CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloud-cli

Sign a cloud provider's CLI in (AWS, Google Cloud, Azure, or another) with a device-code flow, then run that CLI as the requesting user. Covers checking the CLI is installed, the login that survives the browser round-trip, and the boundaries on cloud writes.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills-seed/cloud-cli/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 lean and packed with environment-specific knowledge Claude cannot infer — why localhost-redirect logins fail, the exact device-code flag per provider, the AWS CLI v2.22 PKCE default, and the glibc requirement. Validation and retry guidance are present, and the only notable gaps are the missing concrete install/config examples and the absence of a consolidated step sequence.

Suggestions

Add one concrete install example (e.g. the AWS CLI v2 installer command targeting $HOME) and a sample `[sso-session ...]` block plus profile for ~/.aws/config to close the actionability gaps.

Consolidate the runtime flow into a short numbered sequence (check installed → device-code login via interactive-login → verify with the whoami command → save to keychain → run with execute.credentials) so the order is explicit.

Consider moving the operator-facing "Go-live" setup into a reference file so SKILL.md stays a lean runtime overview.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — "Do not assume the binary is on PATH. The sandbox image ships a small, fixed tool set" — with no padding on concepts Claude already knows; only minor instances could be trimmed ("no amount of keeping the box warm can rescue it" and the opaque Boundaries policy paragraph), so it sits just below the every-token-earns-its-place anchor.

4 / 5

Actionability

Copy-paste-ready commands throughout: `command -v aws || echo "not installed"`, the full login/verify table (`aws sso login --use-device-code` / `aws sts get-caller-identity`, `gcloud auth login --no-launch-browser`, `az login --use-device-code`), plus explicit anti-commands ("Never run the bare form"); the gaps are the missing concrete install command and the absent example `[sso-session …]` config block, keeping it below fully-executable anchor 5.

4 / 5

Workflow Clarity

A clear section sequence (check install → device-code login → verify → boundaries → go-live) with explicit validation checkpoints (the Verify column, "Verify the provider account, region, target, and authority before acting") and an error-recovery loop ("These logins self-expire in roughly ten minutes, so if the user takes too long, start a fresh one"); it falls short of anchor 5 only because there is no consolidated numbered step list or checklist.

4 / 5

Progressive Disclosure

A single well-organized file (~85 lines) with clear section headers and clearly signaled cross-skill references (`interactive-login`, `use-shared-credential`); it is above the compact-skill threshold where sections alone would earn a 5, and the operator-facing "Go-live" section could arguably live in a reference file — good structure with a minor organization gap.

4 / 5

Total

16

/

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 clearly and concretely states what the skill does, with strong provider-name triggers and a distinct niche. Its main weakness is the complete absence of a 'Use when...' trigger clause, which caps completeness at 3 despite otherwise strong specificity and distinctiveness.

Suggestions

Add an explicit trigger clause, e.g. "Use when a task needs a cloud provider CLI (aws, gcloud, az) signed in and run as the requesting user", to lift completeness from 3.

Include natural CLI-name synonyms users actually say — "aws cli", "gcloud", "az", "log into AWS/Azure" — alongside the provider names to improve trigger term coverage.

Replace the abstract phrase "the boundaries on cloud writes" with a concrete action statement such as "gates mutating cloud writes behind user approval".

DimensionReasoningScore

Specificity

Quotes like "Sign a cloud provider's CLI in (AWS, Google Cloud, Azure, or another) with a device-code flow, then run that CLI as the requesting user" and "checking the CLI is installed" list several concrete actions, but "the boundaries on cloud writes" is abstract rather than a concrete action — a minor coverage gap that places this between anchors 4 and 5.

4 / 5

Completeness

The 'what' is clear and concrete, but there is no "Use when..." clause or equivalent explicit trigger guidance anywhere in the description; the 'when' is only weakly implied by the provider names, so per the judging guidelines completeness is capped at 3.

3 / 5

Trigger Term Quality

Strong natural keywords users would say — "AWS", "Google Cloud", "Azure", "CLI", "sign in", "login", "device-code" — but common synonyms such as "aws cli", "gcloud", "az", or "authenticate" are missing, matching the 'good coverage, a few natural terms missing' anchor rather than the comprehensive one.

4 / 5

Distinctiveness Conflict Risk

The device-code cloud CLI sign-in niche with distinct provider-name triggers is well differentiated, but the skill sits in a family of closely related credential/login skills (the body itself references `interactive-login` and `use-shared-credential`), leaving minor overlap risk — anchor 4 rather than 5.

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

yc-software/qm

Path

skills-seed/cloud-cli/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.