todoist-triage/SKILL.md
Triage and manage Todoist inbox tasks using a multi-dimensional system (MoSCoW priorities, time estimates, skill × leverage value tags, and context labels). Use when sorting, triaging, prioritizing, or organizing tasks in Todoist, or when the user mentions inbox cleanup, task categorization, or task dimensions.
npx skillsauth add croesnick/agent-skill-todoist-triage todoist-triageInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Triage incoming tasks by assigning four orthogonal dimensions before placing them in the right project. This skill turns a flat inbox into a structured, actionable system.
NEVER delete any Todoist object without explicit user confirmation. Before calling any delete tool:
No exceptions — even if the user said "delete" in a general context.
When triaging a task, apply these dimensions in order:
Assign one priority level:
| Prio | Meaning | Todoist Field |
|------|---------|---------------|
| P1 | Must — has to be done | priority: "p1" |
| P2 | Should — should be done | priority: "p2" |
| P3 | Could — nice to have | priority: "p3" |
| P4 | Would — someday/maybe | priority: "p4" (default) |
Add one time label:
| Label | Effort |
|-------|--------|
| XS | Few minutes ("snack size") |
| S | ~30 min (1 Pomodoro) |
| M | ~1 hour (substantial block) |
| L | Several hours |
| XL | ~1 day (it's a project) |
Add two labels — one for each axis:
| Label | Axis | Meaning |
|-------|------|---------|
| skill-low | Skill | Low specialization, anyone could do it |
| skill-high | Skill | High specialization, requires your expertise |
| leverage-low | Leverage | Affects one case, one person |
| leverage-high | Leverage | Affects many people or whole systems |
The combination tells you what kind of work it is:
| Combination | Character | Examples |
|-------------|-----------|---------|
| skill-low + leverage-low | Manual, direct | Answering emails, data entry |
| skill-low + leverage-high | Systemic, automated — "busywork at scale" | Script helping 20 people, docs saving 50 questions |
| skill-high + leverage-low | Specialized, individual — expertise without scale | Hard bug, architecture decision, incident mgmt |
| skill-high + leverage-high | Strategic + systemic — changes whole systems | Platform architecture, product vision, process design |
Key: Skill and leverage are orthogonal. High leverage doesn't mean high skill, and vice versa.
Add relevant context labels:
| Category | Tags |
|----------|------|
| Work type | reading, deep-focus |
| Status | waiting, next |
| Energy | energy-low |
| Location | home, errands |
| Communication | call, email, messenger |
Place the task in the correct project. Read project structure reference for the full project list and important sections.
waiting status MUST include a comment explaining what they're blocked on and a reschedule datenext tag = the single next physical action (GTD-style) — not "plan the project" but "draft the email"skill-high + leverage-high work should be protected — schedule deep-focus blocks, don't let it get squeezed by skill-low + leverage-low tasksXL task is actually a project — consider breaking it into subtasksFor each inbox task:
next tag added if this is the immediate next actionwaiting tag + comment + reschedule date if blockeddevelopment
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.