@spardutti/claude-skills 2.57.0 → 2.58.0

package/README.md

@@ -36,7 +36,7 @@ npx @spardutti/claude-skills
 ```
 
 ```text
-  Claude Skills Installer v2.57.0
+  Claude Skills Installer v2.58.0
 
   ── Frontend ──────────────────────────────
   ◉ react              ◯ tanstack-query
@@ -134,7 +134,7 @@ Portable slash commands installed to `.claude/commands/`. Some orchestrate paral
 |---------|--------------|
 | `/ship` | Unified delivery pipeline — commit → gate → PR → merge → release. The gate is the one enforcement moment: it checks the diff's file lengths and that new files sit in their kind folder, audits it against the skills installed in the project, mutation-tests the changed lines to prove the tests would catch a break, and runs one `/code-review` round for logic bugs — **fixing what it finds** rather than handing you a list. It runs before the **PR**, not before every commit: its scope is the whole branch, so gating each commit re-mutated every file the branch had ever touched. `--force` skips it. No argument steps through interactively; `/ship pr` runs through PR creation; `/ship release` runs the full pipeline |
 | `/discover` | Find the right problem before deciding what to build — diverges first: generates competing framings through blind subagents under forced constraints, stress-tests the winner with a blind critic, and refuses to converge until every open question is answered or deferred, then drafts scope, non-goals, edge cases and success criteria for you to correct. Run before `/plan-feature` |
-| `/plan-feature` | Integration-first feature planning, then building — 3 parallel subagents scan for reusable code, patterns and touch points, grounded clarifying questions follow, the plan is written as type-checked stubs at the real paths, and on your go the same agent fills them in |
+| `/plan-feature` | Integration-first feature planning, then building — one agent scans the repo for reusable code, patterns and touch points, grounded clarifying questions follow, the plan is written as type-checked stubs at the real paths, and on your go it fills them in |
 | `/optimize` | Make one measured job faster without changing what it proves — fixes a benchmark and a result that must not move, sends 4 read-only subagents to find suspects, then changes one thing per round with a prediction written first, keeping only what beats the noise. Profiles after every wrong prediction, reruns before judging a result that flipped, and ends by writing the cause as a skill rule for you |
 | `/handoff` | Write a handoff doc so a fresh session picks the work up — captures what auto-compaction loses: decisions made and rejected, dead ends already ruled out, why the tree is dirty, and the one next step |
 | `/lockdown` | Per-repo supply-chain hardening — detects the package managers, Dockerfiles, and CI in use, then guides you through and applies install-time, deploy, and pipeline hardening for npm/pnpm, pip/uv, Docker, and GitHub Actions |

package/hooks/ship-log.mjs

@@ -161,7 +161,9 @@ function run(mode, args) {
 }
 
 try {
-  if (process.env.SHIP_LOG_ROOT) process.chdir(process.env.SHIP_LOG_ROOT);
+  // Like ship-mark, ship-gate and ship-prep, a worktree ship names its folder in CLAUDE_PROJECT_DIR.
+  const root = process.env.SHIP_LOG_ROOT || process.env.CLAUDE_PROJECT_DIR;
+  if (root) process.chdir(root);
   process.exit(run(process.argv[2], process.argv.slice(3)) ?? 0);
 } catch (err) {
   console.error(`ship-log: ${err.message}`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@spardutti/claude-skills",
-  "version": "2.57.0",
+  "version": "2.58.0",
   "description": "Guardrails for Claude Code — best-practice skills, planning commands, and delivery gates.",
   "type": "module",
   "repository": {