CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-core-review

Use ONLY for code review and test write/review guidance in `packages/agent-core-v2` (the DI × Scope agent engine). Does NOT apply to the legacy `packages/agent-core` or to any other package — for those, do not load this skill. Groups the review and testing lenses used for agent-core-v2 — `slop` (single-level-of-abstraction / layered error-handling review, invoked only on explicit request) and `test` (contract-driven per-test rules for both authoring and reviewing tests). Apply the sub-skill that matches the task; do not apply `slop` unprompted.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 tight, well-organized routing skill that efficiently points to its sub-skills with concrete routing rules and per-lens specifics. Its main gap is that the referenced slop/ and test/ sub-skill bundles are not present alongside SKILL.md to verify the navigation targets.

Suggestions

Ship the slop/ and test/ sub-skill directories referenced in the body so the one-level-deep navigation targets actually exist alongside SKILL.md.

Add a brief one-line note in the Routing section on how to confirm which sub-skill applies when a task spans both review and testing, to remove ambiguity in mixed tasks.

Consider a short inline example of a routed decision (e.g., a sample user request → chosen sub-skill) to make the routing rule immediately actionable without opening the sub-skill.

DimensionReasoningScore

Conciseness

Lean and efficient with no padding or re-explanation of concepts Claude already knows; every line (scope, sub-skills, routing) earns its place.

5 / 5

Actionability

Concrete routing rules and specific per-lens guidance (CCCR, one behavior per it, stub only the true external boundary, file:line findings) are present, but the executable test-authoring steps are delegated to sub-skills rather than given inline.

4 / 5

Workflow Clarity

As a routing skill with a single unambiguous decision (identify task type then apply the matching sub-skill), the workflow is clear and well-sequenced; no destructive/batch validation is needed here.

5 / 5

Progressive Disclosure

Clean structure with a concise overview pointing one level deep to sub-skills, but the referenced slop/ and test/ sub-skill directories are not present in the bundle to verify.

4 / 5

Total

18

/

20

Passed

Description

87%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 highly specific, well-scoped description that explicitly states both what the skill does and when to use it, while actively preventing misapplication to other packages. Trigger term coverage is strong but could add a few common synonyms.

DimensionReasoningScore

Specificity

Lists several specific concrete actions (code review, test write/review) and names both lenses with what each does, with only minor gaps in per-lens action coverage.

4 / 5

Completeness

Explicitly answers both what ("Groups the review and testing lenses...") and when ("Use ONLY for... in packages/agent-core-v2", "Apply the sub-skill that matches the task") with concrete trigger guidance.

5 / 5

Trigger Term Quality

Good coverage of natural trigger phrases users would say ("code review", "writing tests", "reviewing tests", "abstraction layers") though a few synonyms like "unit test" are absent.

4 / 5

Distinctiveness Conflict Risk

Pinned to a single package and actively carves out exclusions (legacy agent-core, other packages), giving a clear niche with minimal conflict risk.

5 / 5

Total

18

/

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
MoonshotAI/kimi-code
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.