competitor-teardown
Skill1 starsChanged 5 days agoMITView on GitHub
Build a structured teardown of one competitor from the pages, screenshots, and pricing text you paste in: positioning, target customer, pricing model, a feature table with evidence, and the wedge opportunities where you could win, with every unknown flagged as something to research rather than guessed. Use when sizing up a competitor before a PRD, a pitch, or a pricing decision and you want an analysis grounded only in what they publish.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- teodstr/garagetheir own version, first seen Nov 15, 2026
- eucas-app/eucastheir own version, first seen Nov 8, 2026
- fliqrlabs/instagram-creator-skillstheir own version, first seen Nov 1, 2026
- irinabuht12-oss/marketing-skillstheir own version, first seen Oct 27, 2026
- prosyo-ai/gtm-skilltheir own version, first seen Oct 25, 2026
- rasulshaikh/fde-desktheir own version, first seen Oct 13, 2026
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- irinabuht12-oss/marketing-skills★ 6.5ksame name
- Ootto-AI/claude-content-skills★ 417same name
- prosyo-ai/gtm-skill★ 13same name
- styfinity/claude-marketing-department★ 6same name
- fliqrlabs/instagram-creator-skills★ 5same name
- megandmartin/agent-skills-repo★ 4same name
- fjilvvi/growthlens★ 2same name
- gianpaj/skills★ 1same name
- jpoindexter/theft-kit★ 1same name
- tracetify/skills★ 1same name
5 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 repository163 other files it gives its agents.
- agents.mdAGENTS.md
- 3d-asset-handoff-sheetSkill
- accessibility-regression-auditorSkill
- adr-writerSkill
- agent-memory-designerSkill
- agent-trajectory-evaluatorSkill
- alerting-rules-tunerSkill
- analysis-memo-writerSkill
- annotation-disagreement-ledgerSkill
- annotation-task-spec-builderSkill
- api-deprecation-plannerSkill
- api-error-contract-designerSkill
- architecture-diagram-generatorSkill
- asset-metadata-review-ledgerSkill
- auth-flow-reviewerSkill
- background-job-reliability-auditorSkill
- branch-rebaserSkill
- brand-voice-profilerSkill
- bundle-analyzerSkill
- cache-policy-designerSkill
- canary-release-plannerSkill
- caption-correction-ledgerSkill
- changelog-from-prsSkill
- chart-chooserSkill
- chunking-strategy-optimizerSkill
- circular-dependency-breakerSkill
- claude-settings-auditorSkill
- code-example-verifierSkill
- cold-email-deliverability-auditorSkill
- cold-start-optimizerSkill
- commit-splitterSkill
- component-spec-writerSkill
- connection-pool-tunerSkill
- content-repurposerSkill
- contract-obligation-registerSkill
- contract-test-designerSkill
- conventional-commitsSkill
- cors-configuratorSkill
- coverage-gap-finderSkill
- crm-export-auditorSkill
- dashboard-designerSkill
- data-retention-auditorSkill
- dataset-first-lookSkill
- dead-code-finderSkill
- deadlock-diagnoserSkill
- decision-log-reconcilerSkill
- dependency-auditSkill
- dependency-upgrade-plannerSkill
- design-brief-writerSkill
- design-critique-checklistSkill
- design-token-extractorSkill
- devcontainer-designerSkill
- distributed-tracing-instrumenterSkill
- dockerfile-optimizerSkill
- email-sequence-drafterSkill
- embedding-index-tunerSkill
- embedding-set-inspectorSkill
- entity-match-candidate-ledgerSkill
- exit-ticket-builderSkill
- extract-moduleSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 50
Run it alongside the user-interview-synthesizer skill so the inside and outside views land in the same PRD.
“Common” is measured: kept by at least 6 in 10 of the 13 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
A competitor teardown written from memory is mostly a list of things you believe about a product you have not used lately. This skill does the opposite: you paste what the competitor actually publishes (homepage, pricing page, a docs section, your description of a few screens, review excerpts) and it produces a teardown that cites that material line by line. Where the material is silent, it says so and adds the question to a research list instead of guessing. It needs no browser or tools, only pasted text, so it works on claude.ai, in Claude Code, and in Claude Cowork.
