CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

meojson

Guide for using the meojson C++ JSON library in MaaEnd cpp-algo. Use when writing code that involves JSON parsing, serialization, struct jsonization (MEO_JSONIZATION), json::value manipulation, ext::jsonization custom type support, or custom recognition param parsing in agent/cpp-algo/.

Quality

84%

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

71%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 a well-organized, largely executable API guide with good project-specific patterns and anti-pattern guidance. Its main weakness is progressive disclosure: the closing link points to a reference.md that is absent from the bundle, and inline API-signature bulk that belongs in that file keeps the skill heavier than needed.

Suggestions

Add the referenced detail file to the bundle (e.g., references/reference.md) so the Quick Reference link resolves; currently it points to a file that does not exist.

Move the inline signature listings (Reading Values, Serialization, Sub-Macros table) into reference.md and keep SKILL.md focused on the core parse/serialize/jsonization patterns.

Trim redundant guidance: Pitfalls #2 and #3 restate the from_json() check and the .value_or(...).as<T>() anti-pattern already shown in the Parsing and MEO_JSONIZATION sections.

DimensionReasoningScore

Conciseness

The body is code-forward with no padding explaining what JSON is, and project-specific guidance (JSONC boundaries, anti-patterns) earns its tokens. Minor over-explanation remains: the Reading Values / Serialization sections are signature-listing dumps, and Pitfalls #2–#3 repeat guidance already given inline in the Parsing and MEO_JSONIZATION sections.

4 / 5

Actionability

Most examples are executable and complete (ParseCustomRecognitionParam, WriteJsonDetail, the cv::Rect ext::jsonization specialization), but a few sections use shorthand signature listings rather than compilable code ('v.is_null() / v.is_boolean() / ...', 'v.dumps() // compact string') and rely on unexplained project macros (LogError, VAR). This sits between 'mostly executable with minor gaps' (4) and fully copy-paste ready (5).

4 / 5

Workflow Clarity

As an API reference skill there is no fragile multi-step sequence, and the key patterns do include explicit validation checkpoints (check the std::optional from parse, from_json() return check, LogError + early return). It is not a 5 because there is no explicit end-to-end workflow or error-recovery feedback loop beyond the per-pattern checks, and several sections (Constructing, Merge, Enum) present code without any failure-path guidance.

4 / 5

Progressive Disclosure

Section structure is clear and the Quick Reference section clearly signals a one-level reference ('For detailed API signatures, see [reference.md](reference.md)'), but that file does not exist in the bundle (no references/, scripts/, or assets/ directories) — the single navigation pointer is dangling. Additionally, a significant amount of API signature detail (Reading Values, Serialization, Sub-Macros table) is inlined that the referenced file is meant to hold, so organization is only partially realized. This fits 'some structure; content that should be separate is inline' rather than the well-functioning split of a 4.

3 / 5

Total

15

/

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.

A strong description: specific, third-person, with an explicit 'Use when...' clause and concrete trigger terms scoped to a clear project niche. Only minor keyword gaps (e.g., JSONC, .json) keep trigger coverage from full marks.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete capabilities — 'JSON parsing, serialization, struct jsonization (MEO_JSONIZATION), json::value manipulation, ext::jsonization custom type support, or custom recognition param parsing' — which is comprehensive coverage of the library's surface, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

It explicitly answers both parts: 'what' via 'Guide for using the meojson C++ JSON library in MaaEnd cpp-algo' and 'when' via an explicit 'Use when writing code that involves... in agent/cpp-algo/' clause with concrete trigger phrases. Not below 5 because both what and when are present and explicit.

5 / 5

Trigger Term Quality

Natural terms users would say are present ('JSON parsing', 'serialization', 'json::value', 'custom recognition param parsing', 'MEO_JSONIZATION'), but a few natural variations are missing — no 'JSONC' (a documented feature of the skill), '.json' file extension, or 'enum' triggers. This fits 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym/extension coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

Scoping to 'meojson C++ JSON library in MaaEnd cpp-algo' and 'agent/cpp-algo/' gives it a clear niche with distinct triggers (MEO_JSONIZATION, ext::jsonization, custom recognition param) and minimal conflict risk with generic JSON skills.

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

MaaEnd/MaaEnd

Path

.agents/skills/meojson/SKILL.md

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.