Install
$ agentstack add skill-kotrotsos-claude-skills-non-coding-competitor-read ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Competitor Strategy Reverse-Engineer
When to use this skill
The user needs to understand what a competitor is actually doing, building, hiring for, abandoning, and betting on. Most competitive intel relies on press releases, which is the least informative public signal a company emits. This skill pulls a broader set of signals and weights them appropriately.
Input the user provides
- Competitor name (company)
- Optionally: the user's own positioning, to ground the comparison
- Optionally: the time window (default: last 12 months)
What this skill does
- Gathers public signals from the time window across multiple categories
- Weights signals by predictive value (job postings > product launches > press releases > thought leadership)
- Classifies signals by strategic vector
- Produces a one-page memo in the structure below
Signals to collect (in order of predictive value)
- Job postings (most predictive of what they are building 6 months out). Pay particular attention to:
- New role types not present 12 months ago
- Geographic expansion in posting locations
- Seniority level shifts (more VPs vs. more ICs)
- Technical specializations being hired
- Product changes (release notes, changelog, new product launches, pricing changes, deprecations)
- Executive movements (hires, departures, role changes)
- Customer announcements (named wins, case studies, logo additions)
- Pricing page changes (often signals strategic shifts)
- Conference talks and content (where their voice is going)
- Press releases (least useful in isolation, useful as confirmation of other signals)
Output structure
# Competitor Read: [Company]
*Time window: [start-end]. Signals analyzed: [count]. Confidence: [high/medium/low].*
## Headline
One sentence on what [Company] is actually doing right now.
## Strategic vectors they are betting on
1. **[Vector 1]**: evidence (which specific signals support this read)
2. **[Vector 2]**: evidence
3. **[Vector 3]**: evidence
## What they are not doing (or have quietly abandoned)
- [Abandoned vector 1]: evidence (job postings removed, product feature deprecated, etc.)
- [Abandoned vector 2]: evidence
## Leading indicators worth tracking
- [Job posting category to watch]
- [Product feature to watch for in next release]
- [Hire that would change the read]
## What this means for [User's company]
2-3 sentences on the implications. Not generic ("we should monitor this"). Specific ("their new VP of Sales is a signal they are moving up-market in Q3, which puts our mid-market positioning under pressure if they execute").
## Honest read on confidence
What is uncertain. What would resolve the uncertainty. Where the signals point in different directions.
Calibration notes
- Job postings are the strongest leading indicator. A press release describes what shipped. A job posting describes what is being built 6 months out. Weight accordingly.
- Be specific about which signals support which vectors. "Their hiring suggests cloud focus" is weak. "Three new postings for AWS Solutions Architects in Q2 suggest they are building a cloud delivery capability they did not have 6 months ago" is useful.
- Acknowledge signal noise. Not every job posting is strategic. Backfills, attrition, and unrelated team growth all generate postings.
- If the company is private and signal-poor, say so explicitly. Do not invent strategic narratives from thin data.
- Do not be reflexively negative. Sometimes a competitor is genuinely executing well. Naming that is more useful than rationalizing it away.
When NOT to use this skill
- Pre-IPO companies in stealth mode (signals will be too thin)
- Companies the user has no overlap with strategically (the analysis is academic)
- Adjacent companies that are not actually competitors (different lens needed)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Kotrotsos
- Source: Kotrotsos/claude-skills-non-coding
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.