project-tooling

gh, vercel, supabase, render CLI and deployment platform setup

Quality

32%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/project-tooling/SKILL.md

Quality

Discovery

22%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is essentially a list of tool names with a vague category label ('deployment platform setup'). It lacks concrete actions, explicit trigger guidance, and a 'Use when...' clause, making it difficult for Claude to reliably select this skill at the right time. The tool names provide some distinctiveness but are insufficient on their own.

Suggestions

Add specific concrete actions for each tool, e.g., 'Authenticates and configures gh CLI, deploys projects to Vercel, provisions Supabase databases, and sets up Render services.'

Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to set up, configure, or deploy to Vercel, Supabase, Render, or authenticate with GitHub CLI.'

Include natural trigger term variations users might say, such as 'deploy', 'hosting', 'GitHub CLI login', 'database provisioning', 'cloud setup', or 'CI/CD configuration'.

Dimension	Reasoning	Score
Specificity	The description only names tools/platforms ('gh, vercel, supabase, render CLI') and vaguely says 'deployment platform setup' but does not list any concrete actions like 'configure projects', 'deploy applications', 'manage environment variables', etc.	1 / 3
Completeness	The description weakly addresses 'what' (setup of CLI and deployment platforms) but completely lacks a 'when should Claude use it' clause. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also very weak, so this scores a 1.	1 / 3
Trigger Term Quality	It includes some natural keywords users might say like 'gh', 'vercel', 'supabase', 'render', 'CLI', and 'deployment', but misses common variations like 'deploy', 'hosting', 'GitHub CLI', 'serverless', 'database setup', or specific actions users would request.	2 / 3
Distinctiveness Conflict Risk	Naming specific platforms (Vercel, Supabase, Render, gh) provides some distinctiveness, but 'deployment platform setup' is broad enough to overlap with general DevOps or infrastructure skills. The lack of specific actions makes it harder to distinguish from other deployment-related skills.	2 / 3
	Total	6 / 12 Passed

Implementation

42%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides highly actionable, executable commands and configurations for multiple deployment platforms, which is its primary strength. However, it is far too verbose — it tries to be a comprehensive reference for four CLI tools, CI/CD setup, and deployment configuration all in one file. The content would benefit enormously from splitting into per-tool reference files with a concise overview in the main SKILL.md.

Suggestions

Split per-tool content (Vercel, Supabase, Render, GitHub CLI) into separate reference files and keep SKILL.md as a concise overview with links — e.g., '**Vercel setup**: See [VERCEL.md](VERCEL.md)'

Remove content Claude already knows — basic git remote commands, curl syntax, and standard GitHub Actions boilerplate don't need to be spelled out

Move the validation script to an actual file reference (scripts/verify-tooling.sh) rather than inlining 40 lines in the skill

Add explicit verification steps after key deployment actions (e.g., 'After `vercel --prod`, verify with `vercel inspect <url>` to confirm deployment succeeded')

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~300+ lines, covering four different CLI tools with extensive setup instructions, CI/CD templates, deployment checklists, and render.yaml examples. Much of this is reference documentation Claude already knows (basic git commands, curl syntax, GitHub Actions structure). The validation script alone is ~40 lines that could be a file reference.	1 / 3
Actionability	The content provides fully executable, copy-paste ready commands and scripts throughout — bash verification commands, GitHub Actions YAML, render.yaml, package.json scripts, and curl API calls are all concrete and complete.	3 / 3
Workflow Clarity	Individual tool sections have clear steps, and the validation script provides a good checkpoint at initialization. However, the overall workflow for setting up a project end-to-end lacks explicit sequencing and validation checkpoints between stages (e.g., no verification after deployment, no feedback loop if Vercel link fails).	2 / 3
Progressive Disclosure	This is a monolithic wall of content with no references to external files. The CI/CD templates, render.yaml examples, validation script, and per-platform setup guides should be split into separate referenced files. Everything is inlined, making the skill very long and hard to navigate.	1 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: alinaqi/claude-bootstrap
Commit: d4ddb03

Reviewed: 4 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.