CtrlK
BlogDocsLog inGet started
Tessl Logo

reverse-proxy-and-tunnel

Configures Nginx/Caddy reverse proxies and Cloudflare/WireGuard tunnels for safe homelab service exposure.

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/reverse-proxy-and-tunnel/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 skill body is exceptionally lean and well-structured with clear navigation and a useful safety section, but its access-pattern guidance stays at a high level without executable commands or embedded validation checkpoints. Adding concrete commands and inline validation steps would raise actionability and workflow clarity.

Suggestions

Replace high-level hints with executable commands, e.g. `cloudflared tunnel create <name>` and `cloudflared tunnel route dns <name> subdomain.domain.com`.

Embed validation checkpoints inside each pattern (e.g., 'curl the local service first, then verify the tunnel returns 200') rather than only in the standalone Safety section.

Show a minimal Nginx server-block example with the Certbot command (`sudo certbot --nginx -d subdomain.domain.com`) so the Nginx path is copy-paste ready like the Caddy path.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: no concept explanations of what a reverse proxy is, just tool-specific patterns and a one-line Caddyfile snippet, with every section earning its place.

5 / 5

Actionability

Provides some concrete guidance (a Caddyfile snippet, the /etc/nginx/sites-available/ path, Certbot mention) but most patterns are high-level hints ('Install cloudflared', 'Authenticate', 'Create a tunnel') without actual executable commands, leaving key details missing.

3 / 5

Workflow Clarity

Each access pattern lists a rough sequence, and the Safety section includes a validation note ('Validate DNS propagation before considering a tunnel live'), but validation checkpoints are not embedded in the per-pattern workflows and feedback loops are implicit.

3 / 5

Progressive Disclosure

Well under 50 lines with cleanly organized sections (Invocation, Access Patterns, Safety, Companion Skills, References) and clearly signaled one-level-deep external documentation links; no bundle files are needed and none are missing.

5 / 5

Total

16

/

20

Passed

Description

61%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 is concise, third-person, and names specific tools and a clear niche, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness. Trigger-term coverage is strong but not exhaustive.

Suggestions

Add an explicit trigger clause, e.g., 'Use when exposing homelab services to the internet or setting up a reverse proxy / tunnel.'

Mention Tailscale alongside Cloudflare/WireGuard in the description since it appears in the body as a supported option.

List a second concrete action (e.g., '...and secures them with TLS') to lift specificity toward a 4.

DimensionReasoningScore

Specificity

Names the domain (reverse proxies/tunnels) and tools (Nginx, Caddy, Cloudflare, WireGuard) with one concrete action ('Configures'), but does not enumerate several distinct actions, so it is not comprehensive enough for a 4.

3 / 5

Completeness

Has a clear 'what' (configures proxies/tunnels for safe exposure) but no explicit 'Use when...' trigger clause, and per the rubric a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms users would say ('reverse proxy', 'Nginx', 'Caddy', 'Cloudflare', 'WireGuard', 'homelab'), with good coverage; misses a few natural synonyms (e.g., Tailscale) so it stops short of 5.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (homelab service exposure with named proxy/tunnel tools) with distinct triggers; minor overlap risk with a generic Nginx/networking skill keeps it just below 5.

4 / 5

Total

14

/

20

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
pvnkmnk/AgenticSelfHostSkills
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.