terraform-cli-setup

Terraform CLI 安装与初始化技能。当用户本地未安装 Terraform 时自动完成安装，确保 terraform 命令可用并能执行 init/validate。不负责 Provider 凭证配置，凭证在实际使用时由 terraform-skill 引导。

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/bundle/cloudpaw/skills/terraform-cli-setup/SKILL.md

Quality

Content

77%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 content is highly actionable with executable commands, a verified helper script, and a clear validated workflow with error-recovery loops. Its weaknesses are verbosity from repeated mirror/error-handling content and limited progressive disclosure — most detail is inlined rather than split into reference files.

Suggestions

Deduplicate the mirror configuration: keep one canonical snippet in the China-mirror section and have the auto-fix block and quick-fix table reference it instead of repeating the full .terraformrc.

Move per-OS install steps (Homebrew / manual zip / apt / yum) into a references/ file (e.g. references/install-by-platform.md) and keep SKILL.md as a short overview that points to it.

Remove the explanatory bullets on what `terraform init` does internally (backend/provider/modules/lockfile); Claude already knows this and it adds tokens without adding guidance.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but padded: the same mirror configuration appears three times (auto-fix block, China-mirror section, and the quick-fix table), and the decision tree, auto-selection table, and quick-fix table restate overlapping error→fix mappings; it also over-explains what `terraform init` does (backend/provider/modules/lockfile) which Claude already knows.	3 / 5
Actionability	Provides copy-paste-ready bash for every install path (brew, manual zip, apt, yum), real `terraform init/validate/fmt` commands, a verified working script `scripts/setup_terraform.py` with concrete OS/arch detection, and exact mirror-config snippets — fully executable across the common cases.	5 / 5
Workflow Clarity	The four-step flow (detect → install → init → verify) has explicit validation checkpoints (`terraform version`, `terraform validate`) and real feedback loops (provider download fails → write .terraformrc → retry; lock-file/module errors → `terraform init -upgrade`), matching the anchor for clear sequences with error recovery.	5 / 5
Progressive Disclosure	A real bundle script is referenced and present, but the body itself is a long monolith — all OS install variants, mirror config, error tables, and the decision tree are inlined rather than split into per-OS reference files, so structure exists but content that belongs in separate files is not offloaded.	3 / 5
	Total	16 / 20 Passed

Description

67%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 concrete, third-person, and well-scoped with an explicit trigger and a clear boundary against the sibling terraform-skill. Its main weakness is limited trigger-term coverage — a single condition rather than the natural variations users say.

Suggestions

Add a "Use when..." clause enumerating natural triggers, e.g. "Use when `terraform` reports command not found, when `terraform init` fails on provider download, or when the user asks to install Terraform."

Include common synonyms/file extensions users mention, such as `terraform command not found`, `.tf` files, and `terraform init` failures, to broaden trigger-term coverage.

Keep the existing boundary clause but condense it — the credential disclaimer can be one short sentence.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "自动完成安装", "确保 terraform 命令可用并能执行 init/validate" — covering install, command availability, init, and validate, with only minor coverage gaps (no mention of mirror/backend configuration present in the body).	4 / 5
Completeness	Explicitly answers both what (install + ensure init/validate work) and when (when Terraform is not installed locally); the when clause is concrete but a single trigger rather than a full set, so it falls just short of the comprehensive anchor.	4 / 5
Trigger Term Quality	Contains one natural trigger phrase ("当用户本地未安装 Terraform 时") but misses common variations, synonyms, and the error signal ("command not found") that users actually encounter; coverage is relevant but not comprehensive.	3 / 5
Distinctiveness Conflict Risk	The explicit boundary clause "不负责 Provider 凭证配置...由 terraform-skill 引导" cleanly separates it from the related terraform-skill, leaving only minor overlap risk on generic "terraform" mentions; mostly distinct with a clear niche.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

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: agentscope-ai/QwenPaw
Path: plugins/bundle/cloudpaw/skills/terraform-cli-setup/SKILL.md
Commit: f6dbc1d

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.