investigating-tasks
Skill0 starsChanged 9 days agoMITView on GitHub
Explains a single GetItDone task in full: its content, status, dependencies, attachments, and what an attached video or screen recording shows. Use when the user asks to 'open T-123', 'why can't this task start', 'what is this task waiting on', 'what's in this task', 'what does the screen recording on this task show', or wants a deep dive on one task. Read-only.
In this repository66 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adding-uptime-monitorsSkill
- analyzing-page-performanceSkill
- booking-meetingsSkill
- building-onboarding-workflowsSkill
- building-study-guidesSkill
- capturing-tasksSkill
- capturing-web-pagesSkill
- chasing-unpaid-invoicesSkill
- checking-domain-connectionsSkill
- checking-email-deliverabilitySkill
- checking-notification-deliverySkill
- checking-uptime-statusSkill
- cleaning-up-bookkeepingSkill
- connecting-customer-domainsSkill
- discussing-buildsSkill
- drafting-invoicesSkill
- drafting-social-postsSkill
- editing-demosSkill
- editing-page-draftsSkill
- extracting-document-textSkill
- finding-meeting-timesSkill
- handling-flaky-changesSkill
- making-demo-videosSkill
- managing-bookingsSkill
- managing-content-calendarSkill
- managing-demosSkill
- managing-voice-librarySkill
- planning-revisionSkill
- preflighting-domainsSkill
- publishing-pagesSkill
- reading-financial-reportsSkill
- reading-text-aloudSkill
- reading-web-pagesSkill
- reporting-snapvisor-usageSkill
- researching-course-materialSkill
- researching-summary-librarySkill
- responding-to-incidentsSkill
- reviewing-email-performanceSkill
- reviewing-notification-workflowsSkill
- reviewing-social-performanceSkill
- reviewing-visual-buildsSkill
- reviewing-workloadSkill
- searching-getitdone-api-docsSkill
- sending-email-campaignsSkill
- sending-notificationsSkill
- setup-bioflowSkill
- setup-calySkill
- setup-demofySkill
- setup-dodomainSkill
- setup-getitdoneSkill
- setup-notiflySkill
- setup-postifySkill
- setup-sendlySkill
- setup-shortySkill
- setup-snapvisorSkill
- setup-superbooksSkill
- setup-unotesSkill
- setup-upapiSkill
- setup-uptimelySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 2 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Read one task end to end, including its notes, attachments, dependencies, and any attached video, and explain it in plain words.
- Very specific: line 13
Every tool in this skill comes from the getitdone MCP server, the GetItDone connector, and is written here as getitdone:<tool>.
- Very specific: line 15
Tools listed by name: call them directly, for example getitdone:list_tasks.
- Very specific: line 22
If the tool list shows only getitdone:search_tools and getitdone:execute_typescript, the server is in Code Mode: call each operation below …
- Very specific: line 30
If the user gave a name instead of a short id, call getitdone:list_tasks and match it.
- Distinctive: line 33
If the task is blocked, name each blocking task with its status.
- Very specific: line 34
If the task has a video, or the user asks what a recording shows, call getitdone:get_task_video_context and describe what the frames show, …
- Very specific: line 42
Do not change the task from this skill: never call getitdone:create_task, getitdone:update_task, getitdone:complete_task_occurrence, …
≈ “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.
Files
<!-- Generated from plugins/getitdone/skills/investigating-tasks/SKILL.md by scripts/sync-skills.mjs. Edit the plugin copy, then run the script. -->GetItDone task deep dive
Read one task end to end, including its notes, attachments, dependencies, and any attached video, and explain it in plain words. 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_toolsandgetitdone:execute_typescriptlisted (Code Mode, the default): callgetitdone:search_toolsfirst, then call each tool insidegetitdone:execute_typescriptasexternal_<tool>(for exampleexternal_list_tasks); the program mustreturnits 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_toolsdoes not return the tool either, its OAuth scope was not granted; the user reconnects GetItDone and approves that scope. - No
getitdonetools at all: GetItDone is not connected yet. Follow thesetup-getitdoneskill.
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>.
getitdone:list_tasks: find the task's short id when the user gave only a name.getitdone:get_task_details: the task's rich-text notes, every attachment with a short-lived URL, and its dependency chain (what blocks it and what it blocks). Takes the short id (123 for T-123) or task version id.getitdone:get_task_video_context: evenly spaced still frames from a video uploaded to the task's notes or attachments, with a text summary, plus any YouTube or Vimeo links found in the notes.
Workflow
- If the user gave a name instead of a short id, call
getitdone:list_tasksand match it. Ask if more than one task matches. - Call
getitdone:get_task_details. - Summarize: status, priority, due date, a short summary of the notes, the attachments by file name, and the dependency chain.
- If the task is blocked, name each blocking task with its status. Offer to open the blocker the same way.
- If the task has a video, or the user asks what a recording shows, call
getitdone:get_task_video_contextand describe what the frames show, in order.
Rules
getitdone:get_task_video_contextextracts still frames. It does not transcribe audio and does not watch linked YouTube or Vimeo videos. Say that when you describe a video, and list any linked videos as links only.- In Code Mode only the tool's JSON summary comes back, not the frame images. Describe what the summary says and tell the user the frames themselves need a connection on the full tool surface.
- "No videos found on this task." is a normal result. Report it plainly.
- Attachment URLs expire. Do not store them or present them as permanent links; fetch the task again when the user needs a fresh one.
- Do not change the task from this skill: never call
getitdone:create_task,getitdone:update_task,getitdone:complete_task_occurrence,getitdone:link_task_dependency, orgetitdone:archive_task. Hand off tocapturing-tasksfor changes.
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
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.

