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

78%

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-command/SKILL.md

Quality

Content

70%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 and workflow-clear with strong validation and feedback loops, but it is severely over-long due to extensive repetition and lacks any progressive disclosure (no bundle files, everything inlined in a 700-line monolith). The biggest win is de-duplicating repeated examples and rules and splitting the template/checklist material into reference files.

Suggestions

De-duplicate the repeated content: the <cwd>/.forge/commands CRITICAL rule, the verbatim check-command example, the forge list command verification block, and the naming rules each appear 3-8 times — state each once and reference it.

Introduce progressive disclosure by moving the template gallery, the common-mistakes catalog, and the full validation checklist into separate reference files under references/, keeping SKILL.md as a lean overview that links to them.

Cut the redundant Command Types / Command Templates / Common Patterns sections, which re-cover the same simple/multi-step/automated/git examples already shown in the Example Command File section.

Dimension	Reasoning	Score
Conciseness	The ~700-line body is heavily padded by repetition: the same check command with cargo fmt/clippy/insta tags appears verbatim multiple times, the <cwd>/.forge/commands CRITICAL rule is restated 8+ times, the forge list command verification block is duplicated verbatim, and naming rules repeat across four sections, fitting 'noticeably verbose; several unnecessary padded sections' rather than the more egregious 1 because it does not over-explain basic concepts.	2 / 5
Actionability	Provides copy-paste-ready, fully executable guidance: concrete directory paths, complete <lint>/<test>/<shell> tag examples with real commands (cargo fmt --all, cargo insta test, docker build, kubectl set image), complete frontmatter templates, and example galleries covering the common cases, matching the top anchor.	5 / 5
Workflow Clarity	Offers a sequenced creation process (Steps 1-3), a detailed validation checklist, a numbered testing section with a forge-recognition verification step (forge list command --custom), and an explicit error-recovery feedback loop ("If your command doesn't appear... check:"), matching the 'clear sequence with explicit validation steps and feedback loops' anchor.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ all absent) and the entire 700-line body is a monolithic inlined file with no external references; section headers give it some structure, but large blocks that clearly belong in separate files (template gallery, common-mistakes catalog, validation checklist) are inlined, fitting the 'some structure but content that should be separate is inline' anchor rather than 4 (which requires well-placed references) or 2 (which requires minimal structure).	3 / 5
	Total	15 / 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.

A strong, well-structured description that clearly states both purpose and explicit trigger conditions, scoped to a distinct niche. It is slightly below maximum on specificity and trigger-term coverage only because a few more synonyms/variants would round it out.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("add new commands, modify existing commands, or understand the command file structure") plus the <lint>/<test> tag support, with only minor coverage gaps, matching the 'lists several specific actions' anchor rather than the more comprehensive 5.	4 / 5
Completeness	Explicitly answers what ("Create new commands for the code-forge application...") and when ("Use when users need to add new commands, modify existing commands, or understand the command file structure") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ("new commands", "modify existing commands", "command file structure", "automated workflows", "lint", "test") but is missing common synonyms/variants, fitting the 'good keyword coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	Scoped to the code-forge application and the .forge/commands directory with distinct triggers (<lint>/<test> tags, the .forge/commands path), giving it a clear niche with minimal conflict risk.	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 (710 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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