CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloudflare-one

Design, configure, troubleshoot, or review Cloudflare One Zero Trust and SASE deployments. Use cloudflare-one-migrations for migration planning from other vendors.

Quality

83%

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

The canonical home for this skill is cloudflare-one in cloudflare/skills

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

This is a strong, expert-level skill body: highly actionable, tightly written, with a clear workflow, explicit validation checklists, and disciplined use of external docs as the source of truth for volatile details. The main improvements are trimming soft advisory sentences and the Assessment/Guardrails overlap, and splitting per-product reference material into bundle files.

Suggestions

Trim soft advisory sentences (e.g., the captive-portal friction note) and tighten the overlap between Assessment Prompts and Guardrails entries that restate the same split-tunnel and routing guidance.

Consider moving the longer per-product sections (Device Client Deployment, Infrastructure Access, Logs/Analytics/DEX) into references/ files keyed by task, keeping SKILL.md as the decision-level overview with pointers.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — nearly every line carries non-obvious domain knowledge ("`dns.domains` matches a domain and subdomains; `dns.fqdn` is exact-match only", the split-tunnel mode table). A few advisory sentences could be trimmed ("This is a common source of end-user friction and should be managed carefully") and some territory repeats between Assessment Prompts and Guardrails, keeping it below anchor 5.

4 / 5

Actionability

Guidance is concrete and executable throughout: exact API endpoint (`/access/policies`), exact formats (`non_identity@[team-domain].cloudflareaccess.com`), selector semantics, a copy-paste decision table mapping deployment goals to split-tunnel modes, and named log sources per troubleshooting question. As an instruction-only skill, its guidance is fully actionable and covers the common cases.

5 / 5

Workflow Clarity

The 5-step Workflow sequences classify → gather context → retrieve docs → inspect → propose with validation and rollback built into step 5, and staging ("disabled limited to a pilot") for risky changes. A dedicated Validation Prompts section provides per-product checklists, and troubleshooting guidance defines an explicit feedback loop ("work from logs toward config: identify the log entry showing the failure, then trace back to the responsible rule, route, or policy").

5 / 5

Progressive Disclosure

The single file is well-sectioned with clear headers and consistently well-signaled, one-level-deep external doc links (no nested references; no bundle files exist). It is not anchor 5 because ~175 lines of per-product deep-dives (Device Client Deployment, Infrastructure Access, Logs/DEX) read like material that could be split into per-product reference files to slim the always-loaded body.

4 / 5

Total

18

/

20

Passed

Description

70%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 states a clear, specific scope with concrete verbs and good distinctiveness, and it cleanly disambiguates from a sibling migrations skill. Its main weakness is the missing explicit "Use when..." trigger clause and the absence of product-level keywords (Access, Gateway, WARP, Tunnel) users commonly mention.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions Cloudflare One, Cloudflare Access, Gateway, WARP, Zero Trust, SASE, or private app/network access via Cloudflare."

Include the product names users actually say (WARP, Access, Gateway, Tunnel, ZTNA) as trigger keywords to improve matching.

Optionally state the migration boundary from this side too ("For vendor-to-vendor migration planning, use cloudflare-one-migrations instead") so the delegation reads as routing rather than a trigger.

DimensionReasoningScore

Specificity

"Design, configure, troubleshoot, or review Cloudflare One Zero Trust and SASE deployments" lists several specific actions on a named product family. It falls short of anchor 5 because it does not enumerate the concrete capability areas (Access, Gateway, WARP, Tunnel, DLP) that would give comprehensive coverage.

4 / 5

Completeness

The "what" is clear (design/configure/troubleshoot/review Cloudflare One Zero Trust and SASE deployments), but there is no "Use when..." trigger clause; the "Use cloudflare-one-migrations for migration planning" sentence routes to a sibling skill rather than stating when this skill applies, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

"Cloudflare One", "Zero Trust", "SASE", and "migration" are natural terms users would say, giving good keyword coverage. A few common variations users actually use — WARP, Access, Gateway, Cloudflare Tunnel, ZTNA — are missing, so it is not anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Cloudflare One Zero Trust and SASE deployments" carves out a clear niche, and explicitly delegating migration planning to "cloudflare-one-migrations" minimizes conflict with the closest related skill.

5 / 5

Total

16

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

freekmurze/dotfiles

Path

config/claude/skills/cloudflare-one/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.