autonomous-opus-loop

Autonomous Claude Code operation using Opus 4.5 for intelligent continuation decisions. Use when running long tasks, multi-step implementations, overnight development, or any workflow requiring continuous autonomous operation without human intervention.

Quality

58%

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 ./skills/autonomous-opus-loop/SKILL.md

Quality

Content

42%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 thorough and mostly actionable, but it is severely over-long and inlines material that belongs in reference files, several of which it references but which do not exist in the bundle. Workflow clarity is capped by the absence of explicit validation checkpoints for an autonomous batch operation.

Suggestions

Move the embedded analyzer system prompt, full hook-mechanics explanation, and safety-pattern snippets into the referenced reference files and leave only concise pointers in SKILL.md.

Create the missing referenced files (references/analyzer-prompts.md, references/safety-patterns.md, references/integration-guide.md) or remove their entries from the References list so navigation is not broken.

Add an explicit validation/verification checkpoint to the Quick Start workflow (e.g. confirm the hook fires and the analyzer responds before declaring autonomous mode active).

Dimension	Reasoning	Score
Conciseness	The 560-line body is noticeably verbose: it re-explains hook mechanics already covered in references/hook-mechanics.md, repeats safety snippets and the architecture diagram that the reference also contains, and pads with multiple full example configurations and verbose tables that assume little of Claude.	2 / 5
Actionability	Provides concrete executable commands (install.sh, enable.sh, status.sh) and a complete settings.json hook snippet plus a full analyzer system prompt embedded in the body; minor gaps are the inline safety snippets being illustrative rather than tied to the real script.	4 / 5
Workflow Clarity	Quick Start lists numbered steps (install hook, configure objective, start claude), but this skill drives autonomous batch/long-running operation and the workflow lacks explicit validation checkpoints or a verify-before-continuing feedback loop; per the rubric the missing validation for such an operation caps this at 3.	3 / 5
Progressive Disclosure	Despite a references/ directory existing, the References section lists four reference files (analyzer-prompts.md, safety-patterns.md, integration-guide.md) that do not exist in the bundle, and large amounts of content that belong in those references (full analyzer prompts, full hook-mechanics, safety patterns) are inlined into SKILL.md, producing a monolithic body with broken navigation.	2 / 5
	Total	11 / 20 Passed

Description

75%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 is well-formed with an explicit 'Use when' trigger clause and a clear statement of what the skill does. Trigger terms are natural and coverage of common scenarios is good, though specificity could name more concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain ('autonomous Claude Code operation using Opus 4.5 for intelligent continuation decisions') and a concrete mechanism (external analyzer decides continuation), but the action framing is fairly abstract rather than listing multiple concrete operations.	3 / 5
Completeness	Clearly answers both what ('Autonomous Claude Code operation using Opus 4.5 for intelligent continuation decisions') and when via an explicit 'Use when...' clause enumerating concrete scenarios.	5 / 5
Trigger Term Quality	Includes natural user-facing phrases like 'long tasks', 'multi-step implementations', and 'overnight development' that a user would plausibly say, though it lacks some synonyms or the explicit word 'autonomous loop'.	4 / 5
Distinctiveness Conflict Risk	Targets a fairly distinct niche (external-analyzer-driven autonomous looping) with specific triggers; minor overlap risk with general long-running task skills.	4 / 5
	Total	16 / 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
skill_md_line_count	SKILL.md is long (563 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/autonomous-opus-loop/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.