CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-core-dev

Use when developing in packages/agent-core-v2 (the DI × Scope agent engine) — adding or modifying a domain Service, choosing a LifecycleScope, wiring DI dependencies, splitting a domain across scopes, owning or migrating a config section, gating behavior behind an experimental flag, raising coded errors, working on the permission system, writing DI/Scope tests, porting business logic from agent-core (v1) to v2, triaging a main-branch commit against v2, or exposing a v2 domain over server-v2 while keeping the /api/v1 wire contract compatible with released clients. Self-contained guide organized by development stage (orient → design → implement → test → verify) plus align workflows for v1→v2 migration, main-branch commit triage, and server-v2 wire exposure; each file carries the rules, examples, and red lines for its step.

69

Quality

85%

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

78%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.

The body is an exemplary index/overview: well-structured, tersely imperative, with clear stage sequencing, explicit feedback loops, and clean one-level-deep file navigation. The main room for improvement is tightening the densest red lines (especially config) and surfacing a bit more inline validation detail.

Suggestions

Split red line #12 (config) into 2-3 shorter invariants so each rule is scannable on its own line.

Inline the verify-stage validation commands (lint:imports, typecheck, test) as an explicit ordered checklist in the body rather than only referencing verify.md, so the pre-submit workflow is self-contained at a glance.

Trim the longest topic blurbs under Stage 3 (e.g., permission.md, telemetry.md) to a single clause each, since the details live in the linked files.

DimensionReasoningScore

Conciseness

The body is largely efficient and imperative, but a few red lines are dense enough to be trimmed — notably red line #12 ('Config is the preference registry...') bundles many rules into one long sentence — keeping it just short of fully lean.

4 / 5

Actionability

Routing guidance is concrete ('inject with @IX or accessor.get(IX)', 'refactor (extract a third Service / use an event / re-scope)', explicit per-situation file links) and the red lines give specific directives, though as an index it carries no inline executable code, which is appropriate but leaves minor gaps.

4 / 5

Workflow Clarity

A clear Orient → Design → Implement → Test → Verify sequence is laid out with an explicit feedback loop ('a test failure ... sends you back to design', 'CyclicDependencyError sends you to design.md §dependency-direction') and a pre-submit red-lines checklist, but the detailed per-step validation lives one level deeper in verify.md rather than inline.

4 / 5

Progressive Disclosure

A clear overview with well-signaled, one-level-deep references to stage, topic, and workflow files (orient.md, design.md, implement.md, align.md, etc.), each annotated with its contents and easy to navigate; no nested reference chains.

5 / 5

Total

17

/

20

Passed

Description

92%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.

The description is comprehensive, concrete, and clearly distinguishes the skill's niche while explicitly covering both what it does and when to use it. Its only weakness is a reliance on dense internal jargon over broadly natural trigger phrasings.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'adding or modifying a domain Service, choosing a LifecycleScope, wiring DI dependencies, splitting a domain across scopes, owning or migrating a config section, gating behavior behind an experimental flag, raising coded errors' — giving comprehensive coverage of what the skill handles.

5 / 5

Completeness

Explicitly answers both 'what' ('Self-contained guide organized by development stage (orient → design → implement → test → verify) ... each file carries the rules, examples, and red lines') and 'when' ('Use when developing in packages/agent-core-v2 ...' followed by concrete trigger situations).

5 / 5

Trigger Term Quality

Good keyword coverage with natural task phrasings ('porting business logic from agent-core (v1) to v2', 'triaging a main-branch commit', 'exposing a v2 domain over server-v2'), but the terms are heavily internal jargon and lack common synonyms or file extensions, so a few natural variations are missing.

4 / 5

Distinctiveness Conflict Risk

Tightly scoped to 'packages/agent-core-v2 (the DI × Scope agent engine)' with a clear niche and very specific triggers, making conflict with other skills minimal.

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

relative_links

Relative link issues: 18 missing

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.