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.

68

Quality

83%

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

100%

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

The body is a well-structured, token-efficient routing overview that delegates detail to its sub-skills while embedding concrete review/testing rules. It scores at the top of the rubric across conciseness, actionability, workflow clarity, and progressive disclosure.

DimensionReasoningScore

Conciseness

Lean and efficient at ~20 lines: scope fencing, two sub-skill blurbs, and a routing table, with no concepts Claude already knows explained; every line earns its place and competence is assumed.

3 / 3

Actionability

Concrete actionable guidance throughout — routing maps task types to specific sub-skills, and the blurbs give specific directives ("one behavior per it", "stub only the true external boundary", "control time/config via documented knobs", "report findings with file:line"); absence of code is not penalized for this instruction-only skill.

3 / 3

Workflow Clarity

As a simple single-purpose routing skill under 50 lines with no destructive or batch operations, its single decision (task type → sub-skill) is unambiguous via the Routing section, satisfying the simple-skill allowance.

3 / 3

Progressive Disclosure

Clear overview with well-signaled one-level-deep references to the slop/ and test/ sub-skills, content appropriately split into Scope, Sub-skills, and Routing sections for easy navigation; no bundle files were present to verify, so scoring is based on the written structure.

3 / 3

Total

12

/

12

Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is highly specific and exceptionally distinctive, with clear scope fencing against the legacy package. Its weakness is trigger phrasing: it relies on scope restriction and jargon rather than natural user-intent keywords, leaving trigger quality and completeness at the mid level.

Suggestions

Add a natural "Use when..." trigger clause enumerating user intents (e.g., "Use when the user asks to review code or tests in packages/agent-core-v2, or when writing/modifying tests there") to lift completeness to 3.

Reduce jargon in the trigger phrasing and add common natural variations a user would actually say ("review my code", "check my tests", "write a test") alongside the technical lens names.

Keep the strong scope fencing but move it after a concise capability + trigger sentence so the natural trigger guidance leads.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and lenses — "code review and test write/review guidance", "single-level-of-abstraction / layered error-handling review", and "contract-driven per-test rules for both authoring and reviewing tests" — matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

The "what" is explicit and strong, but the "when" is delivered as a scope restriction ("Use ONLY for ... in packages/agent-core-v2") rather than natural user-intent triggers like "Use when the user asks to review tests", and per the rubric a missing natural "Use when..." trigger caps completeness at 2.

2 / 3

Trigger Term Quality

Relevant natural terms appear ("code review", "test write/review", "reviewing tests") but they are mixed with heavy technical jargon ("DI × Scope agent engine", "single-level-of-abstraction", "contract-driven per-test rules") and common natural variations a user would say are not covered.

2 / 3

Distinctiveness Conflict Risk

Extremely clear niche: explicitly scoped to packages/agent-core-v2, explicitly excludes the legacy packages/agent-core and all other packages, and separates its two sub-skills with anti-collision guidance — unlikely to trigger for the wrong skill.

3 / 3

Total

10

/

12

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.