project-tooling

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

Quality

32%

Does it follow best practices?

Impact

—

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 the word 'setup' appended. It lacks concrete actions, explicit trigger guidance, and any 'Use when...' clause. While the specific platform names provide some natural keywords, the description is too terse and vague to effectively guide skill selection.

Suggestions

Add a 'Use when...' clause specifying triggers, e.g., 'Use when the user needs to configure, authenticate, or deploy using GitHub CLI, Vercel, Supabase, or Render.'

List specific concrete actions the skill performs, such as 'Authenticates CLI tools, configures project settings, deploys applications, manages environment variables, and links repositories to hosting platforms.'

Include common user phrasing variations like 'deploy my app', 'set up hosting', 'connect to Vercel', 'configure Supabase', 'push to Render' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description only names tools/platforms ('gh, vercel, supabase, render CLI') and vaguely says 'setup' but does not describe any concrete actions like 'deploy applications', 'configure environments', 'manage secrets', etc.	1 / 3
Completeness	The description weakly addresses 'what' (setup of CLI and deployment platforms) but completely lacks any 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent.	1 / 3
Trigger Term Quality	It includes some natural keywords users might say like 'vercel', 'supabase', 'render', 'gh', 'CLI', and 'deployment', but misses common variations like 'deploy', 'hosting', 'GitHub CLI', 'cloud platform', 'provision', or specific actions users would request.	2 / 3
Distinctiveness Conflict Risk	The mention of specific platforms (Vercel, Supabase, Render, gh) provides some distinctiveness, but 'deployment platform setup' is broad enough to overlap with other DevOps or infrastructure 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 across four CLI tools, which is its primary strength. However, it is excessively verbose for a skill file — much of the content explains patterns Claude already knows or could be split into referenced sub-files. The lack of progressive disclosure and missing validation checkpoints after critical operations (deployments, migrations) are notable weaknesses.

Suggestions

Split the content into separate files (e.g., VERCEL.md, SUPABASE.md, RENDER.md, CI-CD.md) and use SKILL.md as a concise overview with links, reducing the main file to under 80 lines.

Remove explanatory text Claude already knows (e.g., what branch protection does, how curl works, what migrations are) and keep only the specific commands and project-specific conventions.

Add explicit validation/verification steps after destructive operations like `supabase db push` and `vercel --prod` (e.g., 'Verify deployment: `vercel inspect <url>` or check `vercel ls` for status').

Move the validation bash script and CI/CD YAML configs into actual bundle files (e.g., scripts/verify-tooling.sh, .github/workflows/deploy.yml) rather than inlining them.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~350 lines. It explains basic CLI patterns Claude already knows (how to run `gh auth login`, how curl works, what branch protection is), includes a full validation bash script that could be referenced as a file, and repeats deployment connection steps in multiple formats. The Render section alone has 5 sub-steps with extensive inline commentary. Much of this could be condensed to a concise reference table with commands.	1 / 3
Actionability	The skill provides fully executable, copy-paste ready commands throughout — bash scripts, YAML CI/CD configs, curl commands, package.json snippets, and render.yaml templates. Every section contains concrete, runnable examples with specific flags and arguments.	3 / 3
Workflow Clarity	Steps are listed clearly for individual tools (e.g., Render setup has Step 1-5, deployment checklist exists), but there are no validation checkpoints or feedback loops after destructive operations like `supabase db push` or `vercel --prod`. The verification script at the top is good, but post-deployment verification is absent. The overall flow between sections (when to use what, in what order) is loosely organized rather than tightly sequenced.	2 / 3
Progressive Disclosure	Everything is inlined in a single monolithic file with no references to external files. The validation script, CI/CD configs, render.yaml, and deployment checklists could all be separate referenced files. With no bundle files provided and no external references, this is a wall of text that would benefit significantly from splitting into focused sub-documents.	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: 7e5f7a2

Reviewed: 3 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.