agiled
Agiled integration. Manage Organizations, Leads, Pipelines, Users, Goals, Filters. Use when the user wants to interact with Agiled data.
64
76%
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/agiled/SKILL.mdQuality
Discovery
75%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 adequately identifies the Agiled integration domain and provides an explicit 'Use when' clause, making it functional for skill selection. However, it relies on the generic verb 'Manage' rather than listing specific actions, and it could benefit from more natural trigger terms that users might use when referring to CRM-related tasks.
Suggestions
Replace the generic 'Manage' with specific actions like 'Create, update, delete, and search Organizations, Leads, Pipelines, Users, Goals, and Filters'.
Add natural trigger terms users might say, such as 'CRM', 'sales pipeline', 'deal tracking', or 'customer management' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Agiled) and lists entity types (Organizations, Leads, Pipelines, Users, Goals, Filters), but the action is only the generic 'Manage' rather than listing specific concrete actions like create, update, delete, search. | 2 / 3 |
Completeness | Answers both 'what' (manage Organizations, Leads, Pipelines, Users, Goals, Filters in Agiled) and 'when' ('Use when the user wants to interact with Agiled data'), providing an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes 'Agiled' as a key trigger term and entity names like 'Leads', 'Pipelines', 'Organizations' which users might mention, but misses common action-oriented terms users would say like 'CRM', 'sales pipeline', 'contacts', or 'deal tracking'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Agiled' is a specific product name that creates a clear niche, making it unlikely to conflict with other skills. The entity types listed further narrow the scope to this particular integration. | 3 / 3 |
Total | 10 / 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 excellent actionability and workflow clarity—every step has concrete, executable CLI commands and the connection state machine is well-documented with branching logic. The main weaknesses are some unnecessary introductory content (explaining what Agiled is, the sparse entity overview) and a slightly monolithic structure that could benefit from splitting reference material into separate files.
Suggestions
Remove the introductory paragraph explaining what Agiled is and the sparse 'Agiled Overview' entity list—Claude doesn't need this context and it wastes tokens.
Consider extracting the popular actions table and proxy request reference into separate bundle files (e.g., ACTIONS.md, PROXY.md) with clear links from the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explaining what Agiled is ('all-in-one business management platform...') is unnecessary context Claude already knows. The 'Agiled Overview' section listing entities without actionable detail adds little value. The Membrane CLI setup and connection flow is reasonably efficient but could be tighter. | 2 / 3 |
Actionability | The skill provides fully executable CLI commands for every step: installation, authentication, connection setup, action discovery, action execution, and proxy requests. Commands are copy-paste ready with clear parameter placeholders and flag descriptions. | 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 headless auth flow includes a clear feedback loop (login → get code → complete). The discover-then-run pattern is well-articulated. | 3 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but it's somewhat monolithic for its length (~150 lines). The popular actions table and proxy request details could be split into separate reference files. No bundle files are provided, and no external references beyond the Freshdesk docs link are offered for deeper content. | 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.