competitive-analysis
Skill0 starsChanged 4 months agoMITView on GitHub
Produces a structured competitive analysis of a product or company — mapping the competitive landscape, comparing features and positioning, analyzing rivals through the jobs customers are trying to get done, and landing on a clear "where we win / where we're exposed" conclusion with recommendations. Use this whenever the user wants a competitive analysis, competitor teardown, market/ landscape scan, feature comparison, positioning map, or SWOT of competitors; is preparing a strategy, pitch, roadmap, or launch and needs to understand rivals; or asks how their product stacks up against specific competitors. Push for a decision-focused analysis grounded in evidence, not a neutral feature table that leads nowhere.
54 other projects use a version of this.
Adopted by
Most recently taken up by
- miguelclavel/ux-research-skillstheir own version, first seen Nov 8, 2026
- insight68/Skillstheir own version, first seen Nov 8, 2026
- AgnesAI-Labs/agnet-skills-cntheir own version, first seen Nov 1, 2026
- jaskirat1616/grok-skillstheir own version, first seen Nov 1, 2026
- codeApe-7/ai-agent-workflowGrouptheir own version, first seen Nov 1, 2026
- vijaysuperpositionist/skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use usability-test-plan, onboarding-flow and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
launchapp-devSkillusability-test-plan
Design a usability test plan with tasks, success metrics, participant criteria, and facilitation guide. Use when planning moderated or unmoderated usability testing sessions.
Also in 3 projects that use this
Dragoon0xSkillonboarding-flow
Design first-run experiences that create the aha moment fast. Reduces time-to-value by sequencing actions, progressive disclosure, and contextual guidance. Use when building signup flows, product tours, or empty states.
Also in 3 projects that use this
shawnpangSkilllead-scoring
When a founder needs to qualify inbound leads, define their ICP, build a lead scoring model, set MQL criteria, or route prospects through pipeline stages. Activate when the user mentions lead scoring, ICP, MQL, SQL, lead qualification, inbound leads, or pipeline design.
Also in 3 projects that use this
nicepkgSkilluser-research-synthesis
Synthesize qualitative and quantitative user research into structured insights and opportunity areas. Use when analyzing interview notes, survey responses, support tickets, or behavioral data to identify themes, build personas, or prioritize opportunities.
Also in 4 projects that use this
claude-office-skillsSkillemail-marketing
Email marketing automation - campaign creation, sequence building, A/B testing, deliverability optimization, and analytics
Also in 3 projects that use this
AnthropicSkilluser-research
Plan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or when the user needs help with any aspect of understanding their users through research.
Also in 3 projects that use this
Other versions54 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 54
- anthropics/financial-services-plugins★ 41ksame name
- anthropics/financial-services★ 41ksame name
- claude-office-skills/skills★ 433same name
- shawnpang/startup-founder-skills★ 331same name
- mverab/eGEOagents★ 218same name
- Fokkyp/claude-skills★ 211same name
- aakashg/pm-claude-code-setup★ 152same name
- nahid-sparktales/agent-dispatcher★ 59same name
- agencia-conversion/agentic-seo-skills★ 51same name
- launchapp-dev/animus-cli★ 39same name
44 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- accessibility-reviewSkill
- design-fundamentalsSkill
- heuristic-evaluationSkill
- inclusive-designSkill
- persona-builderSkill
- ux-usability-studySkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 45 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
This is for product / company / market competition: If "competition" means something else — rival job candidates in an interview, sports …
- Distinctive: line 44
Match the artifact to what was asked: If the user asks for *one* piece — "just a feature comparison matrix," "a positioning map" — deliver …
- Very specific: line 139
Default to Markdown (a matrix as a table plus narrative).
“Common” is measured: kept by at least 6 in 10 of the 45 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Competitive Analysis
This skill turns "who else does this and how do we compare?" into a structured, decision-driving analysis. The trap it exists to avoid: a competitive analysis that is just a big neutral feature grid with checkmarks. That looks thorough and changes nothing. A useful competitive analysis has a point of view — it exists to inform a specific decision (how to position, what to build next, where we're vulnerable, whether a market is worth entering) and ends with a clear so-what.
Anchor the whole thing on that decision up front, and let it set the depth: a positioning exercise weights messaging and brand; a roadmap input weights feature gaps and capabilities; a market-entry question weights segments, moats, and economics.
