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.
npx skills add varunk130/ai-customer-discovery-skills --skill competitive-analyzergit clone --depth 1 https://github.com/varunk130/ai-customer-discovery-skillsWrote 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.
[](https://agentmods.dev/skills/varunk130/ai-customer-discovery-skills/competitive-analyzer)<a href="https://agentmods.dev/skills/varunk130/ai-customer-discovery-skills/competitive-analyzer"><img src="https://agentmods.dev/badge/skills/varunk130/ai-customer-discovery-skills/competitive-analyzer/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.
<a href="https://agentmods.dev/skills/varunk130/ai-customer-discovery-skills/competitive-analyzer"><img src="https://agentmods.dev/badge/skills/varunk130/ai-customer-discovery-skills/competitive-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.00800 |
| Opus 5 | $0.00032 | $0.00400 |
| Sonnet 5 | $0.00013 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
competitive-analyzer 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 11d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitive Analyzer
Run a disciplined competitive teardown that goes beyond a feature checklist. The output is the smallest set of decision-relevant dimensions, scored objectively across competitors, with explicit gaps you can attack and risks you should defend.
Core Principle
A competitive analysis is only useful if it changes a decision. Most teardowns produce 40-row feature grids that no one reads. This skill forces brutal selection: pick the 4-6 dimensions buyers actually weigh, score them with a defensible rubric, and surface the 2-3 moves the analysis implies.
Output
Save to outputs/competitive-analysis-[market]-[YYYY-MM-DD].md
| Artifact | Description |
|---|---|
| Dimension Map | The 4-6 buyer-weighted dimensions with rationale for inclusion |
| Scoring Matrix | Each competitor scored 1-5 on each dimension, with one-line evidence per cell |
| Gap Map | Dimensions where every competitor underperforms - the white space |
| Risk Map | Dimensions where one competitor strongly outperforms us |
| Implied Moves | 2-3 concrete strategic moves the analysis suggests, ranked by leverage |
Process
Step 1: Frame the Market
I'll ask:
"What market are we analyzing, and from whose perspective? List the competitors (3-7 works best). What's the deal context - what's a typical buyer trying to accomplish?"
Step 2: Pick the Dimensions
Generate a candidate list of 12-15 dimensions, then ruthlessly cut to 4-6 by applying two filters:
- Decision relevance - does this dimension actually move buying decisions?
- Discriminating power - do competitors meaningfully differ on it? (Dimensions where everyone scores the same get cut.)
Step 3: Score with Evidence
For each (competitor × dimension) cell, score 1-5 with a single sentence of evidence - a public artifact, a customer quote, a product behavior - not opinion.
Step 4: Identify Gaps and Risks
Two scans across the matrix:
- Gap - any dimension where the highest score is ≤3 → market is underserved, opportunity
- Risk - any dimension where a competitor scores 5 and we score ≤3 → defensive priority
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.
- 11d ago First seen · 65 lines · 63 tokens per session scan A 98b27f9995d2
competitive-analyzer is a skill published in the GitHub repository varunk130/ai-customer-discovery-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 800 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
niche-positioning-brief
Writes a concise positioning brief that defines a newsletter's niche, primary differentiator, target reader, editorial promise, and what the publication refuses to do — giving the editor a clear decision-making framework and a document that can anchor copy across subscribe pages, pitches, and About pages.
solution-architecture
Produces a discovery-grade architecture: enough detail to estimate effort, surface technical risks, and explain choices to the client — but not detailed design. Detailed design happens in delivery, not here. Where the BA isn't a tech lead, this skill is best run pair-mode with an architect; otherwise it produces vague…
profile-builder
Produces discovery-context.md — the single source of truth that every other skill in this pack reads. Without it, other skills will warn and offer to bootstrap inline (a 2–3 question mini-interview held in conversation, not written to disk). Running this skill first gives the best, most consistent results.
insight-synthesis
Turns whatever evidence the BA managed to gather into structured insights — weighted by source quality so the team doesn't treat one SME's hunch as equal to five user interviews.
user-interviews
Direct user interviews. Run only when useraccess allows it.
journey-mapping
Turns a persona's lived experience into a stage-by-stage map that surfaces where pain concentrates and where opportunity moments hide. Each pain point is evidence-anchored; each opportunity moment links back to the opportunity-tree.md so journey work doesn't drift from prioritized outcomes.