ai-loop

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body shines on workflow clarity and actionability, with a tightly sequenced spec-build-review loop and explicit validation/approval gates. Its weaknesses are a monolithic structure with no reference files and some redundancy between the phase instructions and the Best Practices section.

Suggestions

Move the full worked example and/or the Best Practices and Common Pitfalls sections into a referenced file (e.g., EXAMPLES.md) and keep SKILL.md as a lean overview with one-level-deep links, improving progressive disclosure.

Trim the Best Practices checklist to items not already stated in the phase instructions to reduce redundancy and save tokens.

Condense the transcript-style example to the minimal illustration of the loop-back behavior rather than a full conversation.

Dimension	Reasoning	Score
Conciseness	The body is mostly procedural and avoids explaining concepts Claude already knows, but the Best Practices checklist largely restates the phase rules and the full transcript-style example is long, so it could be tightened.	2 / 3
Actionability	Guidance is concrete and executable: specific file paths ('specs/<feature-name>.md'), requirement-by-requirement verification, named approval-gate actions, and a worked example; for an instruction-only skill this is copy-paste-ready direction.	3 / 3
Workflow Clarity	The Spec→Build→Review phases are clearly sequenced with an explicit Review→Build feedback loop, upfront iteration budget and verification commands, and explicit stop/approval checkpoints, exactly matching the top anchor for validation-gated workflows.	3 / 3
Progressive Disclosure	The skill is well-sectioned but monolithic: no bundle files exist and all content (long example, best practices, pitfalls) is inline, so content that could be split into references is not, and the under-50-lines exception does not apply.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 clearly conveys what the skill does but lacks an explicit 'Use when...' trigger clause and relies on internal jargon over natural user language. It is a solid mid-tier description that would benefit from concrete trigger phrasing.

Suggestions

Add an explicit 'Use when...' clause with natural triggers users would actually say (e.g., 'Use when building a feature from scratch and you want one bounded pass through spec, build, and verify').

Replace skill-internal jargon like 'spec-build-review development loop' with plainer terms the user would naturally use ('build, verify, and fix a feature in one loop').

Name a couple of distinct concrete actions up front (e.g., 'interviews for requirements, writes a spec, builds to spec, then verifies requirement-by-requirement') to lift specificity.

Dimension	Reasoning	Score
Specificity	It names the domain and core actions ('spec-build-review development loop') plus mechanisms ('explicit scope, stop conditions, and human approval gates'), but reads as a single conceptual statement rather than a crisp list of multiple concrete actions, so it falls short of the top anchor.	2 / 3
Completeness	The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance; 'for risky or ambiguous work' is only a partial implied 'when', so completeness is capped at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	It includes some relevant keywords ('development', 'work') but leans on skill-internal jargon ('spec-build-review development loop', 'human approval gates') rather than phrasing a user would naturally say, missing common variations.	2 / 3
Distinctiveness Conflict Risk	The 'bounded spec-build-review loop with approval gates' is a somewhat specific niche, but without explicit triggers and with overlap against general planning/development skills, it could still trigger for the wrong skill.	2 / 3
	Total	8 / 12 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: sickn33/antigravity-awesome-skills
Commit: 6e69f00

Reviewed: 5 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.