CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

use-native-credential-proxy

Replace OneCLI gateway with the built-in credential proxy. For users who want simple .env-based credential management without installing OneCLI. Reads API key or OAuth token from .env and injects into container API requests.

Quality

86%

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

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.

A strongly executable, well-sequenced migration procedure with genuine validation gates, troubleshooting, and rollback — the body tells Claude exactly what to run and how to confirm success. Its only notable weakness is the absence of any progressive disclosure: all ~160 lines live in SKILL.md with nothing split into reference files.

DimensionReasoningScore

Conciseness

The body is command-driven with almost no padding — every phase is concrete commands plus one-line intent. Minor trimmable bits: the opening paragraph re-states the frontmatter description, and the Phase 3 'description:' strings add a little bulk. Fits 'efficient; minor instances of over-explanation' rather than the perfectly lean anchor 5.

4 / 5

Actionability

Fully executable throughout: exact grep/git/npm/vitest commands, concrete env var names (CLAUDE_CODE_OAUTH_TOKEN, ANTHROPIC_API_KEY, CREDENTIAL_PROXY_PORT, CREDENTIAL_PROXY_HOST), expected log output ('Credential proxy started'), and copy-paste troubleshooting commands including a curl probe. Covers the common cases (subscription vs API key paths) completely.

5 / 5

Workflow Clarity

Clear phased sequence (pre-flight → apply → setup → verify → troubleshoot → removal) with explicit validation checkpoints: 'All tests must pass and build must be clean before proceeding', an expected log line to check, a live test message, conflict-resolution guidance for the merge, a Troubleshooting section for error recovery, and a documented rollback. Matches the anchor with explicit validation and feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist, and the skill is entirely self-contained at ~160 lines with well-organized section headers (Phases 1-4, Troubleshooting, Removal). Structure is good and navigation is easy, but everything is inline in one file — the over-50-lines simple-skill exception doesn't apply, so it sits at 'good structure; most content appropriately placed' rather than a 5 with well-signaled separate references.

4 / 5

Total

18

/

20

Passed

Description

78%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, well-targeted description that clearly states what the skill does and for whom, with minimal conflict risk. Its main weaknesses are a missing literal 'Use when...' trigger phrasing and a few absent natural synonyms ('environment variables', 'migrate from OneCLI').

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to replace or remove OneCLI, or asks for .env/environment-variable-based credential management.'

Include natural synonyms and phrasings users would say: 'environment variables', 'env file', 'migrate from OneCLI', 'switch credential provider'.

Optionally surface one more concrete capability (e.g. verification of proxy startup or rollback to OneCLI) to close the coverage gap.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Replace OneCLI gateway with the built-in credential proxy', 'Reads API key or OAuth token from .env', 'injects into container API requests' — but coverage has minor gaps (no hint of the setup, verification, or troubleshooting scope the skill actually covers). Fits the 'several specific actions; minor gaps' anchor rather than the comprehensive anchor 5.

4 / 5

Completeness

The 'what' is clear and concrete. The 'when' is explicitly stated as 'For users who want simple .env-based credential management without installing OneCLI', which functions as explicit trigger guidance, but it is phrased as an audience description rather than a literal 'Use when...' trigger clause and could be more trigger-shaped. Matches anchor 4 ('when' present but could be more explicit), not anchor 3 where 'when' is only weakly implied.

4 / 5

Trigger Term Quality

Good keyword coverage: 'credential proxy', '.env', 'API key', 'OAuth token', 'OneCLI', 'container'. A few natural terms users might say are missing, e.g. 'environment variables', 'env file', 'migrate from / remove OneCLI', 'secrets'. Falls between the good-coverage (4) and comprehensive (5) anchors, closer to 4.

4 / 5

Distinctiveness Conflict Risk

Highly distinct niche — names the exact predecessor ('OneCLI'), the replacement ('built-in credential proxy'), and the mechanism ('.env', 'container API requests'). Minimal overlap risk with any other skill; matches the clear-niche anchor.

5 / 5

Total

17

/

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

jbaruch/nanoclaw-telegram

Path

.claude/skills/use-native-credential-proxy/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.