grok

Delegate coding to xAI Grok Build CLI (features, PRs).

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/autonomous-ai-agents/grok/SKILL.md

Quality

Content

75%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 copy-paste commands and clear multi-step workflows backed by explicit validation checkpoints, and it is well-structured for a CLI orchestration guide. Its main weaknesses are repetition of the same flag guidance across multiple sections and volatile identifiers that are not flagged as time-sensitive.

Suggestions

Consolidate the repeated --no-auto-update / --always-approve guidance into one authoritative spot and cross-reference it instead of restating in the flag table, deep dive, pitfalls, and rules.

Segregate time-sensitive identifiers (CLI version 0.1.1, model grok-build-0.1, package @xai-official/grok) into a clearly marked version/compatibility section so they don't penalize conciseness.

Add an explicit post-commit/post-push verification step (e.g. check CI status or re-read the diff) to the parallel-worktree workflow to close the validation gap.

Dimension	Reasoning	Score
Conciseness	The prose is terse and assumes Claude's competence (no concept padding), but the same guidance (notably --no-auto-update and --always-approve) is repeated across the flag table, deep-dive examples, pitfalls, and rules, and volatile identifiers (version 0.1.1, model grok-build-0.1) are not segregated in a deprecated/old-patterns section.	3 / 5
Actionability	Throughout the body there are copy-paste-ready terminal(command=...) invocations with concrete flags, workdirs, timeouts, plus executable examples for output formats, session UUIDs, worktrees, and PR posting that cover the common cases.	5 / 5
Workflow Clarity	Multi-step workflows (audit→markdown, PR review, parallel worktrees) are clearly sequenced with explicit validation/feedback loops (e.g. verify first lines with read_file() before overwriting), but the parallel-worktree path commits and pushes without a post-action verification checkpoint.	4 / 5
Progressive Disclosure	The single SKILL.md is well-organized with clear section headers and reads as a cohesive CLI orchestration guide, but at ~275 lines the reference material (flag table, config TOML, subcommand list) could be split into separate files; no bundle files exist.	4 / 5
	Total	16 / 20 Passed

Description

53%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 clearly names the tool and its core purpose but lacks an explicit "Use when..." trigger clause and natural synonyms that would drive reliable skill selection. It is reasonably distinct from sibling skills thanks to the named CLI, yet trigger-term coverage is thin.

Suggestions

Add an explicit trigger clause, e.g. "Use when delegating coding tasks to Grok — building features, refactoring, PR reviews, or batch issue fixing."

Include more natural user phrasings/synonyms ("refactor", "code review", "build", "fix issues") to improve trigger-term quality.

Clarify what distinguishes Grok from sibling skills (codex/claude-code) within the description to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	Names the domain ("Delegate coding tasks") and tool ("xAI Grok Build CLI") with two concrete task types ("features, PRs"), but coverage is not comprehensive and the verb is fairly generic.	3 / 5
Completeness	There is a clear "what" (delegate coding tasks to Grok Build CLI) but no explicit "Use when..." trigger clause, so per the rubric the "when" is only weakly implied and completeness is capped at 3.	3 / 5
Trigger Term Quality	Relevant keywords appear ("coding", "features", "PRs", "Grok", "xAI"), but common natural synonyms users would say ("refactor", "code review", "build") are missing.	3 / 5
Distinctiveness Conflict Risk	Tied to a named specific CLI (Grok/xAI), so mostly distinct from generic skills, with only minor overlap risk against sibling coding-agent skills like codex/claude-code.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/autonomous-ai-agents/grok/SKILL.md
Commit: 6680afb

Reviewed: about 4 hours 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.