Tessl • The management layer for AI agent skills

SkillPublic

omni-tunnels

Create and manage secure tunnels (ngrok, Cloudflare Tunnel, custom) to expose OmniRoute to the internet or share access with remote agents and CI pipelines.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-tunnels/SKILL.md

Quality

Content

41%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 token-efficient, cleanly sectioned auto-generated stub, but it contains essentially no actionable guidance for the skill's stated purpose — no tunnel commands, no workflow, and an explicitly empty endpoints section. It reads as scaffolding awaiting content rather than a usable skill.

Suggestions

Add concrete, executable tunnel commands (e.g., `ngrok http 8080`, `cloudflared tunnel --url http://localhost:8080`) with a short example for each supported provider.

Define a step-by-step workflow: start the local service -> create the tunnel -> verify the public URL responds -> configure the tunnel for remote agents/CI.

Add a verification step (curl the public URL, check tunnel status) since exposing services to the internet is a risky operation that currently has no validation checkpoint.

Remove the verbatim duplicate of the frontmatter description in the Overview section to reclaim tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept over-explanation and assumes Claude's competence, but the Overview section restates the frontmatter description verbatim, a minor redundancy that keeps it from 'every token earns its place' (5).	4 / 5
Actionability	Only two concrete details exist (`POST /api/auth/login` and `REQUIRE_API_KEY=false`); the skill's stated purpose — creating ngrok/Cloudflare tunnels — has no commands, code, or steps at all, and 'No endpoints mapped for this area yet' confirms the gap, matching 'minimal concrete guidance; missing the specific steps'.	2 / 5
Workflow Clarity	There is no sequence whatsoever for the skill's core task: no tunnel-creation steps, no management steps, and no validation checks, matching 'steps missing or incoherent; no sequence' rather than a rough-but-present sequence (2).	1 / 5
Progressive Disclosure	The body is under 50 lines with clear, well-organized sections and one clearly signaled external pointer (`docs/openapi.yaml` / `GET /api/openapi/spec`); a missing blank line before the Payloads heading and a reference to a file outside the bundle keep it just below 5.	4 / 5
	Total	11 / 20 Passed

Description

66%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.

A specific, tool-named description with good natural trigger terms, but it lacks any explicit 'Use when...' guidance and leans on two generic verbs ('create and manage'), leaving the 'when' question unanswered. Adding an explicit trigger clause would raise completeness substantially.

Suggestions

Add a 'Use when...' clause (e.g., 'Use when exposing a local service to the internet, testing webhooks, or sharing access with remote agents') to answer the 'when' explicitly.

Include common synonyms such as 'port forwarding', 'webhook testing', or 'localhost URL' to broaden natural trigger coverage.

Replace the open-ended 'custom' with one or two named alternatives or drop it to keep the capability list concrete.

Dimension	Reasoning	Score
Specificity	Names concrete tools ("ngrok, Cloudflare Tunnel") and several actions ("Create and manage", "expose", "share access") with specific contexts ("remote agents and CI pipelines"), but "custom" is open-ended and coverage of management operations is thin — matching 'several specific actions; minor gaps' rather than comprehensive (5) or minimal (3).	4 / 5
Completeness	Has a clear 'what' (create/manage secure tunnels with named tools) but no 'Use when...' clause or equivalent trigger guidance; the 'when' is only weakly implied by purpose phrases, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Includes natural terms users would say — "tunnels", "ngrok", "Cloudflare Tunnel", "expose... to the internet", "CI pipelines" — but misses common synonyms like "port forwarding", "webhook", or "localhost", matching 'good keyword coverage; a few natural terms missing'.	4 / 5
Distinctiveness Conflict Risk	Tunneling with named tools and a specific product (OmniRoute) is a fairly distinct niche with only minor overlap risk against general networking/deployment skills; not a fully closed niche with explicit triggers, so 4 rather than 5.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: diegosouzapw/OmniRoute
Path: skills/omni-tunnels/SKILL.md
Revision: 5b3be70

Reviewed: 25 days ago

Discovery Implementation Validation

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.

omni-tunnels

Table of Contents

Is this your skill?