Competitive Intelligence
Creates interactive HTML battlecards for structured competitive research.
- Skill Road
- Competitive Intelligence
Categories
Competitive Intelligence is an official skill from Anthropic's knowledge-work-plugins repository for Claude and sales-oriented knowledge work. According to the provider, the skill researches competitors and turns the findings into an interactive battlecard delivered as a self-contained HTML artifact. The result is more than an unstructured summary: it is a navigable working document with a comparison matrix, clickable competitor cards, and sections for positioning conversations. The primary source is the Sales plugin at https://github.com/anthropics/knowledge-work-plugins/tree/main/sales/skills/competitive-intelligence. Anthropic presents the skill as a reusable workflow for current competitive information, not as an independent database or a guarantee that every individual research statement is correct.
Purpose and audience
The skill is aimed at sales, product marketing, and revenue teams that need a disciplined view of one to five competitors before customer conversations. At the start, the user is expected to provide the company, the product or service being sold, and the main competitors. Optional context can focus the work on one competitor, a specific deal, or recurring customer pain points. According to the provider, an existing seller context can shorten later runs. This structure turns a broad request for competitive knowledge into a bounded research assignment. It is particularly useful when several people need a shared, refreshable basis for positioning and want to avoid improvising different claims in different customer meetings.
Research and output
The documented workflow examines the user's company and each competitor through several public signals. These include product offerings, positioning, recent news, releases, product updates, customer reviews, and publicly visible market or hiring signals. When connected tools are available, the provider says that CRM data about won and lost deals, existing documents, internal chat references, and call transcripts can also contribute. Without connectors, the workflow is designed to use public product pages, blogs, release notes, reviews, and other accessible sources. The resulting HTML battlecard contains an overview matrix and individual competitor sections with a profile, strengths, weaknesses, talk tracks, objection handling, and questions that can surface meaningful differences without resorting to personal attacks.
Practical use
A card can be opened before a call to review the relevant competitor tab and scenario-specific talk tracks. During an evaluation, the comparison matrix can help connect capabilities to customer outcomes and market positioning instead of reciting an isolated feature list. After a win or loss, the team can feed new observations into the next refresh. According to the provider, competitive information should be refreshed regularly and also before significant deals or after a competitor announcement because it becomes stale quickly. The artifact is designed as a standalone HTML file that can be viewed locally, hosted internally, or shared with teammates. This catalog entry does not state concrete current prices; the applicable official provider source remains authoritative for commercial terms.
Boundaries, security, and E-E-A-T
Quality depends on the named competitors, the freshness of public sources, available connectors, and review by knowledgeable people. CRM, chat, and transcript content may contain confidential customer, employee, or deal information. Before connecting any source, teams should confirm permissions, data minimization, retention, and internal approvals. Results from local or connected tools may subsequently be passed into the selected Claude workflow and model processing; a local file excerpt is therefore not an automatic guarantee of local-only processing. The skill should not turn unsupported market claims, defamatory language, or guesses presented as facts into a battlecard. Competitor strengths should be acknowledged honestly, and claims should be checked against sources and dates. Anthropic is the provider of the published skill workflow; professional judgment, sales approval, and the decision about customer-facing positioning remain with the responsible team.
Source and license
The official primary source is the named skill directory in Anthropic's public repository. Its skill file describes triggers, seller context, optional connectors, research phases, the HTML structure, refresh cadence, and advice for producing better competitive intelligence. The repository identifies Apache-2.0 in its root license file. Anthropic's official documentation at https://docs.anthropic.com/ provides complementary information about Claude-related products and operation. This entry makes no claim about a particular data entitlement, account permission, or fixed commercial condition. Before production use, sales and privacy stakeholders should confirm which sources may be used and how the generated file must be protected.
- Provider
- Anthropic
- License
- Apache-2.0
- Last reviewed
- 09.09.2026
Repository and documentation
Categories
Compatible with
Related guides
Guides and background related to this entry.
Set up Mapbox MCP Server
Set up the Mapbox MCP Server: hosted endpoint or local token, a first test, and sensible limits.
30.09.2026
Setting up the Agent News MCP Server
The Agent Times' free, no-auth MCP server delivers verified, sourced news with confidence scores about the AI agent and MCP industry.
18.09.2026
Set up Bright Data MCP Server safely
Configure the official Bright Data MCP Server as a remote endpoint or local process: store the API token securely, activate tool groups deliberately, and understand scraping boundaries and prompt-injection risks.
18.09.2026
Set up Qdrant MCP Server
Set up Qdrant semantic search through MCP, limit collection permissions, and control writes.
18.09.2026