CtrlK
BlogDocsLog inGet started
Tessl Logo

10-andruia-skill-smith

Ingeniero de Sistemas de Andru.ia. Diseña, redacta y despliega nuevas habilidades (skills) dentro del repositorio siguiendo el Estándar de Diamante.

24

Quality

14%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/antigravity-awesome-skills-claude/skills/10-andruia-skill-smith/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

17%

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 identifies a specific domain (skill creation for a particular system) and lists high-level actions, but it relies heavily on project-specific jargon without providing natural trigger terms users would actually say. It critically lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill over others. The description reads more like a role title than a functional skill description.

Suggestions

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to create a new skill, add a skill file, generate a skill template, or modify existing skills in the repository.'

Include more concrete actions beyond 'diseña, redacta y despliega' — specify what the skill actually produces (e.g., 'Creates YAML frontmatter, writes markdown skill files, validates against the Diamond Standard schema, and commits skill files to the repository').

Add common user-facing keywords in both Spanish and English that would naturally trigger this skill, such as 'nueva habilidad', 'crear skill', 'skill template', 'agregar skill', 'new skill'.

DimensionReasoningScore

Specificity

Names the domain (skills/habilidades within a repository) and some actions ('Diseña, redacta y despliega'), but the actions are somewhat generic (design, write, deploy) and lack concrete details about what specific operations are performed (e.g., creating YAML frontmatter, writing markdown content, validating against schema).

2 / 3

Completeness

The description answers 'what' at a high level (designs, writes, deploys skills) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1.

1 / 3

Trigger Term Quality

The description uses specialized jargon ('Estándar de Diamante', 'Andru.ia') that users would not naturally say. It lacks natural trigger terms a user might use like 'create a new skill', 'add a skill', 'skill template', or 'skill file'. The terms are too project-specific without broader keyword coverage.

1 / 3

Distinctiveness Conflict Risk

The mention of 'Estándar de Diamante' and 'Andru.ia' provides some distinctiveness, but 'diseña, redacta y despliega nuevas habilidades' could overlap with general code generation or documentation skills. The niche is somewhat defined but not sharply delineated.

2 / 3

Total

6

/

12

Passed

Implementation

12%

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

This skill is essentially a high-level description of a workflow for creating other skills, but it lacks the concrete, actionable content needed to actually execute that workflow. It contains no templates, no code examples, no example outputs, and no references to the standards it claims to follow. The verbosity and self-referential language waste tokens without adding value.

Suggestions

Add a concrete, complete example of a generated README.md template and registry snippet so Claude knows exactly what output format to produce.

Include a link or inline reference to the 'Estándar de Diamante' specification and the actual registry file path/format, so the skill is self-contained enough to execute.

Add explicit validation steps in Phase 3: verify folder creation succeeded, validate README.md against the expected structure, and confirm the registry entry was correctly inserted.

Remove self-descriptive filler ('Soy el Ingeniero...', the generic 'When to Use' and 'Limitations' sections) and replace with actionable content like a README template or example skill output.

DimensionReasoningScore

Conciseness

The content is verbose with unnecessary self-description ('Soy el Ingeniero de Sistemas de Andru.ia'), explains obvious concepts Claude already knows, and includes padded sections like 'When to Use' that just restate the description. The 'Limitations' section is boilerplate. Much of this could be cut in half without losing information.

1 / 3

Actionability

There is no executable code, no concrete templates, no example README.md structure, no example registry snippet format, and no specific file paths or commands. The skill describes what to do abstractly ('Generar el código para los siguientes archivos') without showing how. A skill about creating skills should include at least a template or concrete example of the output.

1 / 3

Workflow Clarity

The three phases provide a reasonable sequence (gather requirements → generate files → deploy), but there are no validation checkpoints. Phase 3 involves destructive filesystem operations (creating folders, writing files, updating a registry) with no verification steps—no 'check if folder exists,' no 'validate README structure,' no 'confirm registry update succeeded.' This caps the score at 2 per the rubric's feedback loop requirement for destructive operations.

2 / 3

Progressive Disclosure

Everything is in a single monolithic file with no references to supporting materials. There's no link to the 'Estándar de Diamante' specification, no reference to the actual registry file format, no template files, and no example skills to follow. For a skill about creating other skills, the absence of any referenced supporting documentation is a significant gap.

1 / 3

Total

5

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
sickn33/antigravity-awesome-skills
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.