agent-instructions
Use when writing project instructions for a coding agent (CLAUDE.md, AGENTS.md, or equivalent). Covers what belongs in them, what does not, structure, and…
Use when analyzing competitors. Covers gathering evidence rather than opinion, positioning and pricing analysis, identifying real differentiation, and producing a conclusion that changes a decision.
$ npx -y skills add nimadorostkar/Claude-Skills-collection --skill competitive-analysis --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/competitive-analysisContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when analyzing competitors. Covers gathering evidence rather than opinion, positioning and pricing analysis, identifying real differentiation, and producing a conclusion that changes a decision.
name: competitive-analysis description: Use when analyzing competitors. Covers gathering evidence rather than opinion, positioning and pricing analysis, identifying real differentiation, and producing a conclusion that changes a decision. metadata: category: business version: 1.0.0 tags: [competitive, market, positioning, pricing, strategy]
Understand what competitors actually do, as opposed to what they say, and turn that into a decision. A feature-comparison table is not an analysis; it is a table.
1. **Define the competitive set honestly** — Including the substitutes. For most B2B products, the largest competitor is a spreadsheet and the status quo, and they are usually left off the list. 2. **Gather evidence, not marketing** — Sign up. Use the product. Read the documentation and the changelog — the changelog tells you what they actually build, as opposed to what they advertise. Read the reviews, especially the three-star ones, which are the honest ones. 3. **Map the positioning** — Two axes that matter to buyers. Where is everyone? The empty quadrant is either an opportunity or a place people have tried and failed. 4. **Analyze the pricing structure, not the number** — What do they charge for, and what does that reveal about who they think their customer is? Per-seat pricing and usage-based pricing target different buyers. 5. **Separate claimed differentiation from real** — Everyone claims to be easy to use and to have great support. What is actually different, and is it something a buyer would pay for? 6. **Reach a conclusion** — An analysis that ends in a table has not concluded anything.
**An analysis that reaches a conclusion:**
## Competitive set
| Competitor | Actual positioning | Evidence |
|-------------------|---------------------------------------|---------------------------------|
| Acme | Enterprise, top-down, procurement-led | 12-month contracts, no self-serve, "book a demo" only |
| Bolt | Bottom-up, developer-first | Free tier, API-first docs, no sales team visible |
| **Spreadsheets** | **The actual incumbent** | **Mentioned in 60% of the reviews we read as "what we used before" — and in 15% as "what we went back to"** |
| Doing nothing | The default | — |
## What the evidence says (not the marketing)
**Acme** — signed up via a demo request. Time to first value: 3 weeks, requiring
an implementation call. Their changelog shows 80% of releases in the last year
were compliance and admin features (SSO, audit logs, SCIM). They are building
for procurement, not for users.
**Bolt** — signed up in 4 minutes. Excellent API documentation. But their
changelog shows almost nothing shipped in the core workflow for 8 months; they
are building integrations. Their three-star reviews consistently say the same
thing: "great API, but the UI is unusable for our non-technical team."
## Positioning map
technical buyer
|
Bolt |
|
self-serve -----+----- sales-led
|
| Acme
business buyer
The empty quadrant — self-serve, business buyer — is where the spreadsheet users
are. That is not a coincidence, and it is not obviously an opportunity: it may be
empty because that buyer will not adopt a tool without being sold to.
## Pricing
Acme: $40/seat/month, annual, minimum 25 seats. Floor: $12k/year.
Bolt : usage-based, free to ~$200/month for a typical team.
The gap between $2,400/year and $12,000/year is where a business-buyer,
self-serve product would sit. Nobody is there.
## Conclusion — and the decision it changes
Do NOT build the enterprise admin features on the roadmap for Q3. That is
competing with Acme on the axis they have spent two years and a sales team
building. We will lose.
The defensible position is self-serve for the business buyer, priced between
the two — which is exactly where our current users came from (60% from
spreadsheets, per our own onboarding survey).
The risk, stated honestly: the quadrant may be empty because that buyer does not
self-serve. Test it before committing the qA curated library of 137 production-grade skills for Claude and other AI coding agents. Every skill follows one structure, speaks with one voice, and earns its place by changing what the agent does.
Repo: nimadorostkar/Claude-Skills-collection
Use when writing project instructions for a coding agent (CLAUDE.md, AGENTS.md, or equivalent). Covers what belongs in them, what does not, structure, and…
Use when an agent needs state that survives a session or a context compaction. Covers what to persist, file-based memory, structuring notes for retrieval, and…
Use when automating agent behavior with lifecycle hooks. Covers hook events, deterministic enforcement of rules the model should not be trusted to remember,…
Use when packaging skills, commands, hooks, and MCP servers into a distributable plugin. Covers manifest structure, bundling, versioning, testing, and…
Use when writing a new skill for an AI agent. Covers scoping, description writing for reliable triggering, progressive disclosure, and the difference between a…
Use when reviewing or improving an existing agent skill. Covers triggering accuracy, content quality, redundancy with the base model, and measuring whether the…