CtrlK
BlogDocsLog inGet started
Tessl Logo

basecamp-automation

Automate Basecamp project management, to-dos, messages, people, and to-do list organization via Rube MCP (Composio). Always search tools first for current schemas.

Install with Tessl CLI

npx tessl i github:Lingjie-chen/MT5 --skill basecamp-automation
What are skills?

63

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

97%

12%

Sprint Planning: Basecamp Project Setup

To-do list setup with color-coded groups

Criteria
Without context
With context

RUBE_SEARCH_TOOLS first

0%

100%

Check existing lists

100%

100%

Dock array for IDs

25%

100%

Integer IDs only

100%

100%

HTML descriptions

100%

100%

Valid group colors

100%

100%

YYYY-MM-DD date format

100%

100%

app_url from response

100%

70%

Correct to-do creation tool

100%

100%

Groups as sub-sections

100%

100%

No URL reconstruction

100%

100%

Correct tool sequence

83%

100%

Without context: $0.4559 · 2m 4s · 25 turns · 100 in / 8,025 out tokens

With context: $0.5947 · 2m 48s · 16 turns · 273 in / 10,517 out tokens

92%

22%

Fix the Weekly Status Update Script

Message board posting and content formatting

Criteria
Without context
With context

status active not draft

100%

100%

HTML content not Markdown

100%

100%

Integer bucket_id

100%

100%

app_url from response

0%

100%

No manual URL construction

0%

100%

Full body on update

100%

100%

Same project IDs

75%

75%

review_notes identifies issues

100%

100%

RUBE_SEARCH_TOOLS noted

0%

0%

CREATE_MESSAGE preferred

100%

100%

Without context: $0.4540 · 2m 34s · 21 turns · 89 in / 8,345 out tokens

With context: $0.4665 · 1m 46s · 21 turns · 279 in / 5,857 out tokens

95%

19%

Onboard New Contractors to a Basecamp Project

People management and project access

Criteria
Without context
With context

RUBE_SEARCH_TOOLS first

0%

100%

GET_PEOPLE before granting

100%

92%

Integer person IDs in grant

60%

80%

create param structure

100%

100%

Single PUT call for all three

0%

100%

project_id same as bucket_id

100%

100%

Correct access tool

100%

100%

Verification step

100%

100%

BASECAMP_GET_PROJECTS used

100%

100%

No string IDs

50%

75%

Dock or project metadata used

100%

100%

Without context: $0.2885 · 1m 30s · 15 turns · 22 in / 5,429 out tokens

With context: $0.5185 · 2m 11s · 20 turns · 26 in / 6,701 out tokens

Evaluated
Agent
Claude Code

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.