CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 tightly written, well-structured review workflow with explicit validation and feedback loops and excellent token efficiency. The only gap is that two fallback paths (git diff, comment posting) are named abstractly instead of given as executable commands.

Suggestions

Add the concrete git diff fallback command (e.g., the exact `git diff` invocation against the merge base plus uncommitted changes) instead of only naming it.

Specify the exact `gh` comment-posting command (or the PR comment tool invocation) so the comment step is copy-paste ready, not just 'otherwise use gh'.

Optionally show the concrete subagent prompt skeleton or role names used for the parallel reviewers so the 'independent reviewers in parallel' step is fully reproducible.

DimensionReasoningScore

Conciseness

A lean ~40-line body that assumes Claude's competence (no explanations of diffs, PRs, or subagents); every line carries concrete instruction with no padding.

5 / 5

Actionability

Provides a copy-paste-ready gh command, specific policy file paths, and concrete precedence rules, but the git-diff fallback and comment-posting mechanics are described abstractly rather than with executable commands.

4 / 5

Workflow Clarity

Five clearly sequenced steps with an explicit validation checkpoint (Step 4) including reject-logic feedback and a terminal 'if nothing survives validation, say so' rule, satisfying the batch-operation validation requirement.

5 / 5

Progressive Disclosure

Under 50 lines with no bundle files and no need for external references; content is cleanly organized into a Workflow section and Fallbacks section, meeting the simple-skill exception.

5 / 5

Total

19

/

20

Passed

Description

95%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 well-crafted description that concisely answers both what and when, with rich natural trigger terms and a clearly distinct niche. The only minor weakness is that its 'actions' are facets of a single review process rather than several separate operations.

DimensionReasoningScore

Specificity

Names the review domain plus several concrete behaviors ('inline comments only for real issues', 'objective bugs', 'applicable policy violations', 'validation before commenting'), but they describe one review process rather than multiple distinct actions, leaving minor coverage gaps.

4 / 5

Completeness

Clearly states what it does ('Run a high-signal review of the current workspace diff or PR in Stave') and explicitly when to use it with concrete trigger phrases via the 'Use when' clause.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases including synonyms and variations ('code review', 'PR review', 'review this diff', 'high-signal review', 'strict review', 'inline comments only for real issues') that users would naturally say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (strict false-positive-filtered review with mandatory validation) with distinct triggers, making overlap with general review skills unlikely.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sendbird/stave
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.