levels-next
Pick the single most valuable next step across all level skills for this project, explain why, and offer to start it. `levels` is the front door; this skill only recommends. Use when the user runs /le
SKILL.mdskills/levels-next/SKILL.md
GitHubLevels next
Arguments: $ARGUMENTS
Treat the arguments as the user's goal or deadline, if given. This skill recommends and hands off. It does no auditing or building of its own.
Step 1: Read the situation
- Read
LEVELS.mdin the project root if it exists: levels, targets, gaps, pending actions, dates, profiles. - Take a short look at the project: is there code, an interface, a server, stored data, tests, deploy files, documentation. Do not audit.
- If there is no goal in the arguments or the record, ask one question with AskUserQuestion: what is the user trying to reach, and by when.
Step 2: Choose
If there is no project yet, recommend idea-level.
If there is a project but no record, recommend the starting point by what exists: backend-level in audit mode for a product with an interface and a server (with design-level as the step after it), design-level or backend-level for one layer alone, code-level first for an inherited codebase the user does not yet understand.
Otherwise rank candidates by this order and take the first that applies:
- Danger already recorded. An open finding about data loss, an exposed secret or a critical security weakness. Run the skill that owns it.
- Waiting on the user. A pending live step or unanswered question blocks other work. Say what it is. No skill needs to run.
- Deadline. With a date close, the layer whose gaps would be seen or felt on the day:
ship-level, thentest-level, thenpitch-levelfor an event or submission. - Order between layers. A layer that others depend on comes first:
code-levelbefore a large build that would land in tangled code.test-levelbefore restructuring or tuning untested code.backend-levelbeforedesign-levelwhen the interface needs states the server does not report.data-levelbeforebackend-levelwhen the stored shape is the problem.security-levelandship-levelbefore anything is exposed to real users.ux-levelbeforedesign-levelwhen users cannot finish a task.restyle-levelafterux-leveland beforedesign-levelwhen the complaint is the look itself, not missing polish.perf-levelonly after behaviour is correct and tested.docs-levelandpitch-levelafter the thing they describe has stopped changing.
- Distance. The layer furthest below its target.
- Never run. A layer relevant to this product with no row in the record.
- Stale. A layer whose record is older than the code it covers.
If the record shows an unfinished flow, recommend resuming levels unless a danger from rule 1 is open.
If every layer is at target and nothing is pending, say so and recommend stopping. Do not invent work.
Step 3: Recommend
Print:
- Next: the skill, the mode and the arguments to run it with.
- Why: one or two sentences tied to the record and the goal.
- What it will cost: whether it starts an Opus audit, and whether it will ask questions first.
- After that: the next two steps in order, one line each.
Then ask with AskUserQuestion: Start it (Recommended) / the second and third candidates, if there are any / Not now.
On a yes, invoke the chosen skill with the Skill tool, passing the goal and the relevant profiles so it does not ask again. One hop: the skill started here reports back and does not start another.
Rules
Recommend one thing, not a list of everything. Never recommend a higher target than the product needs. Never start a skill without the user's answer. If the chosen skill is missing from the skill listing, say so and offer the next candidate.