prose

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

2.09x

Quality

51%

Does it follow best practices?

Impact

92%

2.09x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./extensions/open-prose/skills/prose/SKILL.md

Quality

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 jargon that doesn't convey concrete capabilities. While it provides product-specific trigger terms (OpenProse, .prose files), it lacks natural user-facing keywords and fails to explain what tasks or outputs the skill produces. The description reads more like a label than a useful selection guide.

Suggestions

Replace 'orchestrates multi-agent workflows' with specific concrete actions the skill performs (e.g., 'generates prose documents, runs writing pipelines, manages collaborative text editing').

Add natural language trigger terms that users would actually say, such as 'writing', 'text generation', 'document creation', or 'prose editing'.

Expand the 'what' portion significantly — describe the actual outputs and capabilities so Claude can distinguish this from other workflow or writing skills.

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 has a partial 'when' clause ('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 or produces. The when is present but the what is nearly absent.	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 actually say (e.g., 'writing', 'editing', 'text generation'). The triggers are product-specific rather than task-oriented.	2 / 3
Distinctiveness Conflict Risk	The mention of 'OpenProse', '.prose files', and 'prose command' provides some distinctiveness tied to a specific tool/ecosystem, but 'multi-agent workflows' is generic enough to overlap with other orchestration or workflow skills. The niche is somewhat defined but not sharply.	2 / 3
	Total	7 / 12 Passed

Implementation

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill excels at actionability and workflow clarity, providing concrete commands, clear routing tables, and well-sequenced multi-step processes with validation checkpoints. However, it suffers significantly from verbosity and redundancy—file locations are listed in multiple overlapping tables, state mode details are repeated, and substantial content (PostgreSQL setup, migration details) is inlined rather than delegated to the referenced sub-files. The skill would benefit greatly from aggressive trimming and trusting its own progressive disclosure structure.

Suggestions

Consolidate the three overlapping file location/documentation tables into a single table, removing redundant entries and descriptions.

Move the detailed PostgreSQL setup instructions (Docker commands, connection checking, error messages) into state/postgres.md and keep only a one-line reference here.

Move the migration details into a separate migration.md file and reference it with a single line in the command routing table.

Remove the philosophical preamble about LLMs being simulators and 'simulation with sufficient fidelity is implementation'—this is unnecessary context that doesn't help Claude execute the skill.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~250+ lines. It contains significant redundancy—file locations are listed in multiple tables, state modes are explained twice (once in 'Core Documentation' and again in 'State Modes'), and there's extensive explanation of concepts Claude could infer (e.g., explaining what simulation means, what a VM is). The PostgreSQL setup section alone is disproportionately long with inline bash examples that could be in the referenced postgres.md file.	1 / 3
Actionability	The skill provides concrete, executable guidance throughout: specific command routing tables, exact file paths, bash commands for PostgreSQL setup, migration steps with before/after examples, resolution rules for remote programs, and specific banner output to display. Commands and their expected behaviors are clearly mapped.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with validation checkpoints. The PostgreSQL setup has a 4-step process with connectivity verification before proceeding. Migration has explicit ordered steps with clear output expectations. The execution workflow (read prose.md → become VM → spawn sessions → narrate state → evaluate) is well-sequenced. Remote program resolution has clear ordered rules.	3 / 3
Progressive Disclosure	The skill does reference external files (prose.md, compiler.md, help.md, state backends, guidance files) with clear 'when to load' guidance, which is good. However, too much content that belongs in those referenced files is inlined here—the full PostgreSQL setup instructions, detailed state mode explanations, and migration details could be in separate files. The file location tables are repeated, and the content that should be a concise routing overview has become a monolithic document.	2 / 3
	Total	9 / 12 Passed

Validation

81%

Warnings & errors only

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: qsimeon/openclaw-engaging
Commit: 4467e04

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.