the-high-signal-review
Run a high-signal review of the current workspace diff or PR in Stave. Use when the user asks for "code review", "PR review", "review this diff", "high-signal review", "strict review", "inline comments only for real issues", or wants only objective bugs and applicable policy violations with validation before commenting.
74
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does (high-signal code review focused on objective bugs and policy violations) and when to use it (with an explicit 'Use when' clause containing numerous natural trigger terms). The description is concise, uses third person voice, and carves out a distinct niche by emphasizing its strict, validation-first review philosophy.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'review of the current workspace diff or PR', 'objective bugs and applicable policy violations', 'validation before commenting', 'inline comments only for real issues'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (run a high-signal review of workspace diff or PR, finding objective bugs and policy violations with validation) and 'when' (explicit 'Use when' clause with multiple trigger phrases and conditions). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'code review', 'PR review', 'review this diff', 'high-signal review', 'strict review', 'inline comments only for real issues'. These are phrases users would naturally say when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with its focus on 'high-signal' review, 'Stave' platform, 'objective bugs and applicable policy violations', and 'validation before commenting'. The specificity of the review philosophy (strict, real issues only) clearly distinguishes it from generic code review skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise review workflow skill that clearly defines a multi-step process with strong validation gates and explicit filtering criteria. Its main weakness is that some steps (particularly subagent orchestration and comment formatting) are described at a procedural level without concrete examples or executable templates, which slightly limits actionability. Overall it's a strong skill that efficiently communicates a complex review process.
Suggestions
Add a concrete example of the expected inline comment format (title, problem, evidence, citation) to make step 5 more actionable.
Provide a concrete example of how to invoke or configure the parallel reviewer passes, even if pseudocode, to clarify the subagent orchestration in step 2.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every bullet point adds unique, non-obvious information. It doesn't explain what code review is or how diffs work—it assumes Claude's competence and focuses on the specific workflow, filtering criteria, and validation requirements. | 3 / 3 |
Actionability | The workflow provides specific commands (e.g., `gh pr view --json number,title,body,baseRefName,headRefName`) and clear decision criteria, but much of the guidance is procedural description rather than executable code. The subagent orchestration steps are described abstractly ('Give each reviewer...', 'Use separate passes for...') without concrete implementation details or examples of comment format. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit validation checkpoints (step 4 validates every issue before commenting), a feedback loop (reject anything not clearly real), and clear gating ('Only proceed to comment after validation'). The policy hierarchy and issue bar in step 3 provide unambiguous filtering criteria, and the fallback section handles edge cases. | 3 / 3 |
Progressive Disclosure | For a skill with no bundle files, the content is well-organized into clear sections (Workflow, Fallbacks) with numbered steps and sub-bullets. The skill is under 50 lines and self-contained, with no need for external references. The structure supports easy scanning and discovery. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sendbird/stave
- Commit
e275ad5
- Reviewed
Table of Contents
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.