ruview-verify

Verify a RuView build — full Rust workspace tests, the deterministic Python pipeline proof (SHA-256 Trust Kill Switch), firmware hash manifest, and the ADR-028 witness bundle with one-command self-verification. Use after any significant change, before merging a PR, or to produce an attestation bundle for a recipient.

Quality

90%

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

88%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 well-structured, executable verification workflow with strong sequencing, validation checkpoints, and feedback loops. Conciseness is slightly dinged by scattered version/count specifics, and progressive disclosure could push more detail into the referenced files.

Suggestions

Move brittle counts/versions (e.g. '1,400+ passed', 'espressif/idf:v5.4', '8MB', '33-row') into the referenced docs or a dedicated version-notes block so the core workflow stays stable.

Trim the opening 'The trust pipeline for RuView. Run this after meaningful changes and before merging.' since it duplicates the frontmatter description.

Consider relocating the 12-item pre-merge checklist and QEMU CI notes to the referenced CLAUDE.md/docs and leaving a one-line pointer here to reduce inline bulk.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven with minimal prose, but embeds version- and count-sensitive details (e.g. '1,400+ passed', 'espressif/idf:v5.4', '8MB', 'seed=42') outside any deprecated/old-patterns section, and the opening sentence lightly restates the description.	4 / 5
Actionability	Provides copy-paste-ready, fully executable commands throughout — 'cargo test --workspace --no-default-features', 'python archive/v1/data/proof/verify.py', 'bash scripts/generate-witness-bundle.sh' — covering the common verification cases with concrete expected outputs.	5 / 5
Workflow Clarity	A clearly sequenced five-step workflow with explicit validation checkpoints ('must be 1,400+ passed, 0 failed', 'must print VERDICT: PASS', 'must be 7/7 PASS') and an error-recovery feedback loop for hash mismatches, plus a pre-merge checklist.	5 / 5
Progressive Disclosure	Well-organized into numbered sections with a one-level-deep 'Reference' pointer to repo paths (docs/, scripts/, CLAUDE.md); minor gaps because the 12-item pre-merge checklist and QEMU CI notes are inlined where they arguably belong in the referenced CLAUDE.md/docs.	4 / 5
	Total	18 / 20 Passed

Description

92%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, specific description that clearly states what it does and when to use it in third person, with concrete trigger phrases. Trigger-term coverage is good but slightly situational rather than exhaustive of natural user phrasings.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete verification actions — 'full Rust workspace tests', 'deterministic Python pipeline proof (SHA-256 Trust Kill Switch)', 'firmware hash manifest', and 'ADR-028 witness bundle with one-command self-verification' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what ('Verify a RuView build — ...') and when ('Use after any significant change, before merging a PR, or to produce an attestation bundle for a recipient') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms like 'verify', 'build', 'merge a PR', and 'attestation bundle' are present, but the triggers lean situational ('after any significant change') rather than covering common user-spoken synonyms; a few natural phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	The 'RuView build', 'SHA-256 Trust Kill Switch', 'ADR-028 witness bundle', and 'firmware hash manifest' niche is highly specific with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 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
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: ruvnet/RuView
Path: plugins/ruview/skills/ruview-verify/SKILL.md
Commit: a76adc3

Reviewed: about 4 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.