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.

75

Quality

92%

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

88%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.

A highly actionable, well-structured authoring playbook with concrete templates, a verbatim mandatory line, a full worked example, and an explicit completion-criteria checklist with a stop-gate. It is mostly concise and well-organized, with only mild redundancy and no progressive file-splitting.

Suggestions

Remove the duplicated restating of completion criteria across the 'Required behavioral rules' and 'Anti-patterns' sections to tighten the body.

Move the full system-prompt template and worked example into a referenced file (e.g. templates.md) so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

Mostly lean and instruction-dense with minimal concept re-explanation, but the verbatim mandatory line is repeated and several sections (anti-patterns, behavioral rules) restate the same completion-criteria guidance, adding some redundancy.

4 / 5

Actionability

Provides concrete, copy-ready templates: an exact system-prompt skeleton with fill-in placeholders, a verbatim mandatory sentence, and a full worked example showing produced name/description/tools/prompt — all directly executable.

5 / 5

Workflow Clarity

Clear sequenced authoring flow (identity → mode selection → system prompt → behavioral rules → capabilities → anti-patterns) with an explicit numbered completion-criteria checklist and 'Stop only when all applicable criteria are true' feedback-loop gate.

5 / 5

Progressive Disclosure

Well-organized single-file overview with clear section headers and no nested references, but all content is inlined into one file with no separate reference files for the templates/examples; could be split for a skill of this length.

4 / 5

Total

18

/

20

Passed

Description

96%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, specific, third-person description that clearly states the skill's purpose and provides rich natural trigger terms covering many user phrasings and language names. Its only soft spot is slight over-breadth in trigger terms, which modestly raises overlap risk with plain coding skills.

Suggestions

Consider narrowing the trigger scope to emphasize 'building/authoring an agent' rather than every code-related request, to reduce overlap with general coding skills.

Optionally include an explicit exclusion ('Do not use for one-off code questions without an agent-building outcome') to sharpen conflict avoidance.

DimensionReasoningScore

Specificity

Names a concrete domain (code authoring/agent-building) and enumerates many specific actions — writes scripts, generates code, reviews PRs, refactors, fixes bugs, implements features, writes tests — plus a wide list of target languages.

5 / 5

Completeness

Explicitly answers both 'what' (authoring playbook for agents that write/edit/review/refactor code) and 'when' via a clear 'Use this when the user asks for...' clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms users actually say ('code', 'script', 'PR', 'pull request', 'refactor', 'bug', 'review', 'tests') and concrete file/language names (Python, TypeScript, JavaScript, Go, Rust, SQL, shell).

5 / 5

Distinctiveness Conflict Risk

Niche is fairly distinct (building coding agents specifically), but the breadth of triggers (any 'code'/'function'/'script' request) creates some overlap with general coding assistance skills.

4 / 5

Total

19

/

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.

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.