bkit-explore

bkit Explore — Skill / Agent / Eval Discovery

v2.1.11 Sprint β FR-β1. Wraps lib/discovery/explorer.js to give Yuki + first-run users a single-command surface that answers "what's actually installed and how do I find it?"

Arguments

Argument	Description	Example
(none)	Show all categories with counts + first-line description	/bkit-explore
<category>	One of starter, dynamic, enterprise, pdca-core, utility	/bkit-explore dynamic
evals	List skills with an evals/{cls}/{skill}/eval.yaml definition	/bkit-explore evals
--level <L>	Filter by Starter / Dynamic / Enterprise (cumulative)	/bkit-explore --level Starter

Behavior

Default (no args) — full tree

1. Call explorer.listAll() to read skills/*/SKILL.md + agents/*.md.
2. Render category-grouped table: skill name + first-sentence description.
3. Footer: Total: N skills · M agents · K evals.

<category> — single bucket

1. Validate category against explorer.CATEGORIES.
2. Render skill table + agent table for that bucket only.
3. Suggest /bkit-explore --level Starter if user looks lost.

evals — eval coverage

1. Call explorer.listEvals() and group by classification (workflow, capability, hybrid).
2. Render counts + skill names per group.
3. Tip: /bkit-evals run <skill> to execute one.

--level <L> — Starter / Dynamic / Enterprise filter

1. Starter returns starter + pdca-core + utility.
2. Dynamic adds dynamic (cumulative).
3. Enterprise adds enterprise.

Output Layout (Design §5.1)

bkit Explore — 39 Skills · 36 Agents · K Evals
─────────────────────────────────────────────────
📂 starter (1 skill / 2 agents)
   /starter         — Static web kit
   🤖 starter-guide — Beginner agent
   🤖 pipeline-guide — Phase walk-through

📂 dynamic (8 skills / 2 agents)
   /dynamic           — bkend.ai fullstack
   /bkend-auth        — Authentication patterns
   ...
─────────────────────────────────────────────────
Footer: Try /bkit-explore --level Starter