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

88%

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

92%

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

A command-dense, well-sequenced verification workflow with strong validation checkpoints and an error-recovery loop. The main weakness is progressive disclosure: substantial inline inventories and checklists live entirely in SKILL.md with no accompanying bundle files to absorb detail.

Suggestions

Move the 12-item pre-merge checklist and the QEMU CI notes into a referenced file (e.g. references/pre-merge-checklist.md) and link to it from SKILL.md to keep the body as an overview.

Promote the artifact/manifest inventory under section 4 into a short reference rather than an inline bullet list, so the core workflow stays scannable.

Add the referenced docs/scripts (e.g. scripts/generate-witness-bundle.sh, archive/v1/data/proof/verify.py) as actual bundle files so the one-level-deep references resolve.

Dimension	Reasoning	Score
Conciseness	Lean, command-first body with inline annotations like '# must be 1,400+ passed, 0 failed' and 'must print VERDICT: PASS'; no padding or explanation of concepts Claude already knows, every line earns its place.	3 / 3
Actionability	Fully executable commands throughout (cargo test, python verify.py, pytest, bash scripts/generate-witness-bundle.sh, bash VERIFY.sh, npx security scan) with specific paths, flags, and expected outputs — copy-paste ready.	3 / 3
Workflow Clarity	Five clearly sequenced steps with explicit validation checkpoints ('must be 1,400+ passed', 'must print VERDICT: PASS', 'must be 7/7 PASS'), an error-recovery loop for hash mismatches, and a 12-item pre-merge checklist — matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Good section organization with a one-level Reference section, but the checklist and several dense inline reference lists (artifact inventories, QEMU notes, ADR pointers) are inline content that could be split into reference files; no bundle files exist alongside to delegate to.	2 / 3
	Total	11 / 12 Passed

Description

85%

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 with explicit what-and-when triggers anchored to a clearly distinct verification niche. Trigger phrasing leans on internal process terms rather than the most natural user vocabulary, leaving slight room for improvement.

Suggestions

Add user-natural trigger phrasing alongside process triggers (e.g. 'Use when the user asks to verify, validate, or certify a RuView build / produce a verification attestation').

Surface the most likely plain-language keywords (verify, validate, attest, run tests before merge) so the skill triggers on how users actually phrase the request.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: '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', matching the top anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers what (verify a RuView build via tests, proof, manifest, witness bundle) and when ('Use after any significant change, before merging a PR, or to produce an attestation bundle'), satisfying the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Domain keywords like 'Rust workspace tests', 'PR', 'merging', 'attestation bundle' are relevant but the triggers are process-oriented rather than natural user phrasings; common variations a user would actually say are thin.	2 / 3
Distinctiveness Conflict Risk	Highly specific to RuView/ADR-028/witness-bundle verification, a clear niche with distinct triggers unlikely to collide with other skills.	3 / 3
	Total	11 / 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
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: d9dfea2

Reviewed: about 13 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.