affinda
Affinda integration. Manage data, records, and automate workflows. Use when the user wants to interact with Affinda data.
52
58%
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/affinda/SKILL.mdQuality
Discovery
40%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 relies heavily on the 'Affinda' brand name for differentiation but fails to describe what Affinda actually does or what specific capabilities this skill provides. The actions listed are generic placeholders that could apply to virtually any data platform integration. Without domain-specific terms or concrete actions, Claude would struggle to select this skill appropriately except when a user explicitly mentions 'Affinda'.
Suggestions
Replace vague actions with Affinda-specific capabilities (e.g., 'Parse resumes and CVs, extract invoice data, process document fields' — whatever Affinda actually does).
Expand the 'Use when' clause with natural trigger terms users would say, such as 'resume parsing', 'CV extraction', 'invoice processing', or specific file types Affinda handles.
Add domain-specific keywords that distinguish this from other data management or workflow automation skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'manage data, records, and automate workflows' without specifying any 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 has a 'Use when' clause ('Use when the user wants to interact with Affinda data'), but the 'what' is extremely vague and the 'when' is essentially a tautology — it just restates the product name without providing meaningful trigger guidance. | 2 / 3 |
Trigger Term Quality | It includes 'Affinda' as a key trigger term, which is specific and useful for matching. However, it lacks natural keywords users might say related to Affinda's actual domain (e.g., 'resume parsing', 'document extraction', 'invoice processing', 'CV analysis'). | 2 / 3 |
Distinctiveness Conflict Risk | 'Affinda' as a proper noun provides some distinctiveness, but the generic phrases 'manage data, records, and automate workflows' could easily overlap with many other integration or data management skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid integration skill with strong actionability and workflow clarity—every step has concrete CLI commands and the connection state machine is well-documented with explicit branching. The main weaknesses are moderate verbosity (introductory fluff, a large table of actions with no descriptions) and lack of progressive disclosure structure for what is a fairly long document.
Suggestions
Remove or drastically shorten the introductory paragraph about what Affinda is—Claude already knows this and it wastes tokens.
Either add meaningful descriptions to the popular actions table or remove entries with 'No description' to reduce noise.
Consider extracting the proxy requests section and the popular actions table into separate reference files to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanatory context (e.g., 'Recruiters and HR departments use it to automate resume screening...') and the popular actions table has 'No description' for every entry, adding bulk without value. The Membrane CLI setup and connection flow are reasonably efficient but could be tightened. | 2 / 3 |
Actionability | The skill provides concrete, copy-paste-ready CLI commands for every step: installation, authentication, connection setup, action discovery, action execution, and proxy requests. Flag tables and JSON parameter examples are specific and executable. | 3 / 3 |
Workflow Clarity | The connection workflow is clearly sequenced with explicit state checks (READY, BUILDING, CLIENT_ACTION_REQUIRED, errors), polling instructions, and conditional branching. The overall flow from install → auth → connect → discover → run is well-structured with validation checkpoints at each state transition. | 3 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but it's a long monolithic file with no references to supporting documents. The popular actions table with empty descriptions adds clutter that could be offloaded or removed. No bundle files exist to support progressive disclosure. | 2 / 3 |
Total | 10 / 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
f484c82
- 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.