How do I install the Elsa Whats Next skill?

Run npx skillmds@latest add elsa-workflows/elsa-whats-next in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Elsa Whats Next safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Elsa Whats Next?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Elsa Whats Next free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Elsa Whats Next?

elsa-workflows (@elsa-workflows) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Elsa Whats Next by elsa-workflows — Agent Skill

Name: Elsa Whats Next
Author: elsa-workflows

Elsa Whats Next

Find and rank the next Elsa-brain work unit from unfinished work, reports, specs, and source markers. Use when a user asks what is next, what is unfinished, what is unratified, what is weakly implemented, or which unit should be planned next in elsa-foundation.

File contents

User Input

$ARGUMENTS

Outline

Read AGENTS.md, especially source-of-truth layers and the program goals / drift guard.
Read docs/skills/catalog.md#whats-next--unfinished-work.
Inspect docs/program-goals/ to identify the current program-goal state when it affects ranking or is unclear: a named bucket, none/free-flow, or temporarily unknown/not-assessed.
Read .agent-prefs/session-execution-model.md if it exists.
Read docs/reports/unfinished-work.md as inventory/evidence, not an active queue.
Refresh context with the marker search from unfinished-work.md when the user asks for current state or when freshness is uncertain.
Rank candidates by current program-goal state when applicable, user intent, severity, and unblock value.
Return a concise drift check, top candidates, recommendation, source-of-truth layer, program-goal route, program-goal state when used, and execution route. If the recommended unit requires substantial planning or implementation and the local session preference favors fresh workers or ask-each-time, ask whether to plan/execute here or prepare a reviewed handoff prompt for a fresh agent/thread.

Do not implement from this skill. If the user approves a unit, hand off to elsa-work-unit-planner or the relevant implementation skill.

Frequently asked questions