analyzing-campaign-attribution-evidence
Campaign attribution analysis involves systematically evaluating evidence to determine which threat actor or group is responsible for a cyber operation. This skill covers collecting and weighting attr
36
33%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/analyzing-campaign-attribution-evidence/SKILL.mdQuality
Discovery
32%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 truncated mid-sentence, which severely undermines its completeness and usefulness for skill selection. While it identifies a reasonably specific domain (cyber campaign attribution), it fails to list concrete actions, provide trigger terms, or include a 'Use when...' clause. The truncation makes it impossible for Claude to reliably select this skill from a pool of alternatives.
Suggestions
Complete the truncated description to fully enumerate specific actions (e.g., 'Analyzes indicators of compromise, maps TTPs to MITRE ATT&CK, compares malware signatures, and correlates infrastructure overlaps').
Add an explicit 'Use when...' clause with natural trigger terms such as 'threat attribution', 'APT identification', 'campaign analysis', 'who is behind this attack', 'threat actor', 'IOCs'.
Ensure the description is self-contained and not cut off, so Claude can fully understand the skill's scope and selection criteria.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (campaign attribution analysis, cyber operations) and describes the general action ('evaluating evidence to determine which threat actor or group is responsible'), but it appears truncated and does not list multiple specific concrete actions. | 2 / 3 |
Completeness | The description is truncated mid-sentence, so it only partially answers 'what does this do' and completely lacks a 'when to use' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the truncation makes even the 'what' incomplete. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'campaign attribution', 'threat actor', 'cyber operation', but the description is truncated and misses common user-facing variations such as 'APT', 'IOC', 'indicators of compromise', 'threat intelligence', or 'attribution'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on campaign attribution and threat actor identification is somewhat specific to cyber threat intelligence, but the truncation and lack of explicit triggers means it could overlap with broader threat intelligence or incident response skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a reasonable structural framework for campaign attribution analysis but suffers from verbosity in explaining concepts Claude already understands, while simultaneously lacking concrete usage examples with sample data. The workflow steps are present but miss validation checkpoints critical for an analytical process where false flags and competing hypotheses are central concerns.
Suggestions
Remove or drastically reduce the 'Key Concepts' section—Claude already understands attribution categories, confidence levels, and ACH methodology. Replace with a brief reference table if needed.
Add a concrete end-to-end example showing the classes/functions being called with realistic sample data and expected output, so the workflow is truly executable rather than just defined.
Add explicit validation/feedback loops in the workflow, such as: 'If primary attribution confidence is LOW, revisit evidence collection for gaps' or 'Cross-check against known false flag techniques before finalizing.'
Trim the 'When to Use' and 'Prerequisites' sections to 1-2 lines each, removing generic boilerplate like 'When investigating security incidents that require analyzing campaign attribution evidence.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is verbose with significant unnecessary content. The 'Key Concepts' section explains attribution categories, confidence levels, and ACH methodology that Claude already knows. The 'When to Use' section is generic boilerplate. The 'Prerequisites' section lists obvious requirements. Much of this could be cut to focus on the actual executable workflow. | 1 / 3 |
Actionability | The code is mostly executable Python, but it's more of a framework/class definition than copy-paste-ready analysis code. There's no concrete example showing how to actually run an end-to-end attribution analysis with real or realistic sample data. The functions are defined but never called with example inputs/outputs. | 2 / 3 |
Workflow Clarity | Steps are listed sequentially (collect evidence → analyze infrastructure → compare TTPs → generate report), but there are no validation checkpoints or feedback loops. For an analytical process where false flags and ambiguity are explicitly mentioned, there's no step for validating results, cross-checking against false flag indicators, or iterating when confidence is low. | 2 / 3 |
Progressive Disclosure | The content is a monolithic document with everything inline. The Key Concepts section, detailed code blocks, and references are all in one file. The references section links to external resources but there are no bundle files to offload detailed content like example datasets, extended API references, or detailed ACH matrix templates. | 2 / 3 |
Total | 7 / 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
9a588e6
- 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.