create-agent

Create new agents for the code-forge application. Agents are stored as .md files in the <cwd>/.forge/agents directory with YAML frontmatter (id, title, description, reasoning, tools, user_prompt) and markdown body containing agent instructions. Use when users need to add new agents, modify existing agents, or understand the agent file structure.

Quality

81%

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

Quality

Content

62%Weight 40%Scale 1-3

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

The content is highly actionable with clear, validated workflows, but it is severely verbose and repetitive and fails to use progressive disclosure — everything is crammed into a single monolithic file. Cutting duplication and offloading templates/examples into reference files would dramatically reduce tokens.

Suggestions

Collapse the redundant frontmatter template (currently repeated ~6 times) and the repeated file-location note into a single canonical statement, removing the near-duplicate agent-type examples and agent templates that restate the same content.

Move the complete sample agents, the three agent-type templates, and the 'Common Mistakes' gallery into separate reference files under ./references/ (e.g. TEMPLATES.md, EXAMPLES.md) and link to them one level deep from a concise overview.

Delete concept explanations Claude already knows (e.g. what YAML frontmatter is, generic descriptions of tool categories) and keep only the forge-specific conventions, field rules, and validation steps.

Dimension	Reasoning	Score
Conciseness	The ~1100-line body is heavily padded and repetitive: the frontmatter template recurs ~6 times, the `<cwd>/.forge/agents` location note is restated 5+ times, and the three agent-type examples plus the three agent templates duplicate the same material, much of it concepts Claude already knows.	1 / 3
Actionability	Provides complete, copy-paste-ready agent file templates with all required frontmatter fields and full body sections, plus concrete good/bad comparisons (e.g. CamelCase vs hyphenated IDs, too-many-tools vs correct tool lists).	3 / 3
Workflow Clarity	Creating an agent is sequenced (Step 1-3) and backed by a checkbox validation checklist, a 'Testing Your Agent' section, and a 'Verification' list that acts as explicit validation checkpoints with feedback loops.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but no bundle files exist and all content — full templates, complete sample agents, reference material — lives inline in one ~1100-line file rather than being split into referenced files.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 strong across all dimensions: it states concrete actions, natural trigger terms, an explicit 'Use when' clause, and a clear code-forge niche in third-person voice. No material weaknesses to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create new agents', 'add new agents, modify existing agents, or understand the agent file structure' — and specifies the exact storage format (`.md` files, frontmatter fields), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Create new agents for the code-forge application... stored as .md files... with YAML frontmatter') and when ('Use when users need to add new agents, modify existing agents, or understand the agent file structure').	3 / 3
Trigger Term Quality	Triggers 'add new agents, modify existing agents, or understand the agent file structure' are natural phrasings a user would actually say, with good coverage of the skill's use cases rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped to 'the code-forge application' with distinct, domain-specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
skill_md_line_count	SKILL.md is long (1105 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: tailcallhq/forgecode
Path: .forge/skills/create-agent/SKILL.md
Commit: 1ca089a

Reviewed: 7 days 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.