analyzing-ransomware-leak-site-intelligence
Monitor and analyze ransomware group data leak sites (DLS) to track victim postings, extract threat intelligence on group tactics, and assess sector-specific ransomware risk for proactive defense.
66
58%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/analyzing-ransomware-leak-site-intelligence/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is strong in specificity and distinctiveness, clearly carving out a niche around ransomware data leak site monitoring with concrete actions. However, it lacks an explicit 'Use when...' clause, which limits its completeness score, and could benefit from additional natural trigger terms that users might employ when requesting this type of analysis.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about ransomware group activity, dark web leak monitoring, or tracking threat actor victim postings.'
Include additional natural trigger terms users might say, such as 'dark web monitoring', 'ransomware gangs', 'extortion groups', 'leak site tracking', or 'threat actor intelligence'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'monitor and analyze ransomware group data leak sites', 'track victim postings', 'extract threat intelligence on group tactics', and 'assess sector-specific ransomware risk for proactive defense'. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this dimension at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes relevant domain terms like 'ransomware', 'data leak sites', 'DLS', 'threat intelligence', and 'victim postings', but misses common user variations like 'dark web monitoring', 'ransomware gangs', 'extortion groups', 'leak monitoring', or 'threat actor tracking'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific niche focusing on ransomware data leak site monitoring and victim tracking, which is unlikely to conflict with other skills. The combination of 'DLS', 'ransomware group', and 'victim postings' creates a very distinct trigger profile. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable Python code for ransomware leak site intelligence analysis with real API endpoints and complete implementations. However, it is significantly bloated with explanatory content Claude doesn't need (double extortion model, DLS intelligence value, safe collection practices) and time-sensitive statistics. The workflow lacks inline validation checkpoints between steps, and the monolithic structure would benefit from splitting code into referenced files.
Suggestions
Remove the 'Key Concepts' section entirely—Claude already understands double extortion, DLS intelligence value, and safe collection practices. Move any truly novel constraints (e.g., 'never directly access DLS sites') into a brief 'Constraints' bullet list.
Remove the 'Overview' paragraph's statistics and the 'When to Use' boilerplate section to reduce token waste by ~30%.
Add inline validation between steps: after Step 1, verify data was fetched (e.g., assert len(self.posts) > 0), and after Step 3, validate that sector/country fields exist in the data before proceeding to risk scoring.
Extract the Python classes/functions into a referenced file (e.g., ransomware_intel.py) and keep SKILL.md as a concise overview with usage examples and workflow summary.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is excessively verbose. The 'Key Concepts' section explains double extortion, DLS intelligence value, and safe collection practices—all concepts Claude already knows. The 'Overview' paragraph includes statistics ('96 unique ransomware groups', '535 victims per month') that are time-sensitive filler. The 'When to Use' section is generic boilerplate. Much of this could be cut by 50%+ without losing actionable content. | 1 / 3 |
Actionability | The code is fully executable, copy-paste ready Python with real API endpoints (ransomwatch), proper error handling, and concrete data processing. Each step produces usable output—data ingestion, trend analysis, risk assessment, group tracking, and report generation are all complete implementations. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and logically ordered. However, there are no validation checkpoints between steps—no verification that API data was successfully fetched before analysis, no data quality checks, and no error recovery loops. The 'Validation Criteria' section is a post-hoc checklist rather than inline verification steps. | 2 / 3 |
Progressive Disclosure | The content is largely monolithic—all code is inline in a single file with no references to separate detailed documents. The References section links to external resources but the ~300 lines of Python code could benefit from being split into a separate module file with the SKILL.md providing a concise overview and usage examples. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- mukul975/Anthropic-Cybersecurity-Skills
- Commit
888bbe4
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.