CtrlK
BlogDocsLog inGet started
Tessl Logo

coding-agent

Authoring playbook for building agents that write, edit, review, or refactor code. Use this when the user asks for an agent that writes scripts, generates code, reviews pull requests, refactors a codebase, fixes bugs, implements features, writes tests, or works with programming languages such as Python, TypeScript, JavaScript, Go, Rust, SQL, or shell.

72

Quality

88%

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

77%

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

The body is highly actionable with a concrete template and explicit completion/validation checkpoints, and it assumes Claude's competence rather than explaining basics. It loses points for redundancy across enforcement sections and for keeping all content inline in one file with no progressive disclosure to references.

Suggestions

Deduplicate the verbatim clone sentence, the no-workspace refusal rule, and the completion criteria so each appears once, with enforcement sections pointing back to the canonical location rather than restating.

Move the full system prompt template and/or the complete worked example into a reference file under references/, keeping SKILL.md as a concise overview with a clearly signaled link.

Consolidate 'Mode selection' prose with the template's mode sections to remove the second restatement of the refusal and workspace requirements.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence, but several rules are restated across sections — the verbatim clone sentence, the no-workspace refusal rule, and the completion criteria each appear in the template, the 'Required behavioral rules' list, and the 'Mode selection' prose — adding redundancy that could be tightened.

2 / 3

Actionability

Provides a copy-paste-ready system prompt template with placeholders, concrete identity/description patterns, a capability preference order, and a full worked example, giving fully executable, specific guidance for producing an agent.

3 / 3

Workflow Clarity

Sequences the authoring flow (when-to-use → identity → mode → template → rules → capabilities → anti-patterns → example) and includes an explicit 'Completion criteria — you are NOT done until' checklist with validation checkpoints ('verification performed', 'narrowest relevant check run OR explicit not-run reason').

3 / 3

Progressive Disclosure

The skill is well-organized into clearly headed sections, but it is a single 135-line file with no bundle references, and large inline blocks (the full system prompt template and worked example) could be split into reference files rather than kept monolithic; this sits below the 'one-level-deep references' anchor 3.

2 / 3

Total

10

/

12

Passed

Description

100%

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 precise, action-oriented, and fully addresses both what the skill does and when to invoke it, with rich natural trigger terms and a distinct coding-agent niche. It uses correct third-person voice throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'write, edit, review, or refactor code' plus 'writes scripts, generates code, reviews pull requests, refactors a codebase, fixes bugs, implements features, writes tests' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

States what it does ('Authoring playbook for building agents that write, edit, review, or refactor code') and when to use it via an explicit 'Use this when the user asks for an agent that...' clause, clearly answering both what and when.

3 / 3

Trigger Term Quality

Covers natural terms users would say — 'code', 'scripts', 'pull requests', 'refactor', 'bugs', 'tests', and languages 'Python, TypeScript, JavaScript, Go, Rust, SQL, or shell' — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche — authoring coding agents specifically — with distinct triggers tied to code/PR/refactor/bug/test requests, making overlap with non-coding skills unlikely.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mastra-ai/mastra
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.