agendor
Agendor integration. Manage data, records, and automate workflows. Use when the user wants to interact with Agendor data.
68
61%
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/agendor/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 (Agendor) and including an explicit 'Use when' clause, but it is severely lacking in specificity about what concrete actions the skill performs. The capabilities listed are generic enough to describe almost any data integration, making it hard for Claude to confidently select this skill over others in a large skill library.
Suggestions
Replace vague terms like 'manage data, records, and automate workflows' with specific Agendor actions such as 'create and update deals, manage contacts, track sales pipeline stages, log activities'.
Add natural trigger terms users would say, such as 'CRM', 'sales pipeline', 'deals', 'contacts', 'leads', or 'Agendor API'.
Expand the 'Use when' clause with more specific triggers, e.g., 'Use when the user mentions Agendor, needs to manage CRM contacts, track deals, or automate sales workflows.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'manage data, records, and automate workflows' without specifying concrete actions. It doesn't clarify 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 Agendor data) with an explicit 'Use when' clause, even though both parts are vague in substance. | 3 / 3 |
Trigger Term Quality | It includes 'Agendor' as a key trigger term which is specific to the platform, but lacks natural variations users might say such as CRM, contacts, deals, sales pipeline, leads, or other Agendor-specific entity names. | 2 / 3 |
Distinctiveness Conflict Risk | 'Agendor' as a proper noun provides some distinctiveness, but 'manage data, records, and automate workflows' is so generic it could overlap with many other integration skills. Without mentioning CRM-specific or Agendor-specific concepts, it risks conflicting with other data management tools. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides solid, actionable CLI commands for Agendor integration via Membrane, with a clear installation-to-execution flow. Its main weaknesses are unnecessary introductory context, a bulky actions table with no descriptions adding little value, and missing validation/error-handling checkpoints in the workflow. Trimming the preamble and adding verification steps would significantly improve quality.
Suggestions
Remove or drastically shorten the opening paragraph explaining what Agendor is — Claude already knows this, and the skill description provides context.
Either add actual descriptions to the popular actions table or remove it and rely on the `membrane action list --intent` discovery mechanism instead.
Add explicit validation/verification steps after key operations (e.g., verify connection was created successfully, check action run output for errors).
Move the 'Agendor Overview' bullet list or replace it with something actionable — currently it lists Contact/Company/Task with no linked content or explanation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explaining what Agendor is (CRM, small businesses, etc.) is unnecessary context Claude already knows. The 'Agendor Overview' section with Contact/Company/Task bullet points adds little value. The popular actions table has 'No description' for every entry, adding bulk without information. However, the CLI commands and workflow sections are reasonably efficient. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready CLI commands for every step: installation, authentication, connecting, searching actions, creating actions, and running actions with parameters. The commands include specific flags (--json, --wait, --timeout) and clear parameter placeholders. | 3 / 3 |
Workflow Clarity | The multi-step workflow (install → authenticate → connect → search → run) is present and sequenced, but lacks explicit validation checkpoints. For example, after connecting there's no verification step, and after running actions there's no guidance on checking output validity or handling errors beyond the action creation polling section. | 2 / 3 |
Progressive Disclosure | The content is structured with clear headers and sections, and references official docs externally. However, the popular actions table (20 rows, all without descriptions) could be in a separate reference file, and the document is somewhat monolithic for its length. The 'Agendor Overview' section hints at structure but doesn't link to anything useful. | 2 / 3 |
Total | 9 / 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.