CtrlK
BlogDocsLog inGet started
Tessl Logo

autonomous-loops

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

55

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.kiro/skills/autonomous-loops/SKILL.md

The canonical home for this skill is autonomous-loops in affaan-m/ECC

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 with executable examples and strong sequenced workflows including validation and recovery loops. Its main weakness is progressive disclosure — a ~600-line monolith with no bundled reference files — and moderate verbosity in conceptual prose sections.

Suggestions

Split each major pattern (Ralphinho, Continuous Claude, Infinite Loop) into reference files under references/ and keep SKILL.md as a concise overview with one-level-deep links.

Trim conceptual prose ("The Problem", "Why Not Negative Instructions?") to the non-obvious insight and drop the retention compatibility note or move it to metadata.

Convert the long flag tables for Continuous Claude into a linked reference so the core loop stays scannable.

DimensionReasoningScore

Conciseness

The body is dense with executable bash/code, tables, and diagrams that earn their place, but ~600 lines include conceptual prose sections ("The Problem", "Why Not Negative Instructions?", "Core Insight" quotes) and a top compatibility note that could be tightened; this matches anchor 2 (mostly efficient with some unnecessary explanation) rather than 3 (lean, every token earns its place).

2 / 3

Actionability

Concrete copy-paste-ready examples abound — `claude -p --model opus`, `continuous-claude --max-runs 10 --max-cost 5.00`, `gh pr create`, flag tables, and a full `.claude/commands/infinite.md` template — fitting anchor 3 (fully executable code/commands, specific examples) rather than 2 (incomplete/pseudocode).

3 / 3

Workflow Clarity

Multi-step processes are explicitly sequenced with validation checkpoints and feedback loops: the Sequential Pipeline has a numbered verify step with `set -e` exit propagation, Continuous Claude has CI-failure recovery (fetch run → fix → re-wait), and Ralphinho has merge-queue eviction with context fed back to the next pass; this matches anchor 3 and the destructive/batch cap is not triggered since validation steps are present.

3 / 3

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ absent) and the entire ~600-line body is a single monolithic SKILL.md with well-organized sections but no one-level-deep references splitting detailed patterns out; for a skill this large the inline content that should be separate matches anchor 2 rather than 3 (clear overview + signaled references) or 1 (deeply nested references).

2 / 3

Total

10

/

12

Passed

Description

50%

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 domain and spectrum of patterns but lacks any explicit "Use when..." trigger guidance, which caps completeness and distinctiveness. Trigger terms are present but skew technical and miss common variations.

Suggestions

Add a "Use when..." clause naming concrete triggering situations (e.g., setting up CI/CD-style dev pipelines, parallel agent orchestration, or context-persistent loops).

Broaden trigger terms with natural user phrasing such as "agent loops", "continuous development", or "running Claude unattended".

Lead with concrete capabilities (e.g., "Build, run, and coordinate autonomous Claude Code loops") before the pattern spectrum.

DimensionReasoningScore

Specificity

Quotes "Patterns and architectures for autonomous Claude Code loops" and "from simple sequential pipelines to RFC-driven multi-agent DAG systems" name the domain and two pattern archetypes, but do not list multiple concrete user-facing actions; this matches anchor 2 (names domain and some actions, not comprehensive) rather than 3 (which would enumerate specific operations).

2 / 3

Completeness

The description states what the skill covers but has no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 2 (has what, when missing/implied) rather than 3 (explicit what AND when).

2 / 3

Trigger Term Quality

"autonomous Claude Code loops", "sequential pipelines", and "multi-agent DAG" include the natural term "loops" but lean technical (DAG, RFC-driven) and omit common variations like "CI/CD", "agent loops", or "continuous"; this fits anchor 2 (some relevant keywords, missing common variations) rather than 3 (full natural-term coverage).

2 / 3

Distinctiveness Conflict Risk

"autonomous Claude Code loops" carves a recognizable niche but the absence of explicit triggers and the breadth of "patterns and architectures" leave overlap with general agent-orchestration skills, matching anchor 2 (somewhat specific but could overlap) rather than 3 (clear niche with distinct triggers).

2 / 3

Total

8

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (612 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

13

/

16

Passed

Repository
affaan-m/ECC
Reviewed

Table of Contents

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.