agentleFS
Sign inStart free
michaelalbermichaelalber/ai-toolkit/skills/qrspi-questions/SKILL.md

qrspi-questions

Skill3 starsChanged 4 months agoMITView on GitHub

QRSPI Questions phase -- surface what the agent does not know before any research or design begins. Use for "/qrspi-questions <feature>", "what don't we know about X", "surface unknowns for X", "open technical questions for X". Do NOT use to answer a question or for general Q&A -- this phase ASKS questions, it does not answer them. Do NOT use for the deprecated RPI workflow.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    ASK, never answer -- this phase produces questions, not solutions, designs, or research

    line 25
  2. Very specific:

    STOP after writing questions.md -- the human answers inline before Research begins

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

QRSPI Questions

"Judge a person by their questions rather than their answers." -- Adapted from Voltaire

Core Philosophy

The Questions phase is the first alignment gate of QRSPI. Before any codebase research or design, the agent surfaces every unknown as a targeted technical question and STOPS for the human to answer. A skipped question becomes a wrong assumption; a wrong assumption cascades into wrong code. This phase makes the unknowns explicit and cheap to correct -- one edit in questions.md, not a rewrite later.

Non-Negotiable Constraints:

  1. ASK, never answer -- this phase produces questions, not solutions, designs, or research
  2. Cover ALL relevant areas -- data model, API contract, UI, integration, auth, testing, edge cases
  3. STOP after writing questions.md -- the human answers inline before Research begins
  4. One feature folder per feature -- every QRSPI artifact co-locates there
  5. CONTEXT BUDGET: keep utilization under 40%. At 60%, write questions.md with progress and tell the user to start a fresh session.

Workflow

PRE-FLIGHT
    [ ] Determine the feature slug (kebab-case) and today's date
    [ ] Feature folder = thoughts/shared/qrspi/YYYY-MM-DD-{slug}/   (create if absent)
    [ ] If an ANSWERED questions.md already exists here, this phase is DONE -> route to /qrspi-research

SURFACE
    Enumerate unknowns across every area the feature could touch:
      data model · API contract · UI/UX · integration points · auth · testing · edge cases · migration
    For each unknown, write a specific, answerable question -- never a vague prompt
    Group questions by area; mark any that BLOCK design as [BLOCKING]

WRITE
    Create thoughts/shared/qrspi/YYYY-MM-DD-{slug}/questions.md
    Use references/questions-template.md
    Set status: awaiting-answers

STOP
    Tell the user: answer the questions inline in questions.md, then start a NEW session
    and run /qrspi-research. Do NOT proceed to Research yourself.

Exit criteria: questions.md written with status awaiting-answers; questions cover all relevant areas with blocking items flagged; user told to answer inline and start a fresh Research session.

State Block

<qrspi-questions-state>
phase: PRE-FLIGHT | SURFACE | WRITE | STOP | COMPLETE
feature_slug: [kebab-slug]
feature_folder: thoughts/shared/qrspi/YYYY-MM-DD-{slug}/
areas_covered: [data | api | ui | integration | auth | testing | edge-cases | migration]
question_count: [count]
blocking_count: [count]
context_budget: under-40 | approaching-60 | checkpoint-now
status: awaiting-answers | complete
</qrspi-questions-state>

Output Template

See references/questions-template.md for the full questions.md structure and frontmatter.

Integration with Other Skills

SkillRelationship
qrspi-researchNext phase. Consumes the ANSWERED questions.md as its neutral topic source.
qrspi-specDownstream. Design decisions trace back to the answers captured here.
spec-coachUse instead when you want an interactive design conversation, not a one-shot question dump.
grill-meUse instead to be quizzed and challenged; qrspi-questions surfaces unknowns FOR the human to answer.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free