prose
OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
72
62%
Does it follow best practices?
Impact
92%
2.09xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./extensions/open-prose/skills/prose/SKILL.mdQuality
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 is too vague about what the skill actually does — 'orchestrates multi-agent workflows' is abstract and uninformative. While it provides some trigger terms specific to OpenProse, it fails to describe concrete capabilities or actions. The description reads more like a label than a useful guide for skill selection.
Suggestions
Replace 'orchestrates multi-agent workflows' with specific concrete actions the skill performs (e.g., 'parses .prose files, executes prose pipelines, generates and edits documents using multi-agent coordination').
Add natural language trigger terms that users might actually say, such as 'writing workflows', 'prose generation', 'document pipelines', or whatever the actual use cases are.
Expand the 'what it does' section significantly — currently the description gives almost no information about the skill's actual capabilities or outputs.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'orchestrates multi-agent workflows' which is vague and abstract. It does not list any concrete actions like 'generates documents', 'edits text', or 'formats prose'. 'Skill pack' is also non-descriptive. | 1 / 3 |
Completeness | It partially answers 'when' with 'Activate on any prose command, .prose files, or OpenProse mentions' but the 'what' is extremely weak — 'orchestrates multi-agent workflows' tells almost nothing about what the skill actually does. The 'when' clause exists but the 'what' is essentially missing. | 2 / 3 |
Trigger Term Quality | It includes some trigger terms like 'prose command', '.prose files', and 'OpenProse mentions', but these are fairly niche/technical. It lacks natural language terms a user might say (e.g., 'writing', 'editing', 'text generation') and relies on product-specific jargon. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'OpenProse', '.prose files', and 'prose command' provides some distinctiveness tied to a specific tool/format, but 'multi-agent workflows' is generic enough to overlap with other orchestration or workflow 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 orchestration skill that effectively serves as a routing hub for a complex multi-file system. Its strengths are excellent progressive disclosure with clear load-on-demand signals, highly actionable guidance with concrete commands and resolution rules, and well-sequenced workflows with validation steps. Its main weakness is moderate redundancy in file location tables and some unnecessary philosophical framing about LLM simulation that doesn't add operational value.
Suggestions
Consolidate the 'File Locations' and 'Core Documentation' tables into a single reference table to eliminate redundancy and save ~20 lines.
Remove or drastically shorten the opening paragraph about LLMs being simulators—this philosophical framing doesn't help Claude execute the skill and wastes tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~250 lines) with some redundancy—file locations are listed in multiple tables (File Locations, Core Documentation) with overlapping information. The philosophical preamble about LLMs being simulators and 'simulation with sufficient fidelity is implementation' is unnecessary context for Claude. However, most content is reference-style tables and concrete instructions, which is reasonably efficient. | 2 / 3 |
Actionability | The skill provides concrete command routing tables, specific file paths, executable bash commands for PostgreSQL setup, exact migration steps with before/after examples, and clear resolution rules for remote programs. Commands and code snippets are copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints. The PostgreSQL setup has a 4-step flow with connectivity verification before proceeding. Migration has numbered steps with clear before/after states and output formatting. The execution workflow has a clear 5-step sequence. Remote program resolution has explicit rules with a decision table. | 3 / 3 |
Progressive Disclosure | The skill is an excellent routing document—it clearly identifies when to load each co-located file (prose.md, compiler.md, help.md, state backends, guidance files) with specific trigger conditions. References are one level deep and well-signaled with tables showing file, location, and purpose. The 'When to Load' column in the Core Documentation table is particularly well done. | 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 | |
- Repository
- deepgram/dglabs-deepclaw
- Commit
ec8d4f8
- 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.