Scope: know when this applies (and when to hold back)
Two ways this skill is easy to misuse — avoid both:
- This is for product / company / market competition. If "competition" means something else — rival job candidates in an interview, sports opponents, academic or grant rivals, a debate — don't force this framework onto it. The full apparatus (direct/indirect/substitute typology, feature matrix, market white space, "sources & confidence") is built for products and will read as contrived when bolted onto a person's job search or a race. Help with the actual task, borrowing only the genuinely transferable idea (know your positioning, find your edge) in that domain's own language. Recognizing the mismatch and adapting is the correct move — not silently applying the template.
- Match the artifact to what was asked. If the user asks for one piece — "just a feature comparison matrix," "a positioning map" — deliver that, focused and well-made, and offer to expand into the fuller analysis rather than shipping an unrequested strategy document. Ground it in the framing questions below so it's sharp, but don't balloon a matrix request into the whole report. A tight answer to the actual question beats an impressive answer to a bigger one.
How to build it
1. Frame the analysis
Establish before comparing anything:
- The decision it informs — positioning, roadmap, pricing, go/no-go, sales enablement. Everything downstream serves this.
- Your product and the customer — who you serve and the job they hire the product to do. Comparison is meaningful only relative to a customer and a job.
- The set of competitors, chosen deliberately across three types (people
under-scope this):
- Direct — same solution, same audience.
- Indirect — different solution to the same need.
- Substitutes / non-consumption — the spreadsheet, the manual process, or "do nothing" that customers use today. Often the real competitor, especially for a new category.
- Evidence sources — their site, product, pricing pages, reviews (G2/ Capterra/app stores), docs, changelogs, positioning, analyst notes. Base claims on evidence; where you're inferring or unsure, say so and mark it — a confidently wrong competitive claim is worse than a flagged gap. Never invent a competitor's pricing, metrics, or roadmap.
2. Analyze along the dimensions that matter
Pick the dimensions that bear on the decision; don't compare everything. Common useful ones:
- Positioning & value proposition — who each competitor says they're for and the core promise they lead with. Reveals how the market is segmented and where space is open.
- Target segment — who they actually serve well (and who they underserve — often your opening).
- Key features & capabilities — but organized around the jobs to be done,
not a flat feature dump. "How well does each solve
<job>?" beats "does each have<feature>?" Rate depth, not just presence. - Pricing & business model — how they charge, price points, packaging, and what that implies about their target and strategy.
- Strengths & weaknesses — what each does genuinely well and where they're soft (from reviews, gaps, complaints).
- Differentiation & moat — why customers pick them and how defensible it is (network effects, data, switching costs, brand, integrations).
- Market presence — traction, momentum, funding, mindshare where knowable.
A feature/capability matrix is a good artifact if rows are jobs or outcomes and cells convey depth (strong / partial / none / unknown) rather than bare checkmarks — and if it's paired with narrative, not left to speak for itself.
3. Synthesize into a point of view
This is the part that makes it worth doing. Pull the comparison up into:
- Where you win — the jobs/segments where you're genuinely stronger, and the evidence.
- Where you're exposed — where competitors are ahead or you're vulnerable.
- White space — unmet needs or underserved segments no one owns well.
- Positioning implication — the wedge you should lean into given the above.
- Honest read — don't flatter the home team; an analysis that concludes "we win everywhere" is not credible and not useful.
4. Recommend
Tie back to the framing decision with concrete moves: how to position, which gaps to close first, where not to compete, what to watch. Prioritize.
Report structure
# Competitive Analysis: [your product] vs. [market/competitors]
## Purpose
The decision this informs; your product and the customer/job
## Landscape
The competitor set (direct / indirect / substitute) and why each is included
## Comparison
By dimension or job-to-be-done — matrix (depth, not checkmarks) + narrative
## Competitor profiles (as needed)
Short profile each: positioning, segment, strengths, weaknesses, pricing
## Where we win / where we're exposed / white space
The synthesis — the heart of the document
## Recommendations
Prioritized, tied to the framing decision
## Sources & confidence
What's evidenced vs. inferred; what to validateProducing the deliverable
Default to Markdown (a matrix as a table plus narrative). Offer a .xlsx for the
comparison matrix if the user wants to sort/filter, or slides if it's feeding a
strategy/pitch review. Mark inferences and unknowns clearly, cite where claims
come from, and keep the synthesis section the centerpiece — that's where the
value is.
Pairs well with
- persona-builder — ground the analysis in the customer and job you're serving.
- ux-usability-study — validate the "where we win" hypotheses with real users.
Accuracy
Base competitor claims on real, checkable evidence; explicitly flag anything inferred or uncertain, and never fabricate a competitor's pricing, features, metrics, or plans — an unverified claim presented as fact undermines the whole analysis and can mislead a real decision.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

