CtrlK
BlogDocsLog inGet started
Tessl Logo

twilio-taskrouter-routing

Route tasks to agents using Twilio TaskRouter. Covers Workers, Task Queues, Workflows, Reservations, skills-based routing, and common gotchas (hyphen attributes, HAS operator, reservation cascade). Use this skill for any multi-agent contact center, support queue, or AI agent escalation routing.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

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

A thorough, highly actionable TaskRouter skill with executable code throughout and a clear step-by-step Quickstart. Its main weaknesses are conciseness (Gotchas and CANNOT duplicate each other; dual-language full blocks inflate length) and missing explicit validation checkpoints in the main workflow, plus a monolithic single-file structure that forgoes progressive disclosure.

Suggestions

Collapse the Gotchas and CANNOT sections into a single canonical list to remove the duplicated hyphen/HAS/reservation-cascade/activity-flag entries and recover significant tokens.

Add explicit validation checkpoints to the Quickstart workflow (e.g. after creating a Workspace or Worker, assert the returned SID / fetch the resource to confirm attributes match) so the multi-step flow earns full workflow-clarity credit.

Extract the large CANNOT reference list and/or the full per-step dual-language code into one-level-deep reference files (e.g. reference/api-examples.md, reference/limits-and-gotchas.md) and link from SKILL.md so the overview stays lean.

DimensionReasoningScore

Conciseness

The body is largely concrete with no basic-concept filler, but the Gotchas (#1-4) and the CANNOT section substantially duplicate each other (hyphens, HAS, reservation cascade, activity flag all restated), and most Quickstart steps ship full Python and Node.js blocks, so it could be tightened. It is not a 1 because there is no padding explaining concepts Claude already knows, and not a 3 because real redundancy remains.

2 / 3

Actionability

Packed with fully executable, copy-paste-ready SDK calls across the whole lifecycle (e.g. `client.taskrouter.v1.workspaces(...).workers.create(...)`), concrete workflow_config JSON, and expression tables. Not a 2 because the code is complete and runnable rather than pseudocode.

3 / 3

Workflow Clarity

The Quickstart is a clearly numbered 7-step sequence (Workspace through Assignment Callback) with error-recovery patterns in the Gotchas, but the main workflow has no explicit validation checkpoints (e.g. verifying a resource was created or attributes match). Not a 1 because the sequence is present and well-ordered; not a 3 because validation steps are implicit/missing rather than explicit with feedback loops.

2 / 3

Progressive Disclosure

Sections are well-organized with clear headings and navigation, but this is a single ~410-line file with no bundle files and no one-level-deep `[X.md](X.md)` references, so content that could live in reference files (the extensive CANNOT list, dual-language full code blocks, gotchas) is all inline. Not a 1 because there are no nested or dead references; not a 3 because nothing is split across files and the under-50-lines exemption does not apply.

2 / 3

Total

9

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concise description that names concrete TaskRouter capabilities, provides natural trigger terms, and explicitly states both what the skill does and when to use it. It is clearly distinguishable from sibling Twilio skills and carries no vague fluff.

DimensionReasoningScore

Specificity

Names multiple concrete TaskRouter constructs ('Workers, Task Queues, Workflows, Reservations, skills-based routing') plus specific gotchas ('hyphen attributes, HAS operator, reservation cascade'). Not a 2 because the capability list is comprehensive and concrete rather than naming only the domain and a few actions.

3 / 3

Completeness

Explicitly answers both what ('Route tasks to agents using Twilio TaskRouter') and when ('Use this skill for any multi-agent contact center, support queue, or AI agent escalation routing'). Not a 2 because the explicit 'Use this skill for...' trigger clause is present, satisfying the cap exception.

3 / 3

Trigger Term Quality

Includes natural phrases a user would actually say ('multi-agent contact center, support queue, or AI agent escalation routing'). Not a 2 because it offers good coverage of natural terms rather than a single relevant keyword missing common variations.

3 / 3

Distinctiveness Conflict Risk

Names a specific product (Twilio TaskRouter) and a clear niche (contact center / support-queue / AI-escalation routing), making it unlikely to trigger for the wrong skill. Not a 2 because the niche and triggers are distinct rather than merely 'somewhat specific'.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.