better-proposals-automation
by ComposioHQbetter-proposals-automation helps Claude use Rube MCP to discover Better Proposals tools, verify connections, and run schema-driven proposal workflows safely.
This skill scores 69/100, which makes it acceptable for listing but with caveats. Directory users can understand when to use it and how to connect Rube MCP for Better Proposals automation, but should expect a lightweight, discovery-driven skill rather than a richly documented set of concrete proposal workflows.
- Frontmatter clearly identifies the trigger domain: automating Better Proposals through Rube MCP, with a concise description and required MCP dependency.
- Prerequisites and setup steps are explicit, including adding the Rube MCP endpoint, checking RUBE_SEARCH_TOOLS, managing the better_proposals connection, and confirming ACTIVE status.
- The skill gives agents an important execution rule: always discover current tools and schemas with RUBE_SEARCH_TOOLS before attempting workflows.
- No support files, examples, or reference assets are provided beyond SKILL.md, so users get limited evidence of tested end-to-end workflows.
- The workflow is mostly mediated through RUBE_SEARCH_TOOLS and current MCP schemas, which improves freshness but leaves task-specific Better Proposals operations under-specified in the repository evidence.
Overview of better-proposals-automation skill
What better-proposals-automation does
better-proposals-automation is a Claude skill for running Better Proposals workflows through Composio’s Rube MCP server. It is not a proposal-writing template by itself; it helps an agent discover and call current Better Proposals tools for actions such as finding available operations, checking connection state, and executing supported account workflows with the right schema.
Best fit for Proposal Writing operations
This skill is most useful for teams that already use Better Proposals and want AI-assisted automation around the proposal lifecycle. Good fits include sales ops, agency owners, proposal coordinators, and RevOps teams who need an assistant to work with live Better Proposals tooling rather than only draft text in a chat window.
Key differentiator: tool discovery first
The main value of the better-proposals-automation skill is its “search tools first” pattern. The upstream skill explicitly requires RUBE_SEARCH_TOOLS before execution so the agent gets current tool names, input schemas, execution plans, and pitfalls. That matters because MCP tool schemas can change, and guessing arguments is the fastest way to produce failed automations.
Adoption requirements and limits
You need Rube MCP connected and an active Better Proposals connection through RUBE_MANAGE_CONNECTIONS using the better_proposals toolkit. The repository currently provides a single SKILL.md and no helper scripts, references, or examples directory, so users should expect a compact integration guide rather than a full proposal automation playbook.
How to Use better-proposals-automation skill
better-proposals-automation install context
Install the skill from the Composio skills repository in the environment where your Claude-compatible skill runner can load GitHub skills. A typical directory install command is:
npx skills add ComposioHQ/awesome-claude-skills --skill better-proposals-automation
Then configure Rube MCP by adding https://rube.app/mcp as an MCP server in your client. The skill depends on the rube MCP server and expects RUBE_SEARCH_TOOLS and RUBE_MANAGE_CONNECTIONS to be available.
First-run connection workflow
Before asking the agent to change or retrieve Better Proposals data, verify access:
- Ask the agent to confirm
RUBE_SEARCH_TOOLSresponds. - Call
RUBE_MANAGE_CONNECTIONSwith toolkitbetter_proposals. - If the returned status is not
ACTIVE, complete the authentication link. - Re-check the connection status before running the real workflow.
- Use
RUBE_SEARCH_TOOLSfor the exact Better Proposals task you want to perform.
This sequence is important because the skill is schema-driven. A prompt that skips discovery may fail even if the connection is valid.
Turning a rough request into a usable prompt
Weak prompt:
“Help with Better Proposals.”
Stronger prompt:
“Use the better-proposals-automation skill. First search Rube tools for Better Proposals operations related to proposal retrieval and client follow-up. Confirm my Better Proposals connection is active. Then show the available tool options, required fields, and a safe execution plan before making changes.”
Even better, include the business goal, target record, desired output, and safety boundary:
“Use better-proposals-automation for Proposal Writing operations. I need to locate proposals sent to Acme Corp, identify their current status, and draft a follow-up email. Do not send or modify anything until I approve the tool plan.”
Files to read before use
Start with composio-skills/better-proposals-automation/SKILL.md. It contains the prerequisites, setup path, tool discovery pattern, and core workflow expectation. There are no bundled scripts/, resources/, references/, or README.md files in this skill path, so the practical source of truth is the skill file plus the live schemas returned by Rube.
better-proposals-automation skill FAQ
Is better-proposals-automation a proposal writer?
Not exactly. The better-proposals-automation skill is for automating Better Proposals operations through Rube MCP. It can support a Proposal Writing workflow by helping an agent interact with proposal data and available Better Proposals tools, but you still need to provide positioning, offer details, pricing logic, client context, and approval rules for high-quality proposal content.
How is this better than an ordinary prompt?
An ordinary prompt can draft advice or copy, but it cannot reliably know the current Better Proposals tool schemas. This skill instructs the agent to use RUBE_SEARCH_TOOLS first, then execute against discovered Better Proposals capabilities. That reduces guesswork when tool names, required fields, or recommended execution steps are not known in advance.
Is it beginner-friendly?
It is beginner-friendly if you are comfortable connecting an MCP server and authenticating Better Proposals through Composio/Rube. It is less suitable for users expecting a no-setup writing assistant. The setup is short, but the skill assumes you understand that the agent must discover tools, verify connection status, and avoid executing changes without confirmation.
When should I not install it?
Skip this skill if you do not use Better Proposals, cannot enable Rube MCP, or only need generic proposal copywriting. Also avoid it for high-risk bulk actions unless you are prepared to review tool schemas, preview execution plans, and approve each operation. The repository is intentionally minimal, so teams needing audited workflows may need to add their own guardrails.
How to Improve better-proposals-automation skill
Improve inputs before invoking better-proposals-automation
The output quality depends heavily on the task description used in RUBE_SEARCH_TOOLS. Replace vague use cases with operationally specific ones. For example, “Better Proposals operations” is less useful than “find proposals for a named client, check status, and prepare a follow-up without sending.” Specific use cases help Rube return more relevant tool slugs, fields, and pitfalls.
Add workflow guardrails for safer execution
For production use, wrap the better-proposals-automation skill with rules such as: always confirm connection status, always show the discovered tool schema, never create or modify proposals without explicit approval, and summarize the expected side effects before execution. These guardrails are especially important because the skill has no separate rules folder or scripted safety layer.
Common failure modes to watch
The most common failure is skipping tool discovery and inventing arguments. Another is authenticating the wrong Better Proposals account or proceeding when the connection is not ACTIVE. A third is giving the agent a content-writing goal without the operational details needed to use Better Proposals tools, such as client name, proposal identifier, status needed, or whether modifications are allowed.
Iterate after the first output
After the first tool search, ask the agent to explain which tools were found, which fields are required, and what data is missing. Then refine the request before execution. A strong iteration prompt is:
“Based on the discovered Better Proposals tools, list the minimum fields you need, identify any risky actions, and propose a read-only first step.”
This keeps the better-proposals-automation guide practical, safer, and more useful than a one-shot automation request.