antigravity-workflows

Use when asked to ship a SaaS MVP, audit application security, build an AI agent, run browser QA, or design a domain model with multiple skills and verified checkpoints.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-antigravity-workflows/SKILL.md

The canonical home for this skill is antigravity-workflows in sickn33/agentic-awesome-skills

Quality

Content

76%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.

A cleanly structured orchestrator skill with an excellent, checkpoint-rich workflow and sensible one-level reference to a bundled card file. Its main weakness is actionability: the body leans on procedural hints and routing rather than concrete, copy-paste executable commands, though the referenced file does supply an installer command.

Suggestions

Tighten actionability by including at least one concrete, executable command or code snippet directly in the body rather than only in the referenced card file.

Trim minor over-explanation in the orchestration steps to push conciseness to the top band.

Make the external source-of-truth paths (docs/users/workflows.md, data/workflows.json) more clearly optional/fallback so the skill's behavior is fully grounded in the bundled reference.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and mostly assumes Claude's competence (routing table, short steps, limitations), with only minor padded phrasing in the orchestration rationale; it does not earn 5 because a few explanatory sentences restate obvious orchestration concepts.	4 / 5
Actionability	It gives concrete procedural guidance (numbered steps, routing table, copy-paste prompts, an installer command in references) but the in-body instructions are mostly high-level hints rather than fully executable code or commands, matching 'Some concrete guidance but incomplete' better than the 4 anchor.	3 / 5
Workflow Clarity	The 'How to Run This Skill' section is an explicitly numbered sequence with verification checkpoints ('Verify completion criteria before moving on', retain failure → fix → rerun → continue only after it passes), error recovery loops, and a clear final checklist, matching the top anchor including its destructive/installer feedback loop.	5 / 5
Progressive Disclosure	The SKILL.md is an overview that signals a one-level-deep reference (references/workflow-cards.md, with verified anchor links) and routes detail there; it is not 5 because some card-style detail and installer specifics live partly inline and the primary source-of-truth paths (docs/..., data/...) are external/unverifiable.	4 / 5
	Total	16 / 20 Passed

Description

78%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.

A strong, trigger-rich description that pairs an explicit 'Use when' clause with a list of concrete scenarios, satisfying the completeness anchor well. It is held back from the top band primarily by specificity, since the listed verbs are broad orchestration outcomes rather than granular, mechanic-level actions.

Dimension	Reasoning	Score
Specificity	The description names several concrete outcome verbs (ship, audit, build, run, design) but lists no concrete mechanic-level actions like a PDF extractor would; it matches 'Names domain and 1-2 concrete actions, but not comprehensive' better than the score above because each action is a broad capability rather than a specific operation.	3 / 5
Completeness	It explicitly answers both 'what' (turn a complex objective into a guided sequence of skill invocations across the listed scenarios) and 'when' via an explicit 'Use when asked to...' trigger clause enumerating concrete triggers; it is not below 5 because the when-clause is explicit and concrete.	5 / 5
Trigger Term Quality	It includes natural request phrases users would say ('ship a SaaS MVP', 'audit application security', 'build an AI agent', 'run browser QA'); coverage is good but lacks some synonyms and could not be considered fully comprehensive enough for a 5.	4 / 5
Distinctiveness Conflict Risk	The 'guided sequence of skill invocations' niche is fairly distinct from single-purpose skills, but the broad scenario list (SaaS, security, agents, QA, DDD) creates minor overlap risk with those specialized skills themselves, keeping it just below a clear-niche 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: boisenoise/skills-collections
Path: skills/antigravity-antigravity-workflows/SKILL.md
Commit: 652629d

Reviewed: ~14 hours 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.