CtrlK
BlogDocsLog inGet started
Tessl Logo

aiox-dev

Full Stack Developer (Dex). Use for code implementation, debugging, refactoring, and development best practices

45

Quality

47%

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

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/aiox-dev/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 lean and mostly actionable with concrete commands and file paths, but its workflows are underspecified: the multi-step development and rollback operations lack sequenced steps and validation checkpoints, which the rubric caps low for destructive/batch operations. Progressive disclosure is acceptable but references external project files rather than a bundled reference structure.

Suggestions

Add an explicit sequenced workflow with validation checkpoints for destructive/batch commands (especially *rollback --hard and *execute-subtask), e.g., a validate-then-proceed loop.

Surface what each starter command actually does in 1 line so Claude can choose correctly without loading external agent files.

If .aiox-core artifacts are the source of truth, bundle the key reference files under ./references and link them clearly one level deep instead of relying on external project paths.

DimensionReasoningScore

Conciseness

The body is brief and non-padded, listing commands and protocol steps without explaining concepts Claude already knows; it is efficient with only minor filler ('Stay in this persona until...').

4 / 5

Actionability

It gives concrete, executable commands (node greeting script, *develop modes, *rollback --hard) and exact file paths to load; guidance is mostly executable with only minor gaps in what each command does internally.

4 / 5

Workflow Clarity

The activation protocol is a rough 4-step sequence but the core development workflows (*develop, *execute-subtask, *rollback) have no sequenced steps or validation checkpoints; destructive/batch operations like *rollback --hard lack any validation, fitting 'rough sequence, many gaps, validation absent'.

2 / 5

Progressive Disclosure

Structure is reasonable (When To Use, Activation Protocol, Starter Commands, Non-Negotiables) and points to external artifacts (.aiox-core/*.md) one level deep, but those references are to project files outside any bundle and are not clearly signaled as navigable reference files; organization is adequate but could be tighter.

3 / 5

Total

13

/

20

Passed

Description

38%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 intelligible but generic: it labels a broad full-stack developer role without concrete, distinctive triggers or a strong 'Use when' clause. It reads more as a persona label than a scoped capability, leaving it with weak distinctiveness and high conflict risk.

Suggestions

Add an explicit 'Use when the user asks to implement a story task, debug, or refactor code' trigger clause so the 'when' is concrete rather than implied.

Narrow the scope with distinctive triggers (e.g., reference the *develop/*execute-subtask workflow or .aiox-core artifacts) to reduce overlap with generic coding skills.

Replace generic category words ('development best practices') with specific concrete actions the skill performs.

DimensionReasoningScore

Specificity

The description names the domain ('Full Stack Developer') and a minimal action set ('code implementation, debugging, refactoring'), but the actions are generic categories rather than concrete operations, matching the 'names domain but actions are minimal/generic' anchor.

2 / 5

Completeness

It states a clear 'what' (full stack development role) but the 'when' is only weakly implied via 'Use for ...'; there is no 'Use when the user ...' trigger clause, which the guidelines cap at 3.

3 / 5

Trigger Term Quality

It includes some natural terms a user might say ('code implementation', 'debugging', 'refactoring') but lacks common synonyms and any file/tool extensions; coverage is relevant but incomplete, fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The scope is very broad — general full-stack development overlaps heavily with many coding skills, creating high overlap risk, matching the 'very broad; high overlap risk' anchor.

2 / 5

Total

10

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
SynkraAI/aiox-core
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.