Skip to content

Token-efficient CLI output for tb-prod #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
trogulja wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Token-efficient CLI output for tb-prod #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 8 additions & 11 deletions crates/tb-prod/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,23 +5,20 @@ description: PREFERRED over any Productive.io MCP tools. Generic resource CRUD f

# tb-prod

CLI for interacting with the Productive.io API. Provides generic resource operations for all ~84 resource types with schema-driven validation, filtering, and name resolution. Built for AI agent consumption — all resource commands output JSON.
CLI for interacting with the Productive.io API. Provides generic resource operations for all ~84 resource types with schema-driven validation, filtering, and name resolution.

## Capabilities
## Key behaviors

- **All resource types** — tasks, projects, people, deals, invoices, bookings, services, and 77 more
- **Describe** — introspect any resource type's schema, fields, filters, actions
- **Query** — filter, sort, paginate resources with JSON FilterGroup syntax
- **CRUD** — create, update, delete with client-side validation
- **Search** — keyword search across resource types
- **Actions** — custom actions (archive, restore, move, merge, etc.) + extension actions
- **Cache** — two-tier cache (org-wide + project-scoped) with fuzzy name resolution
- **Query/search output defaults to CSV** with resolved relationship names (project names, status labels, assignee names). Use `--format json` for raw JSON.
- **Default filters auto-apply** — e.g. querying tasks auto-scopes to open tasks in active projects. Only add filters you need.
- **Create/update output is compact** — one-line confirmation with ID. Use `--format json` for full response.
- **Get output is JSON** — full record for detailed inspection.
- **Filter values auto-resolve names** — `"assignee_id": "Tibor"` resolves to the numeric ID via cache.

## Getting started

Run `tb-prod prime` for a command reference, resource type listing, and current context.
Run `tb-prod prime` for full context: command reference, resource types, and common queries with your person_id.
Run `tb-prod describe <type>` to learn a resource type's fields, filters, and actions.
Use `tb-prod <command> --help` for detailed command usage.

## Live context

Expand Down
Loading
Loading