agentmods.dev

competitor-research

competitor-research is a skill for Claude Code, Codex from matteotitta/genesys-skills. It costs 72 tokens per session (1,884 once invoked), scanned A, original, MIT.

A structured investigation of a business-to-business software competitor across 13 areas, with scores, confidence levels, sources, and identified data gaps. It produces a competitor dossier for comparison and decision-making.

In plain words
What is it for?
Use it to research a B2B SaaS competitor’s product, pricing, positioning, content, search visibility, and customer-facing claims.
Why use it?
It organizes scattered competitor information into one evidence-backed view. This makes it easier to see where a competitor is strong, where information is missing, and how your offer may differ.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

not rated 49repo +1 changed today A scan SkillSpector: warn 72 tokens original MIT

Good fit Use it to research a B2B SaaS competitor’s product, pricing, positioning, content, search visibility, and customer-facing claims.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/matteotitta/genesys-skills/competitor-research
View source ↗ matteotitta/genesys-skills newsletter.genesysgrowth.com
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add matteotitta/genesys-skills --skill competitor-research
Clone the repo
git clone --depth 1 https://github.com/matteotitta/genesys-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for competitor-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/matteotitta/genesys-skills/competitor-research/github.svg)](https://agentmods.dev/skills/matteotitta/genesys-skills/competitor-research)
Your own site
<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/competitor-research"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/competitor-research/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for competitor-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/competitor-research"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/competitor-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,884 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 165
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.01884
Opus 5.5 $0.00029 $0.00754
Sonnet 5.5 $0.00014 $0.00377
Haiku 4.5 $0.00007 $0.00188

Measured today against content hash da9cd572e9b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

competitor-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/competitor-research/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

  1. Confirm scope and disambiguate → the premium reference. Verify name + URL, select run mode, lock disambiguation.
  2. 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.
  3. 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").
  4. 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 🟢/🟡/🔴.
  5. 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.
  6. 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.
  7. 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.
  8. 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.
  9. Self-evaluate against quality gates → the premium reference. Run completeness, evidence-quality, and guardrail checks before declaring "done".
  10. 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.
  11. 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.

Read the full file on GitHub · 90 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today Changed · -85 lines · -64 tokens per session da9cd572e9b6
  2. 2mo ago First seen · 175 lines · 136 tokens per session scan A c921d85ca38a

Subscribe to this mod's changes

competitor-research is a skill published in the GitHub repository matteotitta/genesys-skills (49 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,884 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Claude CodeMarketing and SEOResearchagent-skillsai-agentsclaudegtmproduct-marketing
Related

competitor-research compared with skills from other repositories

competitor-research next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
competitor-researchmatteotitta/genesys-skillsSkill49yesterdayMITA72Claude Code, Codex
category-point-of-viewadam-lagerhausen/b2b-marketing-skillsSkill74mo agoMITA46Claude Code
b2b-pmm-orchestratoradam-lagerhausen/b2b-marketing-skillsSkill74mo agoMITA49Claude Code
ai-pmm-revieweradam-lagerhausen/b2b-marketing-skillsSkill74mo agoMITA45Claude Code
customer-story-engineadam-lagerhausen/b2b-marketing-skillsSkill74mo agoMITA38Claude Code
demo-storylineadam-lagerhausen/b2b-marketing-skillsSkill74mo agoMITA41Claude Code
sales-narrative-deckadam-lagerhausen/b2b-marketing-skillsSkill74mo agoMITA54Claude Code