CtrlK
BlogDocsLog inGet started
Tessl Logo

helpdesk-automation

Automate HelpDesk tasks via Rube MCP (Composio): list tickets, manage views, use canned responses, and configure custom fields. Always search tools first for current schemas.

47

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/helpdesk-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a reasonable catalog of HelpDesk tools and their parameters but suffers from significant redundancy (pagination explained three times) and over-explanation of concepts Claude already understands. The workflows are mostly single-tool operations dressed up as multi-step processes, and the skill lacks executable examples with concrete parameter values that would make it truly actionable.

Suggestions

Consolidate the three separate pagination explanations into a single, concise section with a concrete example showing actual parameter values (e.g., next.value='2024-01-15T10:30:00Z', next.ID='ticket_abc123').

Remove obvious explanations Claude already knows (e.g., 'Canned responses are predefined templates for common replies', 'Custom fields extend the default ticket schema') to reduce token waste.

Add a concrete, end-to-end example showing an actual RUBE_SEARCH_TOOLS call followed by a HELPDESK_LIST_TICKETS call with real parameter values and expected response structure.

Remove the vacuous 'When to Use' footer section—it adds no information beyond what the title and description already convey.

DimensionReasoningScore

Conciseness

Significant verbosity throughout. The 'Pitfalls' sections for views, canned responses, and custom fields explain obvious concepts Claude already knows (e.g., 'Canned responses are predefined templates for common replies', 'Custom fields extend the default ticket schema'). The pagination explanation is repeated three times (in workflow 1, Common Patterns, and Known Pitfalls). The 'When to Use' footer is vacuous.

2 / 5

Actionability

Tool names and parameters are clearly listed, which is helpful. However, there are no executable code examples—only pseudocode-style sequences. The pagination pattern is described in prose rather than showing an actual tool call with concrete parameter values. The guidance is specific enough to follow but not copy-paste ready.

3 / 5

Workflow Clarity

Workflows are sequenced but most are single-step operations (list views, list canned responses, list custom fields) that don't really constitute workflows. The multi-step pagination pattern lacks validation checkpoints—there's no guidance on verifying response integrity, handling empty results, or error recovery beyond a brief mention of 429 backoff. The setup section has a reasonable 4-step sequence with a validation checkpoint (confirm ACTIVE status).

3 / 5

Progressive Disclosure

The content is structured with clear headers and a quick reference table, which aids navigation. However, there are no bundle files and no references to external documents. The repeated pagination information across multiple sections suggests content could be better organized. For a skill of this length (~150 lines), some content consolidation or splitting would improve organization.

3 / 5

Total

11

/

20

Passed

Description

58%Scale 1-5

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 provides a reasonable set of concrete actions and identifies the specific platform (HelpDesk via Rube MCP/Composio), giving it decent specificity and distinctiveness. However, it lacks an explicit 'Use when...' clause, which is critical for Claude to know when to select this skill. The trigger terms could also be expanded with more natural user language and synonyms.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about HelpDesk tickets, support requests, help desk automation, or Composio integrations.'

Include natural synonyms and variations users might say, such as 'support tickets', 'customer support', 'help desk', 'ticket system', or 'support queue'.

Expand the action list to cover additional common operations like 'create tickets', 'update ticket status', 'assign tickets to agents', or 'search tickets'.

DimensionReasoningScore

Specificity

Lists several specific actions: 'list tickets', 'manage views', 'use canned responses', 'configure custom fields'. These are concrete actions, though coverage could be more comprehensive (e.g., creating tickets, updating ticket status, assigning tickets).

4 / 5

Completeness

Has a clear 'what' (automate HelpDesk tasks with specific actions listed) but lacks an explicit 'when' clause. The instruction to 'always search tools first' is operational guidance rather than a trigger condition. No 'Use when...' clause is present, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes relevant terms like 'HelpDesk', 'tickets', 'canned responses', 'custom fields', and 'views', but misses common synonyms and natural phrases users might say such as 'support tickets', 'help desk', 'ticket management', 'customer support', or the specific product name variations.

3 / 5

Distinctiveness Conflict Risk

Specifying 'HelpDesk' and 'Rube MCP (Composio)' makes it fairly distinct from generic ticketing or support skills. The specific tool integration (Composio) and product name (HelpDesk) reduce overlap risk, though 'tickets' and 'views' could overlap with other ticketing system skills.

4 / 5

Total

14

/

20

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.