hyperflow-audit

Hyperflow code review. Use when the user wants the current diff, a commit, branch, or PR reviewed — verbs like audit, review, "check for issues", "security check", "code review". Multi-level review (L1 quick → L5 exhaustive), writes findings to .hyperflow/audits/, then a fix-gate.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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 tight, well-structured single-file skill: efficient, immediately actionable, and clearly sequenced with meaningful checkpoints. Its only weaknesses are small — unstated dependencies on the hyperflow doctrine/sibling skills and a missing edge case for invalid or empty review targets.

Dimension	Reasoning	Score
Conciseness	The ~29-line body (levels table, steps, rules) is lean with zero padding and no explanation of concepts Claude already knows — every token earns its place, matching the anchor exactly. The 4 anchor's 'minor instances of over-explanation' does not apply.	5 / 5
Actionability	Concrete, executable guidance throughout: report path pattern "<YYYY-MM-DD-HHmm>-<scope>.md", report section order, grading labels with "file:line + a concrete fix", and exact fix-gate options. Not 5: "route the findings into hyperflow-plan → hyperflow-dispatch" and "Follow the hyperflow doctrine" assume mechanics that are not stated in this file.	4 / 5
Workflow Clarity	A clear 4-step sequence with real checkpoints: the fix gate after findings, the "Audit clean" clean-run rule, and the SECURITY_VIOLATION skip-gate path. Not 5: there is no feedback loop or handling for a degraded case such as an empty diff or an invalid target argument. No destructive/batch cap applies since the workflow is read-mostly.	4 / 5
Progressive Disclosure	Under 50 lines with no external references needed (no references/, scripts/, or assets/ exist), and content is organized into well-labeled Levels / Steps / Rules sections — the rubric's simple-skill case for a 5 applies directly.	5 / 5
	Total	18 / 20 Passed

Description

80%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 description with explicit what/when structure and concrete actions, held back from excellence by generic trigger verbs that create collision risk with other review skills and by missing detail on what the multi-level review actually covers.

Suggestions

Narrow the trigger guidance to reduce conflicts, e.g. "Use when the user asks for a hyperflow audit or wants review findings written to .hyperflow/audits/" instead of universal verbs like 'code review'.

Add one clause about what the levels check (e.g. "security scan at L3+, findings graded Critical/Important/Suggestion with file:line") to lift specificity from good to comprehensive.

Include natural user synonyms such as 'look over my changes' or 'is this safe to merge' alongside the current verb list.

Dimension	Reasoning	Score
Specificity	"Multi-level review (L1 quick → L5 exhaustive), writes findings to .hyperflow/audits/, then a fix-gate" lists several specific concrete actions with an exact output artifact. Not 5: it never says what the levels actually check (e.g., security scan, finding grades), leaving minor gaps in coverage.	4 / 5
Completeness	It explicitly answers both: what ("Hyperflow code review. Multi-level review (L1 quick → L5 exhaustive), writes findings to .hyperflow/audits/, then a fix-gate") and when ("Use when the user wants the current diff, a commit, branch, or PR reviewed — verbs like...") with concrete trigger phrases. Clearly matches the 5 anchor; the 4 anchor's 'when could be more explicit' does not apply.	5 / 5
Trigger Term Quality	"verbs like audit, review, 'check for issues', 'security check', 'code review'" plus "the current diff, a commit, branch, or PR reviewed" gives good natural keyword coverage. Not 5: common user phrasings like 'look over my changes', 'is this safe to merge', or 'review my PR' as synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	"Hyperflow code review" names a niche, but the trigger verbs ('review', 'check for issues', 'code review', 'security check') are the most generic review phrasings and would match almost any general code-review skill. Overlap risk is more than minor (not 4), though the diff/commit/branch/PR scoping keeps it above the 'very broad' anchor 2.	3 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jeremylongshore/tons-of-skills-marketplace
Path: plugins/ai-agency/hyperflow/templates/antigravity/skills/hyperflow-audit/SKILL.md
Commit: 88dcf65

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.