autonomous-loop

Main orchestration loop for autonomous coding. Use when running autonomous sessions, orchestrating feature completion, managing continuous loops, or coordinating agent lifecycle.

Quality

66%

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-loop/SKILL.md

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 SKILL.md body is a concise, well-structured overview with executable Quick Start code and a clear validated workflow including rollback feedback. Its key defect is progressive disclosure: two of its referenced detail files do not exist, leaving dangling navigation links.

Suggestions

Create the missing references/LOOP-LIFECYCLE.md and references/CONTINUATION-PROTOCOL.md files (or remove the References section) so signaled navigation actually resolves.

Make the workflow steps concrete and executable (e.g., actual checkpoint/rollback commands or script invocations) instead of abstract diagram labels to push workflow clarity and actionability toward 5.

Add a minimal runnable example that defines 'project_dir' and shows how a feature list is supplied, closing the actionability gap in the Quick Start.

Dimension	Reasoning	Score
Conciseness	The body is efficient with no concept-explaining padding, assuming Claude's competence; the only potentially trimmable element is the large ASCII workflow diagram, keeping it just below the lean-every-token-earns-its-place bar of anchor 5.	4 / 5
Actionability	Provides concrete executable Quick Start code for AutonomousLoop and LoopConfig plus the LoopResult dataclass, but has minor gaps such as the undefined 'project_dir' and no example of constructing the feature list, fitting anchor 4 rather than fully copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	The workflow shows a clear INITIALIZE -> FEATURE LOOP -> CONTEXT CHECK -> COMPLETION sequence with validation (E2E tests, pass/fail branching, checkpoint, rollback) and a feedback loop, but the steps are abstract and diagrammatic without concrete recovery commands, fitting anchor 4; the destructive/batch cap does not apply because validation is present.	4 / 5
Progressive Disclosure	The body is a well-organized overview and the four referenced scripts exist, but both referenced reference files (references/LOOP-LIFECYCLE.md and references/CONTINUATION-PROTOCOL.md) are missing, so the signaled one-level-deep navigation is broken, fitting anchor 3 rather than the clean reference structure of anchor 4-5.	3 / 5
	Total	15 / 20 Passed

Description

62%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 a clear 'what' and an explicit multi-trigger 'Use when' clause, avoiding first/second person and vague fluff. Its main weakness is that the capabilities are described at an orchestration abstraction level rather than with concrete, distinctive actions.

Suggestions

Add one or two concrete granular actions to the 'what' portion (e.g., 'implements features with TDD, runs E2E verification, checkpoints and rolls back on failure') to lift specificity and completeness toward 5.

Include more natural trigger synonyms a user would actually say (e.g., 'long-running coding tasks', 'unattended feature work', 'self-driving development') to broaden trigger-term coverage.

Sharpen distinctiveness by naming what makes this loop unique versus generic agent-lifecycle or session-management skills.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several actions ('orchestrating feature completion, managing continuous loops, coordinating agent lifecycle') but they are high-level orchestration verbs rather than granular concrete operations, matching the anchor-3 example breadth without anchor-4's concrete specificity.	3 / 5
Completeness	An explicit 'Use when' clause with four concrete triggers clears the missing-trigger cap, and the 'what' ('Main orchestration loop for autonomous coding') is clear, but the 'what' is a single thin phrase rather than the multi-action statement of anchor 5.	4 / 5
Trigger Term Quality	Contains relevant keywords ('autonomous sessions', 'feature completion', 'continuous loops', 'agent lifecycle') but lacks common synonyms and variations a user might naturally say, fitting anchor 3 rather than the broader coverage of anchor 4.	3 / 5
Distinctiveness Conflict Risk	The autonomous-coding orchestration niche is mostly distinct with specific triggers, but terms like 'agent lifecycle' and 'continuous loops' could overlap with related orchestration/lifecycle skills, fitting anchor 4's minor overlap risk.	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

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