Name: auto-claude-cli
Rating: 64.8 (1 reviews)
Author: fernandezbaptiste

auto-claude-cli

Auto-Claude CLI command reference and usage patterns. Use when running specs, managing builds, checking status, or using CLI commands for autonomous coding tasks.

Quality

77%

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 ./.claude/skills/auto-claude-cli/SKILL.md

The canonical home for this skill is auto-claude-cli in fernandezbaptiste/Skrillz

Quality

Content

71%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 content is highly actionable and well-sequenced with a real QA feedback loop, but it is hurt by command repetition across sections and by inlining a full CLI reference instead of pointing to the existing CLI-USAGE.md and CLAUDE.md bundle files.

Suggestions

Consolidate the duplicated command listings: keep the Quick Reference table and the per-command options tables, but avoid restating the same run.py/spec_runner.py invocations verbatim in the Core Commands code blocks.

Replace the inlined detailed CLI usage with a pointer to references/CLI-USAGE.md (e.g. "See [CLI-USAGE.md](references/CLI-USAGE.md) for the full command reference") and reference references/CLAUDE.md for framework context, keeping SKILL.md as an overview.

Add an explicit validation/verify checkpoint before the destructive --merge step in the workflow example (e.g. confirm QA status and review pass before merging).

Dimension	Reasoning	Score
Conciseness	The body is mostly operational command tables and code with little concept-explanation, but the same commands (e.g. "run.py --spec 001 --review/--merge") are repeated across the Quick Reference table, Core Commands sections, and Command Options tables, adding noticeable redundancy that could be tightened.	3 / 5
Actionability	The content is almost entirely concrete, copy-paste-ready bash commands and code examples that cover the common cases (creating specs, running builds, QA, merging, debugging), matching the fully-executable top anchor.	5 / 5
Workflow Clarity	The "Complete Feature Development" example is a clearly numbered sequence (create → run → review → test → merge) and the QA loop is an explicit feedback loop, but not every step has an explicit validation checkpoint and the destructive merge relies on implicit rather than labeled verification.	4 / 5
Progressive Disclosure	The body has good section structure, but it inlines a full ~280-line CLI reference that overlaps with the provided references/CLI-USAGE.md bundle file and never signals either bundle file (CLI-USAGE.md or CLAUDE.md) — references are effectively absent rather than one level deep.	3 / 5
	Total	15 / 20 Passed

Description

83%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 states both what the skill provides and when to use it, with concrete, fairly natural trigger phrases tied to a distinct Auto-Claude CLI niche. Its only weakness is that a couple of trigger terms ("checking status", "CLI commands") are generic enough to risk minor overlap.

Dimension	Reasoning	Score
Specificity	"CLI command reference and usage patterns" names the domain and "running specs, managing builds, checking status, or using CLI commands" lists several concrete actions, but "usage patterns" is slightly generic and coverage of actions is high-level rather than comprehensive.	4 / 5
Completeness	It explicitly answers both what ("Auto-Claude CLI command reference and usage patterns") and when ("Use when running specs, managing builds, checking status, or using CLI commands") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Triggers like "running specs", "managing builds", "checking status", and "CLI commands" are natural phrases a user would say, with good coverage, though some variations (e.g. "spec runner", "run.py") are absent.	4 / 5
Distinctiveness Conflict Risk	The "Auto-Claude CLI" niche is distinct, but generic triggers like "checking status" and "CLI commands" create minor overlap risk with other CLI/status skills.	4 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: .claude/skills/auto-claude-cli/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.