review-correctness
Correctness and logic review instructions for the expert agent
56
46%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./dot_config/opencode/skill/review-correctness/SKILL.mdQuality
Discovery
0%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 description is critically underspecified. It fails to identify what domain or artifacts are being reviewed, what specific actions are performed, and when the skill should be selected. The phrase 'for the expert agent' is internal jargon that provides no value for skill selection.
Suggestions
Specify the domain and concrete actions, e.g., 'Reviews code for logical errors, off-by-one bugs, null pointer issues, and incorrect control flow' instead of the vague 'correctness and logic review'.
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks for a code review, bug check, logic validation, or correctness audit.'
Remove the internal-facing phrase 'for the expert agent' and replace it with user-facing context that clarifies what artifacts or inputs this skill operates on.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('correctness and logic review instructions') without listing any concrete actions. It does not specify what is being reviewed, what outputs are produced, or what domain it applies to. | 1 / 3 |
Completeness | The description weakly addresses 'what' (some kind of correctness/logic review) and completely omits 'when' — there is no 'Use when...' clause or any explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | The terms 'correctness', 'logic review', and 'expert agent' are not natural keywords a user would say. There are no file types, task-specific terms, or common user phrases that would help match this skill to a request. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic — 'correctness and logic review' could apply to code review, math proofs, argument analysis, test validation, or many other domains. It would easily conflict with numerous other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-crafted review skill that provides clear, actionable instructions for correctness review. The exploration phase with explicit steps and the structured JSON output format are excellent. The scope categories are comprehensive and non-obvious, adding genuine value. Minor improvement could come from slightly better progressive disclosure for the detailed scope items.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No unnecessary explanations of what code review is or how git works. The scope list is dense but each item is a distinct, non-obvious category that adds value. The side effect chain tracing instructions are particularly high-signal. | 3 / 3 |
Actionability | Highly actionable with specific steps (grep for callers, read at least one caller, git blame), concrete output format with JSON schema, and clear severity levels. The exploration phase gives explicit commands rather than vague guidance. | 3 / 3 |
Workflow Clarity | Clear two-phase workflow: Phase 1 (Exploration) with numbered steps that must complete before findings, then structured output. The exploration log requirement acts as a validation checkpoint ensuring thorough investigation before reporting. The prior reviews section handles the feedback loop of iterative review. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections (Phase 1, Scope, Escalations, Rules, Output), but everything is in a single file with no references to external resources. For a skill of this length (~70 lines of content), this is borderline acceptable, but the scope section could benefit from being split out or having examples linked separately. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- athal7/dotfiles
- Commit
07d79b6
- 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.