) per the push targets in frontmatter. For refresh mode, update the existing Notion page rather than creating a duplicate.5311. **Offer iteration prompts** post-delivery → the premium reference. If user signals approval (`"great research"`, quick approval), offer to save the output as a reference example under the premium reference.5455## What good looks like5657### Evaluations (binary pass/fail before declaring "done")5859- ≥3 sources per major claim (revenue, funding, team size, pricing).60- ≥50% `[VERIFIED]` confidence; ≤20% `[ESTIMATED]`.61- Threat level set on every competitor: `PRIMARY` / `ENTERPRISE TIER` / `DIRECT ICP` / `STEALTH WATCH` / `LOW` / `DEFUNCT`.62- Inline `(Source: X)` on every key data point (no verbose `[VERIFIED: url, date]` blocks inline).63- Sources & data quality table at end-of-document with URLs + access dates + confidence per dimension.64- Data-gaps section non-empty if any dimension is incomplete or `[UNAVAILABLE]`.65- All 13 dimensions present (or marked `[Not available]` / `[Requires premium tool]` explicitly).66- Recent-changes header present in `--quick` and `--refresh` modes; "Last refreshed" date updated.67- Output title is `# Competitor research: [Name]` exactly — no aliases like "competitive intelligence analysis" or "Competitive Intelligence Report".68- Premium-tool limitations noted explicitly (Ahrefs absent → Serper or manual, BuiltWith absent → "Not available", JS-walled ad libraries → manual check noted).6970## Scheduling (recurring runs)7172```73/loop 1w /competitor-research --quick [competitor-name] # weekly quick scan, set-and-forget74/loop 1M /competitor-research --refresh [competitor-name] # monthly deep refresh, review-and-approve7576/schedule create --name "competitor-[name]-weekly" --cron "0 9 * * 1" --prompt "/competitor-research --quick [name]"77/schedule create --name "competitor-[name]-monthly" --cron "0 9 1 * *" --prompt "/competitor-research --refresh [name]"78```7980For multiple competitors in parallel: `/competitor-research --refresh --all` spawns one subagent per competitor in the premium reference.8182## Sourced patterns — person-level competitor profiling8384Standard `/competitor-research` profiles the *company* (11 dimensions covering positioning, pricing, features, content, GTM, team, funding, etc.). For deeper buyer-side intelligence, add a **person-level layer** that profiles the named decision-maker / champion / founder behind the competitor:8586- **Founder / CEO behavioral profile.** Public-content cadence (LinkedIn, X, podcast appearances), preferred narratives, hiring-page tells (what roles they're scaling), customer-conversation patterns (testimonials they highlight, objections they pre-empt). Read for *positioning intent* — founders telegraph strategy in public.87- **Champion persona at the buying account.** Who actually drives the buy at their target accounts? Title patterns, tenure patterns, pain-point language (lifted from their case studies). This is the ICP-buyer side of the equation, not just the ICP-company side.88- **Departure / hiring signals.** Recent senior departures at the competitor = signal of internal tension; recent senior hires = signal of investment lane. Both inform competitive timing.89- **Social-graph cluster.** Who are they engaging with on LinkedIn? Who endorses them publicly? Builds a map of allied / adjacent companies that may be partnership or co-marketing candidates.9091Use when the standard 11-dimension company profile isn't enough — typically for direct-competitor showdowns or accounts where the champion person is the deal-maker (mid-market and below).