Name: coding-agent
Rating: 64.8 (1 reviews)
Author: fernandezbaptiste

coding-agent

Incremental development agent with TDD workflow. Use when implementing features one at a time, following test-driven development, making commits, or resuming development work.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/coding-agent/SKILL.md

The canonical home for this skill is coding-agent in fernandezbaptiste/Skrillz

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-structured, actionable overview with real bundle references and a clearly sequenced TDD workflow including verification checkpoints. The main weakness is token-heavy ASCII diagrams that add decoration rather than information.

Suggestions

Replace the large ASCII box-drawing diagrams (Session Protocol, TDD Cycle) with plain numbered lists to cut tokens without losing information.

Add an explicit error-recovery branch to the TDD workflow (e.g. 'if the test does not pass, fix the implementation and re-run before marking complete').

Include the CodingAgent constructor/import context (e.g. how project_dir is obtained) so the Quick Start snippet is fully self-contained.

Dimension	Reasoning	Score
Conciseness	The content is mostly useful and avoids explaining concepts Claude already knows, but the large ASCII box-drawing diagrams for the Session Protocol and TDD Cycle are decorative token padding that could be tight numbered lists, matching the 'mostly efficient but could be tightened' anchor at 3.	3 / 5
Actionability	Quick Start provides executable Python using the real CodingAgent API and the commit format includes a concrete filled-in example, with only minor gaps (e.g. no import/constructor setup beyond the snippet), fitting the 'mostly executable' 4 anchor.	4 / 5
Workflow Clarity	The 8-step Session Protocol and TDD cycle are clearly sequenced with explicit verification checkpoints ('Verify test fails', 'Verify test passes', 'VERIFY BEFORE MARKING'), but no explicit error-recovery branch is spelled out, holding it at 4 rather than 5.	4 / 5
Progressive Disclosure	The body is a clear overview that pushes detail to one-level-deep, well-signaled references — all three references/.md and four scripts/.py paths listed exist on disk — with a dedicated References and Scripts section, matching the top anchor.	5 / 5
	Total	16 / 20 Passed

Description

83%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 cleanly answers both what the skill does and when to use it, with several concrete trigger phrases and a distinct TDD-focused niche. The main gap is missing synonym variations in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'implementing features one at a time, following test-driven development, making commits, or resuming development work' — with only minor coverage gaps, matching the 'several specific actions' anchor rather than the 1-2 action anchor at 3.	4 / 5
Completeness	It explicitly states what ('Incremental development agent with TDD workflow') and when ('Use when implementing features one at a time, following test-driven development, making commits, or resuming development work') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'implementing features', 'making commits', and 'resuming development work' give good keyword coverage, but common synonyms/variations are missing, so it sits at 4 rather than the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The TDD/incremental-development framing carves a fairly distinct niche, though 'implementing features' and 'making commits' could overlap with generic coding skills, placing it at 4 rather than the minimal-conflict 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: .claude/skills/coding-agent/SKILL.md
Commit: 93ed392

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.