create-command

Create new commands for the code-forge application. Commands are stored as .md files in the <cwd>/.forge/commands directory with YAML frontmatter (name, description) and markdown body containing command steps. Use when users need to add new commands, modify existing commands, or understand the command file structure. Supports special command tags like <lint> and <test> for automated workflows.

Quality

82%

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

65%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 concrete, executable examples and clear directory/tag guidance, but it suffers from significant redundancy across many near-duplicate example and reference sections. Consolidating the repeated structure, templates, and verification steps would materially improve conciseness and workflow clarity.

Suggestions

Consolidate the overlapping sections (Example Command File, Complete Sample Command, Command Types, Command Templates, Common Patterns, and Quick Reference) into a single canonical structure reference plus one template gallery to remove repeated examples like the 'check' command that appear three or more times.

Merge the duplicated 'Testing Your Command' and 'Verification' sections into one validate->fix->retry feedback loop with explicit checkpoints, since they both repeat the same 'forge list command' checks.

Trim the re-explanations of basic rules (naming, tag placement, frontmatter fields) that already appear earlier, keeping only the Quick Reference as a compact summary.

Dimension	Reasoning	Score
Conciseness	The body is roughly 700 lines with heavy redundancy: the command-file structure and the 'check' example recur across Example Command File, Complete Sample Command, Command Types, Command Templates, Common Patterns, Common Mistakes, and Quick Reference. It is mostly efficient and the examples aid actionability, but the repetition pads the skill beyond what earns its place, so it does not reach the lean level-3 anchor.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: exact directory paths ('<cwd>/.forge/commands'), executable tag commands such as '<lint>cargo +nightly fmt --all; cargo +nightly clippy --fix ...', full templates, and a specific verification command 'forge list command --custom'. This matches the fully-executable level-3 anchor.	3 / 3
Workflow Clarity	Sequences are present (Creating a New Command Steps 1-3, a 5-step Testing Your Command list, a Verification list), but validation is duplicated and loose rather than a tight validate->fix->retry loop, and the two verification sections overlap. It exceeds the unclear level-1 anchor but lacks the explicit checkpoint feedback loops of level 3.	2 / 3
Progressive Disclosure	There are no bundle files and all content lives in a single monolithic SKILL.md; sections are well-organized with clear headers, but the large amount of inline, duplicated content that could be consolidated or split keeps it below the cleanly-organized level-3 anchor for a no-reference skill.	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 specific, uses third-person voice, includes an explicit 'Use when' trigger clause, and carves out a distinctive niche around code-forge command files. It satisfies all four dimensions at the top of the scale with no over-claims or vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'Create new commands', 'modify existing commands', 'understand the command file structure', and 'Supports special command tags like <lint> and <test>', matching the level-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	It explicitly answers both what (commands stored as .md files with YAML frontmatter and special tags) and when ('Use when users need to add new commands, modify existing commands...'), matching the level-3 anchor that requires both with explicit triggers.	3 / 3
Trigger Term Quality	The clause 'Use when users need to add new commands, modify existing commands, or understand the command file structure' uses natural phrasing a user would actually say, with good coverage of the main variations; not merely a 2-level 'Works with PDF files' style trigger.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow and specific (code-forge command files in <cwd>/.forge/commands with <lint>/<test>/<shell> tags), making it unlikely to trigger for an unrelated skill; it clearly exceeds the level-2 'could still overlap' anchor.	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 (710 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: tailcallhq/forgecode
Path: .forge/skills/create-command/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.