audit

Use when the user wants a code review on recent changes — quality, spec, security, or performance feedback. Triggers a multi-level (L1-L5) review with a standalone Reviewer; on NEEDS_FIX, offers to apply findings via /hyperflow:plan. Trigger with /hyperflow:audit, "review this change", "review my PR", "audit the diff", "code review".

Quality

86%

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

Quality

Content

81%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 highly actionable, well-sequenced orchestration spec with concrete paths, commands, templates, and rich validation/feedback loops. Its main weakness is conciseness — late Overview/Instructions/Output sections restate the Flow — plus one missing referenced file (references/compaction.md) and cross-skill sibling dependencies that slightly muddy the reference structure.

Suggestions

Remove or fold the trailing Overview, Instructions, and Output sections into the existing Flow/Output Format sections to eliminate restated content and trim the token budget.

Fix the broken reference at line 209: references/compaction.md does not exist in the bundle — either add it or repoint the link to the intended skills/cache/references/compaction.md path it already names.

Consolidate cross-skill sibling references (../hyperflow/DOCTRINE.md, artefact-format.md, failure-recovery.md, session-handoff.md, ../agents/README.md) into a single 'Dependencies' section so the body's self-contained vs. external split is explicit.

Dimension	Reasoning	Score
Conciseness	The prose assumes Claude's competence (no concept over-explanation), but the back-half Overview/Instructions/Output sections restate the Flow already given in detail and the Output Format block is long, adding length that could be tightened.	3 / 5
Actionability	Concrete file paths (.hyperflow/audits/..., .hyperflow/specs/...), concrete commands (git diff HEAD, Skill skill:plan args:...), per-step agent dispatch recipes, and copy-paste markdown templates cover the common cases fully.	5 / 5
Workflow Clarity	A clearly sequenced 6-step process with explicit per-step sub-phases, verdict states, retry limits, and validation checkpoints (2d coverage gate, Step 5 severity reconciliation, 4d dedup/compaction) plus NEEDS_REVISION feedback loops.	5 / 5
Progressive Disclosure	Good structure with well-signaled one-level references into the real references/ bundle and examples explicitly moved out to keep the body lean, but references/compaction.md is cited (line 209) and does not exist in the bundle, and several ../hyperflow/* sibling dependencies are cross-skill rather than self-contained.	4 / 5
	Total	17 / 20 Passed

Description

91%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, third-person description that explicitly covers both what the skill does and when to trigger it, with natural trigger phrases and a distinctive slash command. Minor gaps: actions are process-level rather than output-level, and some overlap with generic code-review skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('multi-level (L1-L5) review', 'standalone Reviewer', 'apply findings via /hyperflow:plan'), but the actions are process-level rather than output-level like the anchor's extract/fill/merge, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (multi-level L1-L5 review with a standalone Reviewer and fix chaining) and 'when' ('Use when the user wants a code review...' plus concrete trigger phrases).	5 / 5
Trigger Term Quality	Covers natural phrases users would say ('review this change', 'review my PR', 'audit the diff', 'code review') plus the /hyperflow:audit slash command — comprehensive including synonyms.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (multi-level code review chained to /hyperflow:plan) with a distinctive slash command, but has minor overlap risk with generic code-review skills.	4 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 7 suspicious	Warning

	Total	13 / 16 Passed

Repository: jeremylongshore/tons-of-skills-marketplace
Path: plugins/ai-agency/hyperflow/skills/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.