From yukti
[Deprecated as standalone — internal pipeline stage] Locate the minimum set of files relevant to a task. Returns a precise file list. Runs on Haiku. Use /yukti:smart for code-change tasks; the orchestrator invokes the explorer internally. Direct invocation is preserved for power users but may be removed in v0.3.
How this skill is triggered — by the user, by Claude, or both
Slash command
/yukti:exploreexplorerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **Deprecated as a standalone skill.** The `explorer` agent is still actively used by the `smart-orchestrator` as Step 1 of the `/yukti:smart` pipeline — it's not going away. Direct invocation via `/yukti:explore` is preserved for now but is **redundant** for most users:
Deprecated as a standalone skill. The
exploreragent is still actively used by thesmart-orchestratoras Step 1 of the/yukti:smartpipeline — it's not going away. Direct invocation via/yukti:exploreis preserved for now but is redundant for most users:
- For a code-change task, just type
/yukti:smart <task>— the orchestrator invokes the explorer for you.- For a "where is X?" question, plain Claude Code is faster (the smart skill is non-forked; it'll route to direct answer).
Direct
/yukti:exploreis most useful when you specifically want a fresh Haiku-based file scan with no further pipeline. May be removed entirely in v0.3 if usage signal stays low.
Locate the files needed for this task:
$ARGUMENTS
Follow your system prompt rules. Return only the structured file list — no preamble, no explanation. Stay under 10 tool calls.
npx claudepluginhub akii09/yukti --plugin yuktiGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Implements work from a spec or tickets using TDD at agreed seams, with regular typechecking and test runs, followed by code review.