When to use this skill
- You are writing a PRD and need the competitive landscape section to be evidence rather than opinion; the prd-writer skill can take this output as input.
- You are setting or changing prices and want to see exactly where a competitor's tiers gate features.
- An investor asked "how are you different from X?" and you want an answer that survives them opening X's website.
- You are choosing a wedge, a narrow segment or use case to win first, and want it derived from the competitor's blind spots rather than your preferences.
[!NOTE] The skill works only from what you paste. It will not state a price, feature, customer count, or funding round from memory, even for a well-known product, because that memory has a date. Everything it cannot see goes into Gaps to research. In Claude Code with web access, hand that section to the web-research-pipeline skill for a cited follow-up.
Instructions
- Inventory the material. List every source the user pasted: what page or screen it is and the date it was captured (if missing, continue with "date not given"). This inventory is the entire evidence base; nothing outside it exists for the analysis.
- Extract positioning. Quote the headline, subheadline, and any tagline exactly. Then state in one line each: the category they claim to be in, the promise they make, and who they name or imply as the alternative ("replace your spreadsheet", "unlike legacy tools"). Mark each as STATED (quoted) or INFERRED (your reading).
- Identify the target customer. Derive the ideal customer profile from the language, plan names, logos or case studies, advertised integrations, and roles named on the site. Two or three sentences, each claim marked STATED or INFERRED. If the material shows two audiences (a marketing page for teams, docs for developers), report both.
- Describe the pricing model. Name the model type: per seat, usage based, flat, freemium with tiers, sales-led, or a mix. Then list the tiers by their published names and, for each, what the pricing page says it gates (seats, volume, features, support). Copy figures exactly as they appear, with currency and billing period, and attach the capture date. If no pricing material was provided, this section reads "NOT PROVIDED, see Gaps to research" and nothing else.
- Build the feature table. Columns: Feature, Competitor (Yes / No / Unclear), Evidence (which source, quoted phrase). If the user supplied their own feature list, add a Yours column. "Unclear" is the correct answer whenever the material does not mention a feature; do not downgrade it to "No".
- Find wedge opportunities. Three to five, each derived from a specific observation in the material: a segment their language ignores, a pricing cliff between two tiers, a feature marked No or Unclear that your interviews say matters, a complaint pattern (only if review excerpts were provided), or a positioning promise their own docs undercut. Each wedge has three fields: Observation (with source), Opportunity, and What would need to be true for it to work.
- List the gaps to research. Everything marked INFERRED or Unclear, plus what a founder would want that the material did not cover: pricing if absent, churn signals, recent changes, integrations, support quality. Phrase each as a question and suggest where the answer lives (changelog, docs, a free trial, a review site, one of their customers).
- Assemble the teardown in this order: Sources, Positioning, Target customer, Pricing model, Feature table, Wedge opportunities, Gaps to research. Keep it to two pages.
Output
A Markdown teardown with the seven sections above. Every factual line either quotes a source from the inventory or carries an INFERRED label, and the Gaps to research section is a checklist you can hand to whoever does the next pass. Run the skill once per competitor and compare the feature tables side by side.
Example
Excerpt from a teardown of a pasted pricing page captured on 3 September 2026:
### Pricing model
Model: freemium with three self-serve tiers plus a sales-led tier (STATED).
- Free: "up to 3 projects", no integrations listed
- Pro: gates "unlimited projects" and "Slack + Zapier"
- Team: gates "roles and permissions" and "SSO"
Price cliff: integrations sit behind Pro, so a solo user who needs one integration pays for unlimited projects they do not need.
### Wedge opportunities
1. Observation: integrations are gated at Pro (pricing page). Opportunity: a free tier with one integration for solo users. What would need to be true: solo users are a meaningful share of their signups (INFERRED, research).Run it alongside the user-interview-synthesizer skill so the inside and outside views land in the same PRD; Claude skills for founders shows the sequence.
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.

