parallel-run
Orchestrate parallel agent execution with git worktrees
Install with Tessl CLI
npx tessl i github:jpoutrin/product-forge --skill parallel-run69
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
40%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 identifies a specific technical niche (git worktrees for parallel agents) which makes it distinctive, but it's too terse to be effective. It lacks explicit trigger guidance ('Use when...') and doesn't enumerate the concrete actions the skill enables, making it difficult for Claude to know when to select it from a large skill library.
Suggestions
Add a 'Use when...' clause with trigger scenarios like 'Use when running multiple agents simultaneously, parallelizing tasks across branches, or when the user mentions worktrees, concurrent execution, or parallel workflows'
Expand the capabilities list with specific actions: 'Creates git worktrees, spawns parallel agent processes, coordinates multi-branch work, manages worktree cleanup'
Include natural language variations users might say: 'parallel tasks', 'run agents concurrently', 'multiple branches at once', 'speed up with parallelism'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (parallel agent execution, git worktrees) and implies an action (orchestrate), but doesn't list multiple concrete actions like 'create worktrees, spawn agents, merge results, manage branches'. | 2 / 3 |
Completeness | Provides a brief 'what' (orchestrate parallel agents with worktrees) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes relevant technical terms 'git worktrees' and 'parallel agent execution', but missing common variations users might say like 'concurrent tasks', 'multiple agents', 'parallel processing', or 'worktree'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'parallel agent execution' and 'git worktrees' is a clear, specific niche that is unlikely to conflict with other skills - this is a distinct technical capability. | 3 / 3 |
Total | 8 / 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 skill with excellent actionability and workflow clarity. The step-by-step execution instructions are concrete and the error handling is comprehensive. However, it could be more concise by removing redundant sections (cpo CLI reference duplicates earlier content) and better leverage progressive disclosure by moving the manifest format documentation to a separate reference file.
Suggestions
Move the 'cpo Manifest Format' section to a separate MANIFEST-REFERENCE.md file and link to it
Remove or consolidate the 'cpo CLI Reference' section at the end as it duplicates commands already shown in the main instructions
Tighten the 'Purpose' section - Claude doesn't need explanation of what parallel execution does
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some redundancy - the cpo CLI reference at the end duplicates information already covered, and some explanations (like what cpo does) could be tighter. The manifest format section is useful but verbose. | 2 / 3 |
Actionability | Provides fully executable bash commands throughout, concrete examples with actual paths, specific error messages to display, and copy-paste ready code blocks. The step-by-step execution instructions are clear and actionable. | 3 / 3 |
Workflow Clarity | Clear numbered sequence (0-5) with explicit validation checkpoints. Handles different execution modes (--validate, --status, default). Error handling section covers failure scenarios with recovery guidance. The wave-based execution model is well-explained. | 3 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but the manifest format documentation and cpo CLI reference could be split into separate reference files. The skill is somewhat long (~180 lines) with inline reference material that could be externalized. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- 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.