add-skill

Use this skill when the user asks to "add a skill", "create a skill", "new skill", "write a skill for", "skill for cx <something>", "add a user-facing skill", "create a SKILL.md", "teach an agent how to use", "agent skill for", "document a command as a skill", "make a skill", "add skill to skills/", "create agent instructions for", "build a skill", or wants to create a new user-facing skill in the skills/ directory that teaches AI agents how to use a cx CLI command. Use this even when the user is following the add-command workflow and reaches the skill creation step.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

78%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.

A well-structured workflow skill that clearly sequences the skill-creation process with a verification checklist and good progressive disclosure to a reference guide. Slight room to tighten explanatory asides and make the validation feedback loop more explicit.

Suggestions

Tighten rationale asides (e.g., the sentence explaining why agents should study existing skills first) to lift conciseness toward the top anchor.

Make Step 4's verification an explicit feedback loop (e.g., 'If any check fails, return to the relevant step, fix, and re-verify before proceeding') rather than a soft 'if not, add missing steps' note.

Dimension	Reasoning	Score
Conciseness	The body is well-organized into numbered steps with specific file paths and commands and assumes Claude knows basics; it is not a 5 because a few rationale asides (e.g., "Agents that study existing skills first produce consistent, high-quality results rather than inventing new formats") could be trimmed.	4 / 5
Actionability	It gives concrete, executable guidance (create `skills/cx-<domain-name>/SKILL.md`, run `bash scripts/sync-shared-references.sh`, named sections like "§ Complete Template"), but a fair amount of detail is delegated to `contributing/adding-a-skill.md` rather than inlined, leaving minor gaps.	4 / 5
Workflow Clarity	Steps 0-4 are clearly sequenced and Step 4 provides a 7-item verification checklist with validation checks; it is not a 5 because the feedback loop is soft ("If not, add missing steps or examples") rather than an explicit validate-fix-retry cycle.	4 / 5
Progressive Disclosure	SKILL.md functions as a tight overview with well-signaled, one-level-deep references to `contributing/adding-a-skill.md`, `skills/README.md`, shared references, and the sync script, with dense material split out appropriately and easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

91%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, trigger-rich description that clearly states what the skill does and when to use it, with explicit boundary handling for the related add-command workflow. The only weakness is that several trigger phrases are generic skill-creation terms that could overlap with a general skill-creator.

Dimension	Reasoning	Score
Specificity	The description concretely specifies the action ("create a new user-facing skill in the skills/ directory that teaches AI agents how to use a cx CLI command"), the target location, and purpose, sitting above the midpoint; it is not a 5 because it centers on a single action rather than listing several distinct concrete actions.	4 / 5
Completeness	It explicitly answers both what ("create a new user-facing skill ... that teaches AI agents how to use a cx CLI command") and when ("Use this skill when the user asks to ..." plus the add-command workflow boundary), with concrete trigger phrases.	5 / 5
Trigger Term Quality	It enumerates 14 natural trigger phrases a user would actually say ("add a skill", "create a skill", "make a skill", "build a skill", "create a SKILL.md") with comprehensive synonym coverage, matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	It is scoped to a clear niche (cx CLI command skills) and clarifies the add-command boundary, but several trigger phrases ("add a skill", "make a skill", "build a skill") are generic and carry minor overlap risk with a general skill-creator, so it is not a 5.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: coralogix/cx-cli
Path: .claude/skills/add-skill/SKILL.md
Commit: 4aa811a

Reviewed: 2 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.