CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

iron-proxy-gateway

Use Iron Proxy for external accounts and APIs, including GitHub through gh. Connect credentials through the operator console and diagnose blocked requests without exposing tokens or adding unnecessary MCP servers.

Quality

81%

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

86%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 an exceptionally lean, policy-dense instruction set: one concrete command, explicit anti-patterns, and a clear handoff workflow with a verification checkpoint. Its only weakness is that the verification and diagnostic steps are described behaviorally rather than with executable commands or a numbered sequence.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — "A bare `403` does not prove which layer rejected the request" — with no padding or explanation of known concepts. The "## Rules" section lightly restates body points, but as a deliberate checklist rather than over-explanation, so anchor 5 fits better than 4.

5 / 5

Actionability

Provides a concrete executable command (`ncl groups connect --host <API hostname>`) plus specific directives such as "Return the exact `connect_url` and describe its `action`" and the `gateway-managed`/`GH_TOKEN` placeholder example. Minor gaps (no example of the verifying credentialed request) place it at anchor 4 rather than 5, and it is far above the pseudocode level of 3.

4 / 5

Workflow Clarity

The connect-account flow is sequenced with an explicit validation checkpoint — "verify with a credentialed request after the operator completes configuration. Never claim connected before success" — plus failure-diagnosis guidance ("A 401 is not proof that injection did not happen"). It falls short of anchor 5 because steps are prose rather than a numbered sequence and the verification step lacks a concrete command, but is above 3 since checkpoints are explicitly present.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (references/, scripts/, assets/ are absent), and the body is well organized into clearly signaled sections ("Policy failures", "Connect an account", "Rules") with all content appropriately inline at one level. Per the rubric guideline for short single-purpose skills, this fits anchor 5.

5 / 5

Total

18

/

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.

The description is specific, third-person, and reasonably rich in natural domain terms, but it lacks an explicit "Use when..." trigger clause, leaving the activation conditions only weakly implied. Trigger coverage is good but misses common phrasings users would say when hitting proxy or auth failures.

Suggestions

Add an explicit trigger clause, e.g. "Use when connecting external accounts or APIs, when requests fail with 403/401 or proxy errors, or when the user mentions Iron Proxy, gh authentication, or blocked requests."

Include natural user-phrase synonyms such as "proxy error", "blocked", "authentication failure", and "connect an account" alongside the existing technical terms.

Briefly state what diagnosing blocked requests involves (report hostname and observed error, request a host-side check) so the "what" is more complete.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Connect credentials through the operator console", "diagnose blocked requests", "including GitHub through gh" — with minor gaps in coverage. It is above anchor 3 (more than 1-2 generic actions) but not anchor 5 (only two or three actions, not comprehensive).

4 / 5

Completeness

The "what" is clear and specific, but there is no "Use when..." clause or equivalent explicit trigger guidance; the "when" is only weakly implied by "for external accounts and APIs". Per the judging guidelines, a missing explicit trigger clause caps completeness at 3, and the clear "what" keeps it above 2.

3 / 5

Trigger Term Quality

Good natural-term coverage: "external accounts", "APIs", "GitHub", "gh", "credentials", "tokens", "MCP servers", "blocked requests". Missing common user-phrase variations such as "proxy error", "403", or "authentication failure", so it fits anchor 4 rather than 5 and is clearly above 3.

4 / 5

Distinctiveness Conflict Risk

Names a distinct niche ("Iron Proxy", "operator console", "gh", "MCP servers") that is unlikely to trigger the wrong skill, with only minor overlap risk against general proxy/networking skills. Not anchor 5 because trigger phrases are not fully distinctive across all network-error scenarios.

4 / 5

Total

15

/

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

nanocoai/nanoclaw

Path

.claude/skills/add-iron-proxy/payload/container/skills/iron-proxy-gateway/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.