freshdesk-automation
Automate Freshdesk helpdesk operations including tickets, contacts, companies, notes, and replies via Rube MCP (Composio). Always search tools first for current schemas.
73
65%
Does it follow best practices?
Impact
82%
1.41xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/freshdesk-automation/SKILL.mdQuality
Discovery
67%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 reasonably strong in specificity and distinctiveness, clearly identifying Freshdesk as the target platform and listing concrete entity types it operates on. Its main weakness is the absence of an explicit 'Use when...' clause, which caps completeness at 2, and it could benefit from additional natural trigger term variations like 'support tickets' or 'customer support'.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Freshdesk, support tickets, helpdesk management, or customer support operations.'
Include common trigger term variations such as 'support tickets', 'customer support', 'help desk', 'ticket management', or 'CRM' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'tickets, contacts, companies, notes, and replies' and specifies the platform (Freshdesk) and integration method (Rube MCP/Composio). Also includes the operational guidance to 'search tools first for current schemas.' | 3 / 3 |
Completeness | Clearly answers 'what does this do' (automate Freshdesk helpdesk operations including tickets, contacts, etc.), but lacks an explicit 'Use when...' clause specifying when Claude should select this skill. The 'when' is only implied by the domain. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Freshdesk', 'helpdesk', 'tickets', 'contacts', 'companies', 'notes', and 'replies', which are natural terms users might say. However, it misses common variations like 'support tickets', 'customer support', 'help desk', 'ticket management', or 'CRM'. | 2 / 3 |
Distinctiveness Conflict Risk | Very clearly scoped to Freshdesk specifically, with distinct triggers like 'Freshdesk', 'helpdesk', and the Composio/Rube MCP integration. Unlikely to conflict with other skills unless there are multiple Freshdesk-related skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured API reference skill that clearly documents Freshdesk tool workflows with good sequencing and helpful pitfall callouts. Its main weaknesses are redundancy across sections (status/priority mappings repeated multiple times), lack of concrete executable examples showing complete tool invocations, and being overly long for a single file without progressive disclosure to supporting documents.
Suggestions
Add 1-2 complete executable examples showing actual tool call parameters as JSON objects (e.g., a full FRESHDESK_CREATE_TICKET call with all required fields filled in) to improve actionability.
Consolidate repeated reference data (status codes, priority values, cf_ prefix rules) into a single 'Reference Values' section or a separate REFERENCE.md file to reduce redundancy.
Extract the detailed parameter lists and the quick reference table into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with workflow sequences and key pitfalls only.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy — status/priority integer mappings are repeated three times (in create ticket, search tickets, and known pitfalls), and the custom field cf_ prefix note appears twice. The quick reference table at the end largely duplicates information already covered in the workflows. However, most content is genuinely useful reference material rather than explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter lists, and query syntax examples (e.g., `"email:'user@example.com'"`, `"status:2 AND priority:3"`), which is good. However, there are no complete executable workflow examples showing actual tool calls with full parameter objects — everything is described rather than demonstrated with concrete input/output examples. The guidance is specific but not copy-paste ready. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with numbered steps, labeled as [Required], [Optional], or [Prerequisite]. The setup section includes a verification flow (check connection → authenticate if needed → confirm ACTIVE). The tool sequences logically build on each other with clear ordering. The ID Resolution pattern provides a practical feedback loop for resolving identifiers before operations. | 3 / 3 |
Progressive Disclosure | The content is a monolithic single file with no bundle files to reference. At ~200+ lines, the detailed parameter lists, pitfalls sections, and the comprehensive quick reference table could benefit from being split into separate reference files. The structure within the file is well-organized with clear headers, but the sheer volume of inline reference material makes it heavy for a SKILL.md overview. | 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
- davepoon/buildwithclaude
- Commit
d065ead
- 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.