CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

freshdesk-automation

Automate Freshdesk helpdesk operations including tickets, contacts, companies, notes, and replies via Rube MCP (Composio). Always search tools first for current schemas.

Quality

68%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/freshdesk-automation/SKILL.md

The canonical home for this skill is freshdesk-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-5

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

The body is a dense, actionable reference rich in non-obvious API quirks, with clearly sequenced per-workflow tool lists. Its weaknesses are repetition of the same facts across sections, missing post-operation validation for batch/update operations, and a fully inlined structure with no reference files.

Suggestions

Deduplicate repeated facts (status/priority mappings, the 300-result search limit, the double-quoted query rule) into the single "Known Pitfalls" section and remove them from per-workflow parameter lists.

Add validation steps after batch and mutating operations, e.g., after `FRESHDESK_IMPORT_CONTACT` list the imported contacts to verify, and after `FRESHDESK_UPDATE_TICKET` view the ticket to confirm the change.

Remove the content-free "When to Use" section, and consider splitting the Quick Reference table and full parameter documentation into a references/ file to shorten the main SKILL.md.

DimensionReasoningScore

Conciseness

Most content is Freshdesk-specific fact Claude cannot know (e.g., "Custom field keys must be prefixed with `cf_`", "Query string limited to 512 characters"), but status/priority mappings are repeated three times (workflow 1, workflow 2, and "Parameter Quirks"), the 300-result search limit appears three times, and the "When to Use" section ("This skill is applicable to execute the workflow or actions described in the overview.") is content-free filler. Not 4 because the redundancy and filler exceed minor trimmable instances.

3 / 5

Actionability

Concrete tool slugs, Required/Optional markers, exact parameter names, and copy-ready query syntax examples (e.g., "email:'user@example.com'" and "status:2 AND priority:3"). Not 5 because there is no complete worked example of a full tool invocation (e.g., a filled-out create-ticket call with actual values); not 3 since the guidance is fully concrete, not pseudocode.

4 / 5

Workflow Clarity

Each workflow has a numbered tool sequence with Required/Optional markers, and setup includes validation ("Confirm connection status shows ACTIVE before running any workflows"), plus a prerequisite verification step ("Verify ticket exists and check current state"). However, batch and mutating operations such as `FRESHDESK_IMPORT_CONTACT` (bulk CSV import) and ticket/company updates lack post-operation verification steps — per the judging guidelines, missing validation in batch operations caps workflow clarity at 3.

3 / 5

Progressive Disclosure

The body is well sectioned (Prerequisites, Setup, Core Workflows, Common Patterns, Known Pitfalls, Quick Reference), but everything is inlined in a single ~220-line file with no bundle/reference files; the full parameter reference and the 20-row quick-reference table are detail that could be split out. Not 4 because no external references exist and clearly separable content is inline; not 2 because headers provide real, navigable structure.

3 / 5

Total

13

/

20

Passed

Description

65%Weight 40%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 clearly identifies a distinct product niche with concrete object coverage, but the action verb is generic and there is no explicit "Use when..." trigger guidance, which limits both completeness and specificity.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user mentions Freshdesk, helpdesk tickets, support requests, or customer support operations."

Replace "Automate ... operations" with specific actions, e.g., "Create, update, search, and reply to Freshdesk tickets; manage contacts and companies."

Include natural synonyms such as "support tickets" and "customer support" to broaden trigger term coverage.

DimensionReasoningScore

Specificity

"Automate Freshdesk helpdesk operations including tickets, contacts, companies, notes, and replies" names the domain and five concrete objects, but the only action verb is generic ("Automate ... operations") — specific actions like create/update/search tickets are not listed. Not 4 because several specific actions are absent; not 2 because it enumerates concrete capabilities well beyond a bare domain name.

3 / 5

Completeness

The "what" is clear ("Automate Freshdesk helpdesk operations including tickets, contacts, companies, notes, and replies via Rube MCP (Composio)"), but there is no "Use when..." clause or equivalent trigger guidance — per the judging guidelines this caps completeness at 3. Not 4 because the "when" is entirely absent, not merely imprecise.

3 / 5

Trigger Term Quality

"Freshdesk", "helpdesk", "tickets", "contacts", "companies", "notes", "replies" are natural terms users would say. Not 5 because common synonyms like "support tickets" and "customer support" are missing; not 3 because coverage goes well beyond one or two generic keywords.

4 / 5

Distinctiveness Conflict Risk

"Freshdesk" is a unique named product, giving the skill a clear niche with minimal overlap risk against other skills. Not 4 because the trigger is a specific product name rather than a broad category with closely related neighbors.

5 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/freshdesk-automation/SKILL.md

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.