Add PRD to steel thread skill - #1
Conversation
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Engagement example of skill being used on a real feature that was shipped.Running agent with skillRunning.agent.with.skill.movInternal agent asking human questions (guided by skill)Ravi.asking.human.questions.guided.by.skill.movInternal agent asking human questions for further clarification after creating steel thread docRavi.asking.human.questions.for.further.clarification.after.creating.steel.thread.doc.movSteel thread ready!The next step is to run Usually the PRD itself is fed into |
bsigney
left a comment
bsigney
left a comment
There was a problem hiding this comment.
Really like this. What makes it work for me: steel thread as Slice 0 and solo before anything fans
out, infrastructure only in the slice that exercises it, and "capacity is a ceiling, not a target" —
that last one is the opposite of how most plans get written. Flat Slice 0..N instead of lanes and
1a/1b keeps it readable too. Repo side's clean: validate passes, links stay inside the skill,
README row's there.
Just a few inconsistencies to sort out — mostly the same rules written in several places, and a
couple have already drifted apart from each other. Comments inline.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
bsigney
left a comment
bsigney
left a comment
There was a problem hiding this comment.
Just two critical points Rahul.
Otherwise everything else looks good.
|
|
||
| **Gate:** obtain explicit human confirmation before writing the final artifact. | ||
|
|
||
| Then write `steel-thread.md` next to the source PRD using |
There was a problem hiding this comment.
written with no existence check — no instruction to check whether one already exists and what to do with it.
Will be overwritten according to this.
|
|
||
| Do not create artificial sub-slices merely to occupy every pair. | ||
|
|
||
| ### 8. Confirm the roadmap and write the artifact |
There was a problem hiding this comment.
The architecture path, infrastructure ownership, SDD command, pair count and Slice 0 approval are each established through a gate, then held only in conversation. Nothing is written until step 8. On a compacted, resumed or interrupted run the agent still has the PRD and the template in front of it, so it doesn't start over. It re-derives an architecture path and a pair count instead, which is what SKILL.md:43-44 forbids: "Do not assume architecture, infrastructure, team capacity." The rule is asserted with no mechanism behind it
2 participants
Why
Product PRDs describe what to build, but technical planning benefits from first identifying the thinnest end-to-end steel thread and then sequencing the remaining scope as demo-ready vertical slices. This skill creates that bridge without embedding organization-specific domain knowledge.
Parallelism must be considered while slices are formed, not added after technical tasks are generated. Capturing Dev+agent pair capacity, dependencies, safe parallel groups, and synchronization points in
steel-thread.mdgives Spec Kit/speckit.planor an equivalent SDD planning step the delivery constraints needed to produce an executable design without forcing unsafe concurrency.What changed
prd-to-steel-threadskillsteel-thread.mdwith a solo steel thread, demo-ready slices, JIT infrastructure, and capacity-aware parallelism