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

73%

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 ./.forge/skills/create-agent/SKILL.md

Quality

Content

60%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 highly actionable with strong templates and validation checkpoints, but it is severely bloated by duplicated agent examples and lacks any progressive disclosure: material that belongs in separate reference files is inlined into a single monolith.

Suggestions

Collapse the redundant Example / Agent Type / Template sections for forge, sage, and muse into a single set of canonical templates; remove the repeated Quick Reference and Verification restatements of the same rules.

Move the full agent templates and the Common Mistakes catalog into separate reference files under references/ and link to them one level deep, keeping SKILL.md as a concise overview.

Trim generic explanations of fields and concepts Claude already knows, retaining only the forge-specific conventions (file location, required frontmatter, tool selection rules).

Dimension	Reasoning	Score
Conciseness	The ~1100-line body is noticeably verbose with heavy redundancy: the same agent structures (forge, sage, muse) appear as Example, Agent Type, and Template sections with near-verbatim duplication, and Validation/Testing/Verification/Quick Reference all restate the same guidance.	2 / 5
Actionability	Provides fully executable, copy-paste-ready frontmatter examples, complete agent templates, field-by-field specs, tool lists, and concrete file-path conventions covering the common cases.	5 / 5
Workflow Clarity	"Creating a New Agent" gives a clear 3-step sequence and the Validation Checklist / Testing / Verification sections provide explicit checkpoints and a validate-then-fix loop, with only minor validation gaps.	4 / 5
Progressive Disclosure	No bundle files exist and everything (three full agent templates, common-mistakes catalog, reference material) is inlined into one monolithic 1100-line file with no offloaded references or clear one-level-deep navigation.	2 / 5
	Total	13 / 20 Passed

Description

87%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 is strong: it clearly states what the skill does, where agent files live, and when to use it, all in third person with concrete trigger phrases. Minor room to broaden natural-term coverage (synonyms, file extensions).

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("Create new agents", "add new agents, modify existing agents") plus concrete structural details (file location, the six frontmatter fields), with minor gaps in coverage of editing nuances.	4 / 5
Completeness	Explicitly answers both what (agents stored as .md files in <cwd>/.forge/agents with named frontmatter fields) and when ("Use when users need to add new agents, modify existing agents, or understand the agent file structure").	5 / 5
Trigger Term Quality	Natural triggers like "add new agents, modify existing agents, or understand the agent file structure" are present, but common synonyms and file-extension triggers (e.g., .forge/agents, .md) are not exhaustively covered.	4 / 5
Distinctiveness Conflict Risk	Scoped specifically to the code-forge application and the .forge/agents directory, giving it a clear niche and minimal conflict risk with other skills.	5 / 5
	Total	18 / 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
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: 6ed5d37

Reviewed: 24 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.