Agent Native

stage-playbook

This skill guides agents to advance deals through a six-stage pipeline based on momentum and risk signals.

by open-mercatoCommunityNot reviewed

Community author

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
License
MIT (permissive)
Pin
5e58462pinned Oct 9, 2026
Context cost
about 240 tokenswhen the skill loads
GitHub stars
1,831on open-mercato/open-mercato
Scripts
None found

What it does

“How to choose the next pipeline stage for a deal from its momentum and risk signals.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill guides agents to advance deals through a six-stage pipeline based on momentum and risk signals. It applies decision rules around forward signals, risk factors, and conservative staging to recommend the next appropriate stage and justifies the choice with the triggering signal.

When to use it

  • Updating deal stage in a CRM based on customer interaction data
  • Reviewing pipeline deals to assess momentum and risk factors
  • Automating stage advancement decisions with clear rationale requirements
  • Managing sales workflows with defined progression criteria

When not to

  • Predicting deal close probability or revenue forecasting
  • Handling complex multi-threaded deals with competing stakeholders
  • Deals requiring custom stage definitions beyond the standard six

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add open-mercato/open-mercato --skill stage-playbook

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install open-mercato/open-mercato stage-playbook@5e58462586a2c8c17c311cc4b8729f04b345ecc3

Installs the commit we checked (5e58462).

Copy by hand

Download the folder at 5e58462 and put it in .claude/skills/stage-playbook for Claude Code and in .agents/skills/stage-playbook for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 5e58462

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "stage-playbook" by open-mercato.

Source, pinned to commit 5e58462586a2c8c17c311cc4b8729f04b345ecc3:
https://github.com/open-mercato/open-mercato/tree/5e58462586a2c8c17c311cc4b8729f04b345ecc3/docker/opencode/skills/stage-playbook

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/stage-playbook/ for Claude Code and .agents/skills/stage-playbook/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/open-mercato/stage-playbook

SKILL.md at the pin

---
name: stage-playbook
description: "How to choose the next pipeline stage for a deal from its momentum and risk signals."
---
Use this playbook to pick the single most appropriate next stage for a deal.

Pipeline stages, in order:

1. `lead` — initial interest, no qualification yet.
2. `qualified` — budget, authority, need, and timeline (BANT) confirmed.
3. `proposal` — a quote or proposal has been sent.
4. `negotiation` — terms are actively being discussed.
5. `won` — the deal is closed and signed.
6. `lost` — the deal is dead; record the reason.

Decision rules:

- Advance one stage at a time unless a strong signal justifies a jump.
- Strong forward signals: a signed document, a scheduled close date, an
  explicit verbal commitment, or procurement engagement.
- Risk signals that hold a deal back: no reply for two or more weeks, the
  champion leaving, or repeated reschedules.
- When momentum is unclear, prefer the conservative stage and lower your
  confidence rather than guessing high.

Always justify the chosen stage in the rationale with the specific signal you
relied on.

From open-mercato/open-mercato at 5e58462, shown as plain text under its license: MIT (permissive). The license text is in LICENSE.

View SKILL.md on GitHub at 5e58462

Files

1 file, 1.1 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 5e58462
  • accelo-automation

    This skill enables agents to automate Accelo project management tasks by discovering and executing operations through Composio's Accelo toolkit via Rube MCP.

    by ComposioOfficial publisher

    Agents not labelled yet · about 690 tokens · pinned 6 days ago

  • acculynx-automation

    This skill automates Acculynx operations by discovering and executing available tools through the Rube MCP server.

    by ComposioOfficial publisher

    Agents not labelled yet · about 690 tokens · pinned 6 days ago

  • active-campaign-automation

    This skill automates ActiveCampaign tasks by discovering and executing tools through Rube MCP and Composio's ActiveCampaign toolkit.

    by ComposioOfficial publisher

    Agents not labelled yet · about 710 tokens · pinned 6 days ago

  • adrapid-automation

    This skill enables agents to automate Adrapid tasks through Composio's toolkit via Rube MCP.

    by ComposioOfficial publisher

    Agents not labelled yet · about 690 tokens · pinned 6 days ago

  • aeroleads-automation

    This skill automates Aeroleads tasks by connecting to the Aeroleads toolkit via Composio's Rube MCP server.

    by ComposioOfficial publisher

    Agents not labelled yet · about 700 tokens · pinned 6 days ago

  • affinity-automation

    This skill automates Affinity CRM operations by executing tools through Rube MCP and Composio's Affinity toolkit.

    by ComposioOfficial publisher

    Agents not labelled yet · about 690 tokens · pinned 6 days ago

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use