task-management
Skill150 starsChanged 9 days agoMITView on GitHub
Query and update recorded planning and research portfolio state across tasks, topics, papers, outputs, submissions, venues, people, institutions, and deadlines. Use when asking what is already recorded, including institution- or venue-associated topics, or when doing daily planning and weekly review. For venue suitability recommendations, inspect recorded state first and then use the venue-recommendation workflow.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- ishenli/investment-agenttheir own version, first seen Nov 8, 2026
- mondaycom/monday-claude-cowork-plugintheir own version, first seen Oct 28, 2026
- shahrukh-hack/vibe-skillstheir own version, first seen Oct 20, 2026
- mondaycom/skillstheir own version, first seen Oct 19, 2026
- shahrukh-hack/vibe-agencytheir own version, first seen Oct 13, 2026
- anthropics/knowledge-work-pluginstheir own version, first seen Oct 13, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- anthropics/knowledge-work-plugins★ 35ksame name
- MeisnerDan/mission-control★ 955same name
- joelhooks/joelclaw★ 65same name
- ishenli/investment-agent★ 10same name
- mgonzalezbaile/personal-assistant★ 8same name
- mondaycom/skills★ 5same name
- jwilger/agent-skills★ 4same name
- mondaycom/monday-claude-cowork-plugin★ 2same name
- shristi2211/Claude_Skills★ 1same name
- edu6565/claude-skills★ 0same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository89 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- beamer-deckSkill
- bib-coverageSkill
- bib-filterSkill
- bib-parseSkill
- brief-compliance-checkSkill
- camera-readySkill
- causal-designSkill
- checkpointSkill
- code-archaeologySkill
- compile-knowledgeSkill
- computational-experimentsSkill
- cross-language-checkSkill
- data-analysisSkill
- devils-advocateSkill
- docs-consistencySkill
- docxSkill
- experiment-designSkill
- grill-meSkill
- handoffSkill
- ideasSkill
- init-project-courseSkill
- init-project-lightSkill
- init-project-orchestrationSkill
- init-projectSkill
- insights-deckSkill
- interview-meSkill
- knowledge-lintSkill
- latex-diffSkill
- latex-health-checkSkill
- latex-polishSkill
- latex-postersSkill
- latex-scaffoldSkill
- latexSkill
- latex-templateSkill
- lean-checkSkill
- math-proofSkill
- mcp-builderSkill
- method-auditSkill
- multi-perspectiveSkill
- numerical-checkSkill
- pdfSkill
- pipeline-manifestSkill
- playwright-cliSkill
- postmortemSkill
- pre-commit-auditSkill
- pre-submission-reportSkill
- project-deckSkill
- project-safetySkill
- proof-readabilitySkill
- proofreadSkill
- python-envSkill
- quarto-deckSkill
- reorgSkill
- replication-auditSkill
- replication-packageSkill
- retarget-journalSkill
- review-clusterSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Before any vault-dependent workflow, probe the portable CLI once:
- Distinctive: line 27
Ask questions: before dumping lists (the user prefers this)
- Distinctive: line 28
Update context: after sessions
- Distinctive: line 48
When the user asks to plan their day:
- Distinctive: line 64
When the user asks to extract actions from a meeting:
- Distinctive: line 81
When the user asks for weekly review:
- Distinctive: line 97
When creating tasks in vault:
- Distinctive: line 122
Treat “do I have,” “which of my,” and “what is recorded” as stored-state queries, not venue recommendations.
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
the user's Task Management System
Portable vault pre-check
Before any vault-dependent workflow, probe the portable CLI once:
taskflow-cli list-topics --limit 1 --jsontaskflow-cli is the default route in both clients. A Taskflow MCP registration is an optional Claude adapter; its absence never means that the vault is unavailable. If the CLI probe fails, report the failure and follow shared/mcp-degradation.md.
For the boundary between stored portfolio facts, venue recommendations, venue policy, and interface audits, follow shared/research-query-routing.md.
