hani-q/qstack / skills/qstack-next
qstack-next
VerifiedRecommend the one installed skill to run next, from what the conversation has done so far and the state of the plan folder on disk. Use when invoked as /qstack-next, when asked "what now?" or which skill to use next, or as the last step of /qstack.
/qstack-next
Say what was just done, what that leaves undone, and the one skill that closes the gap. Three or four lines. Name the skill; never run it.
Evidence, heaviest first
- The plan folder. Files on disk say where the work is more reliably than the conversation does. See the table below.
- The working tree.
git branch --show-current,git status --short,git log --oneline -5. Uncommitted changes mean work that is not yet verified or reviewed. - The conversation. What the user asked last, what was produced, what was verified. Facts, not tone: "it's broken" followed by three guards and no reproduction is evidence; a frustrated message is not.
Read what you need and no more. This skill is read-only.
The plan lifecycle
Plan folders are qstack/compound_engineering/plans/<slug>/, or the legacy
compound-engineering/plans/<slug>/. The folder whose slug matches the branch
or the conversation is the one that matters. Its files arrive in a fixed
order, and the first one missing is the next step:
| The folder has | Run next |
|---|---|
| Nothing yet, and the user is describing a feature or change | /qstack-plan-prior-art, then draft plan.md |
plan.md and no plan.html | /qstack-plan-to-html |
plan.html with notes at data-status="open" | /qstack-ask-plan-open-questions |
plan.html and no board-events.js, or a board without its complete-breakdown marker | /qstack-plan-to-html to finish the board |
board-events.js with cards still open | the execution loop execution.md shows was used; /qstack-loop-no-nonsense when it shows none |
every card closed and no outcome.md, on a board with no review epic | /qstack-plan-adherence-review, then /qstack-plan-close |
every card closed and no outcome.md, on a board whose review epic gate card is done | /qstack-plan-close; the gate card already ran the adherence review |
outcome.md | nothing from the lifecycle |
Work with no plan folder and no feature being described is outside the lifecycle; do not push it in.
Outside the lifecycle
Match the conversation against the description: of every installed skill.
The listing script in /qstack prints them; ls ~/.claude/skills ~/.codex/skills ~/.agents/skills names them. Each description says when its
skill applies; that text is the rule, so this file does not repeat it.
Prefer, in order: a QStack skill, a skill from a collection QStack's installer offers, anything else installed. Never recommend a skill that is not installed.
Output
Three or four short lines of plain prose, no heading, no list:
- What was just done. One concrete fact: a file written, a card closed, a branch merged, a failure described.
- What that leaves undone.
Run /<skill>, with its argument when the skill takes one. Name a second skill only when it follows directly, asplan-closefollowsplan-adherence-review.
When a file decided the recommendation, name the file. When nothing is undone
and no description matches: output nothing if /qstack called this skill,
otherwise one line, Nothing pending. Never pad to reach four lines.
Hard rules
- Read-only. Edit nothing, run no skill, start no work.
- One recommendation, not a menu.
- Evidence, not mood. Every recommendation rests on a file, a diff, or a message you can point to.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |