claude-dev-env 1.50.3 → 1.51.0

package/skills/refine/SKILL.md

@@ -1,6 +1,12 @@
 ---
 name: refine
-description: Interview-driven plan refiner with built-in audit loop. Takes a draft, a topic, or the active conversation; fans out research agents; interviews via AskUserQuestion until further questions would be impractical hypotheticals; writes the plan to the Obsidian vault under Research/<topic>/<slug>.md; then loops a general-purpose audit and fix pass (both with plan-quality rubrics) until the plan is clean, with a sibling <slug>-implementation-notes.html capturing design decisions, deviations, tradeoffs, and open questions across iterations. The interview is mandatory and the vault is the only output target — these survive any session-level "no clarifying questions" or local plans/ shortcuts. Use when the user says /refine, "refine this", "turn this into a plan", "flesh this out", "make a spec for this", "let's plan this out", or asks for a vague idea to be matured into a plan. Always operates on plans — skill plans, new-code implementation plans, or code-refinement plans.
+description: >-
+  Interview-driven plan refiner with built-in audit loop: fans out research agents,
+  interviews via AskUserQuestion (mandatory — survives no-question directives), writes
+  the plan to the Obsidian vault under Research/<topic>/<slug>.md, then loops audit and
+  fix until clean. Triggers: /refine, "refine this", "turn this into a plan", "flesh
+  this out", "make a spec for this", "let's plan this out", or any vague idea to mature
+  into a plan.
 ---
 
 # refine
@@ -164,7 +170,7 @@ Spawn `general-purpose` (`subagent_type: general-purpose`, foreground) with:
   - **Ambiguity** — no parked open questions where a decision is required for implementation to begin
   - **Implementer-readiness** — a downstream implementer can act on each step without back-and-forth (file paths named, agents named, change concrete)
 - A required return shape: structured findings as `severity (P0/P1/P2) | location | violation`, plus an explicit `CLEAN` verdict when no findings remain
-- An explicit instruction NOT to apply code-review rubrics (CODE_RULES categories A–N, API contracts, resource cleanup, etc.) — the audit target is a markdown plan, not source code
+- An explicit instruction NOT to apply code-review rubrics (CODE_RULES categories A–P, API contracts, resource cleanup, etc.) — the audit target is a markdown plan, not source code
 
 If the verdict is `CLEAN`: skip step 8 and proceed to step 10.
 

package/skills/structure-prompt/SKILL.md

@@ -1,16 +1,11 @@
 ---
 name: structure-prompt
 description: >-
-  Restructure any user-provided prompt — order blocks correctly, replace persona
-  framing with task constraints, enforce per-category dispositions, replace
-  ceremony directives with measurable constraints, expand placeholder tokens
-  into real values via the sibling rubric or AskUserQuestion, add file:line
-  citations for identifiers that appear in the data body, mark the canonical
-  sub-bucket with ⭐, and sharpen generic adversarial-pass phrasing into a
-  category-specific failure-mode noun. Trigger when the user invokes
-  /structure-prompt, pastes a prompt and asks to optimize it, asks for a
-  "minimally invasive edit" to a prompt artifact, or asks to "tighten this
-  prompt."
+  Restructure a user-provided prompt: order blocks, replace persona framing with task
+  constraints, enforce per-category dispositions, expand placeholder tokens via the
+  sibling rubric or AskUserQuestion, add file:line citations, mark the canonical
+  sub-bucket, sharpen adversarial-pass phrasing. Triggers: /structure-prompt, "optimize
+  this prompt", "minimally invasive edit" to a prompt artifact, "tighten this prompt".
 ---
 
 # structure-prompt