CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-development

This skill should be used when the user asks to "create an agent", "write an agent", "build an agent", or wants to add new agent capabilities to Claude Code.

76

1.84x
Quality

65%

Does it follow best practices?

Impact

96%

1.84x

Average score across 3 eval scenarios

SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./plugins/toolkit/skills/agent-development/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 skill body is concise and well-organized as a compact reference, excelling at progressive disclosure for a short skill. Its weakness is actionability and workflow clarity: it tells Claude about agent colors and behaviors but gives little concrete, sequenced guidance on how to actually construct an agent definition.

Suggestions

Add a minimal agent-creation template showing the full frontmatter plus an instructions body, so the core task is executable rather than implied.

Provide a short sequenced workflow (e.g. 1. pick color by purpose, 2. write description with triggers, 3. add instructions, 4. hot-reload) with the existing hot-reload note as the final checkpoint.

List the required/optional frontmatter fields (name, description, color, tools) explicitly rather than only showing color in the example.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, using a compact color-convention table and brief notes, matching 'Efficient; minor instances of over-explanation that could be trimmed'; the trailing sentence on permission resilience ('This makes autonomous workflows more resilient...') is mildly explanatory, keeping it just below 5.

4 / 5

Actionability

A concrete YAML frontmatter example with a color field and a color-to-type table provide some executable guidance, but the core task of actually building an agent is left underspecified with no template structure, required fields, or example instructions block, matching 'Some concrete guidance but incomplete; missing key details'; it is not 4 because key creation details are absent and not 2 because the yaml example is genuinely concrete.

3 / 5

Workflow Clarity

There is no real multi-step sequence for creating an agent — the content is organized reference material (colors, behavior, hot-reload note) rather than a sequenced workflow, matching 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit' in spirit; it is not lower because the material is organized, and not higher because no creation workflow is laid out at all.

3 / 5

Progressive Disclosure

The body is under 50 lines with no external references needed and is organized into clear sections (Agent Colors, Agent Behavior, Important) plus a table, matching the guideline that short skills with no need for external references can score 5 with well-organized sections; no bundle files exist to verify, and none are required.

5 / 5

Total

15

/

20

Passed

Description

65%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 has strong, natural trigger phrasing with good synonym coverage and clear niche targeting, but the 'what' is only implied and the listed actions collapse to a single generic capability. Tightening the action list and stating the capability explicitly would lift it above the midpoint.

Suggestions

State the concrete capability explicitly, e.g. 'Creates and modifies Claude Code agent definition files (frontmatter + instructions)' before the trigger clause.

Add at least one more distinct concrete action (e.g. 'configure agent colors', 'set tool permissions') so the action list is not three synonyms of one task.

Add a tail 'Use when...' clause summarizing the triggers to make the when/what split fully explicit.

DimensionReasoningScore

Specificity

The description names the agent-development domain but the actions ("create an agent", "write an agent", "build an agent") are three synonymous phrasings of one generic action rather than distinct concrete capabilities, matching the anchor 'Names the domain but actions are minimal or generic'; it does not reach 3 because no second distinct concrete action is listed.

2 / 5

Completeness

It explicitly states when to use the skill ("should be used when the user asks to...") and implies the what (creating/adding agent capabilities), matching 'Has both what and when; when could be more explicit or specific'; the what is only weakly stated rather than crisply enumerated, so it does not reach 5.

4 / 5

Trigger Term Quality

Phrases like "create an agent", "write an agent", "build an agent", and "add new agent capabilities to Claude Code" are natural user utterances with good synonym coverage, fitting 'Good keyword coverage; a few natural terms missing'; it falls short of 5 because there are no file-extension or additional variant triggers and the set is otherwise limited.

4 / 5

Distinctiveness Conflict Risk

The agent-creation niche is clear with distinct trigger phrases, matching 'Mostly distinct; minor overlap risk with closely related skills'; it does not reach 5 because "agent" is a broad term that could overlap with related Claude Code skills.

4 / 5

Total

14

/

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
dwmkerr/claude-toolkit
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.