looped-builder
Scaffold large implementation tasks for iterative execution with Claude in a bash loop. Creates spec.md, implementation_plan.md, prompt.md, and run.sh for autonomous multi-step coding tasks.
Install with Tessl CLI
npx tessl i github:xaneem/looped-builder-skill --skill looped-builder79
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
67%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 excels at specificity and distinctiveness by naming exact deliverables and a clear use case for autonomous multi-step coding. However, it lacks an explicit 'Use when...' clause and could benefit from more natural trigger terms that users would actually say when needing this skill.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user wants to break down a large coding task into autonomous steps, mentions iterative execution, or asks for scaffolding a multi-file implementation.'
Include more natural trigger terms users might say: 'scaffold', 'automate coding', 'break down task', 'iterative development', 'autonomous execution'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Scaffold large implementation tasks', 'Creates spec.md, implementation_plan.md, prompt.md, and run.sh'. The description names exact file outputs and the purpose (autonomous multi-step coding tasks). | 3 / 3 |
Completeness | Clearly answers 'what' (scaffolds tasks, creates specific files for autonomous execution), but lacks an explicit 'Use when...' clause. The 'when' is only implied through the description of the purpose. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'implementation tasks', 'bash loop', 'autonomous', 'multi-step coding', but misses common variations users might say like 'scaffold project', 'generate boilerplate', 'automate coding', or 'iterative development'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific file outputs (spec.md, implementation_plan.md, prompt.md, run.sh) and a clear niche (bash loop iterative execution). Unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill that provides complete, executable scaffolding for iterative implementation tasks. The workflow is clear with proper validation checkpoints and the code examples are copy-paste ready. The main weakness is verbosity—the inline templates make the skill long, and some explanatory text could be trimmed.
Suggestions
Consider moving the large markdown templates (spec.md, implementation_plan.md, prompt.md) to separate reference files and linking to them from the main skill
Trim explanatory text that Claude can infer, such as 'The output is a set of files that enable iterative, autonomous implementation' which is evident from the file list
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary explanation (e.g., explaining what the files are for when the structure is self-evident). The markdown templates are verbose and could be condensed, though they serve as useful copy-paste references. | 2 / 3 |
Actionability | Provides fully executable code for run.sh, complete markdown templates for all output files, and specific step-by-step instructions. The examples of good vs bad steps are concrete and actionable. | 3 / 3 |
Workflow Clarity | Clear 5-step sequence with explicit phases. The workflow includes validation (Step 5: Present for Review), feedback loops in the prompt.md template (check progress → implement → update → report), and explicit testing phases in the implementation plan structure. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but the skill is monolithic—all templates and instructions are inline rather than referenced from separate files. For a skill of this complexity (~200 lines), splitting templates into separate reference files would improve navigation. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.