adversus
Adversus integration. Manage data, records, and automate workflows. Use when the user wants to interact with Adversus data.
56
46%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/adversus/SKILL.mdQuality
Discovery
57%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 benefits from naming the specific platform (Adversus) and including an explicit 'Use when' clause, which helps with completeness and some distinctiveness. However, it is severely lacking in specificity — the actions described are generic placeholders that could apply to virtually any integration. Without concrete Adversus-specific capabilities or natural user trigger terms, Claude would struggle to confidently select this skill over other data/workflow tools.
Suggestions
Replace vague terms like 'manage data, records, and automate workflows' with specific Adversus actions such as 'create and update leads, manage call campaigns, sync contact lists, configure automated dialer workflows'.
Expand trigger terms in the 'Use when' clause to include natural phrases users would say, such as 'Adversus CRM', 'call center leads', 'dialer campaigns', 'Adversus API', or 'outbound calling workflows'.
Add domain context to distinguish from other CRM/integration skills, e.g., 'Adversus outbound call center platform integration' rather than just 'Adversus integration'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'manage data, records, and automate workflows' without specifying concrete actions. It doesn't explain what kind of data, what records, or what workflows — these are generic terms that could apply to almost any integration. | 1 / 3 |
Completeness | It does answer both 'what' (manage data, records, automate workflows) and 'when' (when the user wants to interact with Adversus data) with an explicit 'Use when' clause, even though both parts are vague in substance. | 3 / 3 |
Trigger Term Quality | It includes 'Adversus' as a key trigger term which is specific to the platform, and 'data' and 'workflows' are somewhat relevant. However, it lacks natural terms users might say like specific Adversus features (e.g., leads, campaigns, call lists, contacts, CRM, dialer). | 2 / 3 |
Distinctiveness Conflict Risk | 'Adversus' as a product name provides some distinctiveness, but 'manage data, records, and automate workflows' is extremely generic and could overlap with many other integration or data management skills. Only the brand name prevents a score of 1. | 2 / 3 |
Total | 8 / 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.
This skill suffers severely from an enormous, seemingly auto-generated list of 150+ entity types that dominates the content and provides no actionable guidance. The Membrane CLI integration instructions are reasonable but generic across all Membrane-based skills, with minimal Adversus-specific examples or workflows. The description of Adversus as a 'competitive intelligence platform' appears inaccurate given the entity types listed (which resemble a legal practice management system).
Suggestions
Remove or drastically reduce the 150+ entity bullet list — it wastes tokens and provides no actionable value. If needed, move it to a separate ENTITIES.md reference file.
Add concrete end-to-end examples showing actual Adversus workflows (e.g., creating a lead with specific input JSON and expected output).
Fix the inaccurate description of Adversus — verify what the platform actually does and align the overview with its real capabilities.
Add error handling guidance and validation steps for common failure scenarios when running Adversus actions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The massive bullet-point list of 150+ entity types (Case, Contact, Task, etc.) is overwhelmingly verbose and provides no actionable value. Many of these entities appear to be from a legal practice management system, not a competitive intelligence platform like Adversus, suggesting this is copy-pasted boilerplate. The description of Adversus itself is also inaccurate/generic. | 1 / 3 |
Actionability | The Membrane CLI commands are concrete and executable (install, login, connect, action list/run), but the skill provides no Adversus-specific executable examples. The popular actions table is helpful but lacks example input/output for any of them. No concrete example of running an Adversus action end-to-end. | 2 / 3 |
Workflow Clarity | The authentication and connection flow is reasonably sequenced (install → login → connect → search → run), and the action creation flow includes polling with state checks. However, there are no validation checkpoints for verifying connection success, no error handling guidance for failed action runs, and no feedback loops for common failure scenarios. | 2 / 3 |
Progressive Disclosure | The content has some structure with sections (Overview, Working with Adversus, Best practices), but the enormous entity list should be in a separate reference file or removed entirely. The skill is monolithic with no references to external files for detailed information about specific entities or advanced usage. | 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
- membranedev/application-skills
- Commit
56d7336
- 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.