claude

projects

Runs a project from named problem to shipped release. Its problem-statement agent finds recurring problems in bounded internal, meeting, CRM, sales-engagement and support context, or works from a known problem, then writes the case that one is worth fixing only after explicit approval. The skills scope the work, create tasks, communicate changes and record the release. External connectors are read-only and Notion is the only write destination. Needs the setup plugin, which it reads config from and never calls.

0 on GitHubby Sarah Maddenv0.3.0MITupdated 2 months agoproductivity
/

Plugin projects from marketplace gtm-operator in sarahcallmesmadds/gtm-operator. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (6)

  • comms

    Write the update that tells the people affected by a project what changed, as one Project Update memo. Use when the user says "write the project update", "announce this change", "tell people about this", "who needs to know", or whenever a project changes something other people depend on. Not on a sc

  • new

    Create the tasks for a project that scope has already created, and move that project from Scoped to In progress. Also fills in a project someone created by hand. Use when the user says "start the project", "break this into tasks", "create the tasks", "let's build it", or after scope offers this pre-

  • problem-scan

    Find problems that keep coming up and that nobody has written down, from bounded conversation, meeting, CRM, sales-engagement and support context the user selects, and hand the ones worth writing up to problem-statement pre-filled. Use when the user says "what problems keep coming up", "scan for pro

  • problem-statement

    Write the case that something is worth fixing, before anyone proposes a fix, as one Problem Statement memo in the Memos log. Use when the user says "write the problem statement", "write up this problem", "make the case for fixing this", when problem-scan hands one over, or before scoping anything. N

  • scope

    Work out what a project actually is, what it deliberately is not, and whether it should be built at all, then create the project row at Scoped or Canceled. Use when the user says "scope this", "should we build this", "turn this problem into a project", "what would this take", or after a problem stat

  • ship

    Record that a project shipped and close it, as one Release memo and the move from In progress to Done. Use when the user says "we shipped it", "write the release", "close the project", "mark it done", or when work reaches the people who will use it, not when it merges. Lists open tasks and asks befo

Subagents (1)

  • problem-statement-agent

    Finds a recurring problem in bounded company context or works from a problem the user already knows, then builds the evidence-based case that it is worth fixing before anyone proposes a solution. It may search and synthesize inside the scope the user approved, but it writes a Problem Statement memo

MCP servers (10)

  • notion

    connects to: https://mcp.notion.com/mcp

  • granola

    connects to: https://mcp.granola.ai/mcp

  • gong

    connects to: https://mcp.gong.io/mcp

  • slack

    connects to: https://mcp.slack.com/mcp

  • gmail

    connects to: https://gmailmcp.googleapis.com/mcp/v1

  • hubspot

    connects to: https://mcp.hubspot.com/anthropic

  • salesforce

    connects to: https://api.salesforce.com/platform/mcp/v1/platform/sobject-reads

  • outreach

    connects to: https://api.outreach.io/mcp

  • intercom

    connects to: https://mcp.intercom.com/mcp

  • pylon

    connects to: https://mcp.usepylon.com/

View source on GitHub

More from sarahcallmesmadds/gtm-operator

All 7 plugins →

process

claude

The Process library: the living reference of how and why things are done. Finds current answers, audits stale or conflicting artifacts, and sweeps scoped documents, conversations, meetings, CRM activity, billing, and spend evidence for missing process knowledge. Proposes candidates one approval at a time. Needs the setup plugin, which it reads config from and never calls.

5 skills · 1 agent · 12 MCP servers

0

software

claude

The Software directory: what we use, who owns it, what we pay and when that comes round again, and what would break if it went away. Adds and maintains tools, reports renewals by consequence, and backfills from signed agreements, spend, accounting, a named contract folder, the user's own mailbox and bounded Slack context. External systems are read-only, candidates are approved one at a time, and Slack can support Importance only with exact consequence evidence. Needs the setup plugin, which it reads config from and never calls.

5 skills · 8 MCP servers

0

memos

claude

Time-stamped communication, append-only. Writes one memo of any of seven types from free-form notes or explicitly scoped Slack and Gmail context, turns a Granola or Gong meeting source into a record of what it decided, assembles the recurring team update from Projects, Calendar, Memos and Tasks rather than from memory, and finds what was said about something and when, following corrections to the end of the chain. There is no update skill and there never will be: a correction is a new memo. Needs the setup plugin, which it reads config from and never calls.

4 skills · 5 MCP servers

0

Imports lead lists into the CRM config names, HubSpot or Salesforce, one per install: mapped, deduped, matched to companies, on the memberships the org's grid names, verified by reading every write back, and written back to a Notion source. Every write sits behind one confirmation.

2 skills · 5 MCP servers

0

calendar

claude

The GTM calendar: what is happening in market, and when. Shows what else is already aimed at the same people before it writes anything, asks how it went when a row is marked done, and answers what an audience is receiving for a window. Needs the setup plugin, which it reads config from and never calls.

3 skills · 1 MCP server

0

setup

claude

Creates the Notion databases the foundation plugins read and write, wires the relations between them, and writes the foundation's config. Nothing else in the marketplace creates a database, and nothing else writes the foundation's config. install explains the model before it asks anything, asks only the questions that are genuinely the user's to decide, and reads everything it created back out of Notion before calling itself done.

2 skills · 1 MCP server

0

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

AI-powered codebase understanding — analyze, visualize, and explain any project

9 skills · 10 agents · hooks

Egonex-AI/Understand-Anything 92,410

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

Maintain projects?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins7 plugins