System Overview
This is a hybrid vault + local context library system. Before taking action:
- Read context files in
.context/to understand current state - Query vault for dynamic task data
- Ask questions before dumping lists (the user prefers this)
- Update context after sessions
Key Locations
Context Library (.context/)
profile.md— Who the user is, roles, research areascurrent-focus.md— What they're working on NOW (update this!)projects/_index.md— All active projectsworkflows/— How to help with specific taskspreferences/— Priority definitions, naming conventionspeople/— Supervisors and collaborators
Vaults
- Tasks Tracker: Research Vault tasks database at
~/vault - Research Pipeline: Research Vault pipeline database at
~/vault
Workflows
Daily Planning
When the user asks to plan their day:
- Read
.context/current-focus.mdand.context/workflows/daily-review.md - Query vault for:
- Overdue tasks (Due date < today, Status != Done)
- Due today (Due date = today)
- High priority items
- Ask orientation questions:
- "How's your energy today?"
- "Any fixed commitments?"
- "What were you working on yesterday?"
- Help prioritise based on answers
- Update
current-focus.mdat end of session
Meeting Action Extraction
When the user asks to extract actions from a meeting:
- Read
.context/workflows/meeting-actions.md - Find the meeting transcript in vault (pages starting with @Date)
- Extract action items looking for:
- "I'll...", "I need to...", "I should..."
- "Can you...", "Please..."
- "We agreed to...", "Next step is..."
- Create tasks in vault with full context:
- Task name (action verb + object)
- Project (infer from context)
- Source: "Meeting"
- Due date (if mentioned)
- Description (meeting context)
Weekly Review
When the user asks for weekly review:
- Read
.context/workflows/weekly-review.md - Query vault for:
- Completed tasks this week
- Overdue tasks
- Upcoming deadlines
- Guide through reflection:
- What got done?
- What didn't happen?
- What emerged?
- Help plan next week's Big 3
- Update
current-focus.mdandprojects/_index.md
Task Creation
When creating tasks in vault:
Required fields:
- Task name (action verb + specific object)
- Status: "Not started"
Recommended fields:
- Project: Match to existing project
- Source: Meeting, Email, Supervisor request, Self-initiated, etc.
- Priority: High/Medium/Low (see
.context/preferences/priorities.md) - Due date: If known
- Task type: 📝 Writing, 📚 Reading, 🔬 Research, 📅 Meeting, 📋 Admin, 📧 Communication
Research Pipeline
For paper-related queries:
- Query Research Pipeline database for paper status
- Stages: Idea → Literature Review → Drafting → Submitted → R&R → Published
- Link tasks to papers via Project property
Research portfolio lookup
For questions such as “Do I have any topics associated with institution X that record venue Y?”:
- Treat “do I have,” “which of my,” and “what is recorded” as stored-state queries, not venue recommendations.
- Query the complete relevant inventories with
--jsonand a sufficient--limit:taskflow-cli list-topicsfor topic status, theme, and institution;taskflow-cli list-papersfor output venue and output status;taskflow-cli list-submissionsfor active and historical venue events;taskflow-cli list-venuesfor the canonical venue identity;taskflow-cli list-peoplewhen collaborator or supervisor metadata defines the requested association.
- Filter on structured metadata such as
institution, not words appearing in titles. - Join topics to outputs by topic slug and submissions by their paper/topic wikilink. Resolve venue aliases through the venue inventory.
- Report three categories separately:
- explicit potential venue — recorded as an Idea/planned output;
- active or previous output — a concrete Drafting/Submitted/Accepted/Rejected/Published-style output or submission event;
- inferred suitability — plausible from the topic, but not recorded in the vault.
- Invoke the installed venue-recommendation workflow only when the user asks for suitability, recommendations, or acceptance assessment. Never present recommendation inference as stored portfolio state.
the user's Preferences
- Questions over lists — Don't dump task lists, ask what to focus on
- Full context for actions — Include who, what, why, when in task descriptions
- Flexible/reactive style — They work on what feels right, help them navigate
- Daily review preferred — Short check-ins work better than big weekly sessions
- multiple active projects — Help manage cognitive load, don't add more
Important Context
- PhD Year 1 at [University]
- Teaching
- 4 supervisors across institutions
- Research: [your research areas]
- Current papers: journal revision, [Project] theory, [Project]
After Every Session
Update .context/current-focus.md with:
- What was worked on
- Where things were left off
- What's next
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.

