project-tooling

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

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/project-tooling/SKILL.md

Quality

Content

65%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 highly actionable with concrete, executable commands throughout, but it is a monolithic reference that inlines file-sized scripts and config that belong in separate bundle files, and it lacks validation feedback loops around destructive database operations.

Suggestions

Move scripts/verify-tooling.sh, render.yaml, and the GitHub Actions workflows into actual files under scripts/ and references/, replacing the inlined blocks with one-level-deep links.

Add explicit validate->fix->retry checkpoints around destructive operations (e.g. run migrations against a preview, verify, then "supabase db push") to lift workflow clarity above the cap.

Trim redundant section intros and consolidate repeated auth/verify command patterns to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command reference with little concept over-explanation, but it inlines a full bash validation script, a render.yaml, two GitHub Actions workflows, and a package.json block that belong in separate files. It is above anchor 2 (not padded with prose) but below 4 because of the inlined file-sized blocks.	3 / 5
Actionability	Nearly every section gives concrete, copy-paste-ready executable commands (e.g. "gh repo create <repo-name> --private --source=. --remote=origin --push", "supabase db push") covering the common cases. It matches the 'fully executable, copy-paste ready' anchor.	5 / 5
Workflow Clarity	Sequences are present (e.g. the numbered Render setup steps and the validation script with set -e / exit 1), but destructive/batch operations like "supabase db reset", "supabase db push", and branch-protection PUTs have no validation feedback loop, which caps workflow clarity at 3 per the rubric. Not a 4 because the cap applies; not a 2 because there is a real sequence and one explicit verification script.	3 / 5
Progressive Disclosure	Section headers give reasonable structure, but no bundle files exist and content that clearly belongs in separate files (scripts/verify-tooling.sh, render.yaml, workflow YAMLs) is inlined with only a comment-style path reference. It is above anchor 2 (has clear sections) but below 4 because file-worthy content is not split out and references are not real signaled links.	3 / 5
	Total	14 / 20 Passed

Description

61%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 about which tools it covers and what it does, but omits any explicit "when to use" trigger guidance, which caps completeness. Trigger-term and distinctiveness are reasonably strong thanks to the named CLIs.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when setting up deployment, CI/CD, or when CLI tools are needed" to raise completeness.

Expand the action beyond the single generic verb "setup" (e.g. "authenticate, link, deploy, and run migrations") to improve specificity.

Include natural synonyms/file references users say (e.g. "deploy", "CI/CD", ".env") to push trigger-term coverage toward 5.

Dimension	Reasoning	Score
Specificity	Names concrete tools ("gh, vercel, supabase, render") and a concrete action ("setup"), but the action is generic and coverage is not comprehensive. It fits the 'names domain and 1-2 concrete actions' anchor; not a 2 because specific tool names add concreteness, not a 4 because only 'setup' is named as an action.	3 / 5
Completeness	It clearly states the "what" (CLI and deployment platform setup) but provides no "when" / "Use when..." clause; per the guideline a missing explicit trigger clause caps completeness at 3. Not a 4 because no 'when' guidance is present at all in the description field.	3 / 5
Trigger Term Quality	"gh, vercel, supabase, render" and "deployment" are natural terms users say when requesting these tools; a few common variations (e.g. file extensions, synonyms like 'deploy') are missing. It is above anchor 3 (good keyword coverage) but below 5 (not comprehensive synonym/extension coverage).	4 / 5
Distinctiveness Conflict Risk	Naming the specific CLIs (gh, vercel, supabase, render) gives a clear niche with minor overlap risk against generic deployment skills. Not a 5 because "deployment platform setup" is still somewhat broad and could overlap with a general deploy skill.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: alinaqi/claude-bootstrap
Path: skills/project-tooling/SKILL.md
Commit: abc600e

Reviewed: 7 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.