prose
OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
72
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.
This description relies heavily on product-specific jargon ('OpenProse VM', 'multi-agent workflows') without explaining what concrete value it provides to users. While it has trigger terms for activation, it fails to communicate what actions the skill performs or what problems it solves.
Suggestions
Replace 'orchestrates multi-agent workflows' with specific concrete actions the skill performs (e.g., 'Creates prose documents, manages writing projects, coordinates collaborative editing')
Add natural language trigger terms that users would actually say (e.g., 'writing', 'document creation', 'text generation') alongside the technical triggers
Expand the 'Use when' guidance to include user intent scenarios (e.g., 'Use when users need to create, edit, or manage prose documents or writing workflows')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'orchestrates multi-agent workflows' without specifying concrete actions. It doesn't explain what the skill actually does beyond abstract terminology. | 1 / 3 |
Completeness | Has a partial 'when' clause ('Activate on any prose command...') but the 'what' is extremely weak - 'orchestrates multi-agent workflows' doesn't explain what the skill actually accomplishes for the user. | 2 / 3 |
Trigger Term Quality | Includes some trigger terms ('prose command', '.prose files', 'OpenProse mentions') but these are technical/product-specific rather than natural user language. Missing common variations of what users might actually say. | 2 / 3 |
Distinctiveness Conflict Risk | The '.prose files' and 'OpenProse' terms provide some distinctiveness, but 'multi-agent workflows' is generic and could overlap with other orchestration or automation skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
85%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 that provides clear command routing, concrete file locations, and actionable guidance for a complex multi-file system. The progressive disclosure is excellent with clear navigation to supporting documents. Minor verbosity in the philosophical framing and some redundant explanations prevent a perfect conciseness score.
Suggestions
Remove or significantly condense the philosophical opening paragraph about LLMs being simulators—Claude doesn't need this context to execute the skill.
The 'Important: Single Skill' section could be reduced to a single line since it's defensive documentation that may not be needed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundant explanations (e.g., explaining that LLMs are simulators, the philosophical framing about 'simulation with sufficient fidelity'). The tables and command routing are well-organized but could be tighter. | 2 / 3 |
Actionability | Provides concrete command mappings, specific file paths, executable bash examples for PostgreSQL setup, clear migration steps with exact file format conversions, and specific example file references. Copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints (e.g., PostgreSQL setup checks connection before proceeding, migration has ordered steps with clear output). The state mode selection flow includes fallback handling. | 3 / 3 |
Progressive Disclosure | Excellent structure with clear overview, well-organized tables pointing to specific files (prose.md, compiler.md, state/*.md, guidance/*.md), and explicit 'When to Load' guidance. References are one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 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.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 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.