Repository navigation
✨ spec: start a spec from a voice recording (wording-only, per #122) - #124
clubanderson wants to merge 1 commit into
Conversation
The spek-new skill already starts a spec from existing material fetched with the agent's own tools, so a voice recorder's MCP server (Plaud's @plaud-ai/mcp, free) is a source like any other. This names it: the skill recognises "my latest Plaud recording" / "the note titled …", fetches both the AI summary and the transcript, records plaud://recordings/<id> (or the exported file) as provenance, and the seeded interview maps the summary onto sections, action items onto acceptance criteria, and keeps the transcript's exact phrasing in the working context, treating tentative remarks as gaps to ask about. No CLI change: the design (epics-and-seeded-specs) keeps fetching on the agent side, so no Plaud client lands in the binary. Signed-off-by: Andrew Anderson <andy@clubanderson.com> (cherry picked from commit ad4bb67)
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
![hivecommons-hive[bot]](https://avatars.githubusercontent.com/in/3568013?s=60&v=4){kind=small}
There was a problem hiding this comment.
Looks correct to me for #122’s wording-only scope. cmd/epic.go:204 accepts nonempty source URIs without restricting the scheme, and internal/steps/spec/steps.go:127 passes those sources into the seeded interview, so recorder URIs and exported transcript paths fit the existing CLI contract. The guidance at templates/skills/workflows/spek-new/SKILL.md:152 fetches both summary and transcript; templates/steps/spec/00b-interview.md:24 keeps exact phrasing in working context and tentative remarks as questions, as requested.
The regression test checks the rendered installed skill and seeded interview wording. Local tests were blocked by the reviewer environment; the current head’s Dagger Build and Test checks report success.
— hive: agent=reviewer backend=codex model=gpt-6.1-sol codex=0.167.0
Closes #122.
Wording-only change to the
spek-newskill and the seededinterviewstep, exactly the scope #122 asked for. No CLI change: fetching stays on the agent side with its own tools, so no Plaud client lands in the binary.plaud://recordings/<id>) or the exported file as provenance..spektacular/working-context.md, and treats tentative remarks ("maybe", "we could") as gaps to ask about.templates/seeding_test.gopins the wording.This is the first commit of #123 carved out on its own. The rest of #123 (an in-binary Plaud MCP client, Wispr Flow, a
voicecommand and publish chain) is intentionally not included; see the comment on #123 for why.CI (Dagger) is the verdict; no tests were run locally.
🤖 Generated with Claude Code