agentleFS
DevinoSolutionsDevinoSolutions/claude-plugins/skills/reviewing-workload/SKILL.md

reviewing-workload

Skill0 starsChanged 9 days agoMITView on GitHub

Summarizes what is on the user's plate in GetItDone: tasks due, in progress, in review, and blocked, per workspace or project. Use when the user asks 'what's on my plate this week', 'what should I work on next', 'what's due', 'what's blocked right now', 'give me a status update on this project', 'show my to-do list', or wants a workload or project status overview. Read-only.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 0 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every tool in this skill comes from the getitdone MCP server, the GetItDone connector, and is written here as getitdone:<tool>.

    line 13
  2. Very specific:

    Tools listed by name: call them directly, for example getitdone:list_tasks.

    line 15
  3. Very specific:

    If the tool list shows only getitdone:search_tools and getitdone:execute_typescript, the server is in Code Mode: call each operation below …

    line 22
  4. Very specific:

    Call getitdone:list_workspaces.

    line 31
  5. Very specific:

    If the user named a project, call getitdone:list_projects and use its id as the getitdone:list_tasks filter.

    line 32
  6. Very specific:

    Call getitdone:list_tasks.

    line 33
  7. Very specific:

    Do not change anything from this skill: never call getitdone:create_task, getitdone:update_task, getitdone:complete_task_occurrence, …

    line 44
  8. Very specific:

    If a project the user named is not in getitdone:list_projects, say it does not exist.

    line 46
  9. Very specific:

    If a workspace id the user gave is not one of theirs, say so and offer getitdone:list_workspaces.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Generated from plugins/getitdone/skills/reviewing-workload/SKILL.md by scripts/sync-skills.mjs. Edit the plugin copy, then run the script. -->

GetItDone workload review

Turn the workspace's task list into a short, prioritized view of what needs attention. Read only.

Connecting and calling the tools

Every tool in this skill comes from the getitdone MCP server, the GetItDone connector, and is written here as getitdone:<tool>.

  • Tools listed by name: call them directly, for example getitdone:list_tasks.
  • Only getitdone:search_tools and getitdone:execute_typescript listed (Code Mode, the default): call getitdone:search_tools first, then call each tool inside getitdone:execute_typescript as external_<tool> (for example external_list_tasks); the program must return its result. Scopes, confirmations and gates are identical on both surfaces.
  • "Tool not found": switch to the Code Mode route instead of retrying the direct call. If getitdone:search_tools does not return the tool either, its OAuth scope was not granted; the user reconnects GetItDone and approves that scope.
  • No getitdone tools at all: GetItDone is not connected yet. Follow the setup-getitdone skill.

Tools you will use

If the tool list shows only getitdone:search_tools and getitdone:execute_typescript, the server is in Code Mode: call each operation below inside getitdone:execute_typescript as external_<name>, and use one program to run several independent reads together.

  • getitdone:list_workspaces: the workspaces the account belongs to, with their ids. Pass an id as workspaceId to target one.
  • getitdone:list_projects: the projects in the workspace with their ids.
  • getitdone:list_tasks: the latest version of each task with name, short id, status (TODO, IN_PROGRESS, IN_REVIEW, COMPLETED, BLOCKED), priority, due date, projects, whether it is blocked, and how many tasks it blocks. Filters by status, priority, and project.
  • getitdone:get_task_details: notes, attachments, and the dependency chain for one task, when a summary line is not enough.

Workflow

  1. Call getitdone:list_workspaces. If the user belongs to more than one and did not name one, ask which, or use the one they usually work in and say which you used.
  2. If the user named a project, call getitdone:list_projects and use its id as the getitdone:list_tasks filter.
  3. Call getitdone:list_tasks. Leave out COMPLETED tasks unless the user asks for them.
  4. Present, in this order:
    • Blocked tasks, with how many tasks each one blocks.
    • Overdue tasks and tasks due in the window the user asked about (default: the next 7 days), sorted by due date then priority.
    • In progress and in review.
    • A count of the remaining TODO tasks.
  5. For the top blocked task, call getitdone:get_task_details and name what blocks it.
  6. Close with at most three suggested next actions drawn from the list, such as the blocker that unblocks the most tasks.

Rules

  • Do not change anything from this skill: never call getitdone:create_task, getitdone:update_task, getitdone:complete_task_occurrence, getitdone:link_task_dependency, or getitdone:archive_task. Hand off to capturing-tasks for changes.
  • Refer to tasks by short id and name so the user can find them in the app.
  • If a project the user named is not in getitdone:list_projects, say it does not exist. Do not guess another one.
  • If a workspace id the user gave is not one of theirs, say so and offer getitdone:list_workspaces.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.