flatten: skills directly at repo root, no skills/ subdir

~/dev/skills/skills/boss/ was visually awkward (skills/skills
read twice) and structurally unnecessary — the skills ARE the
repo's main content, not a sub-collection inside it.

Layout changes:
- boss/SKILL.md moves to the repo root
- skills/README.md (migration notes) moves to docs/migration.md
  where documentation-about-the-system belongs
- install.sh discovers skills via the SKILL.md marker file
  instead of a hardcoded skills/<name>/ path, so future skill
  additions just drop in at the root

Cross-references in boss/SKILL.md (../README.md, ../brainstorm,
etc.) now resolve against the repo root instead of the old
skills/ subdir, which is what they describe: top-level
README is the skill table; sibling skill dirs are the other
migrated skills.

README.md

@@ -70,7 +70,8 @@ plugin.
 
 ## Status
 
-This is the skeleton commit. The skill bodies and agent files
+Migration from AILang's in-tree `~/dev/ailang/skills/` is in
-still need to be migrated from AILang's in-tree
+progress. The `boss` skill is the landed pilot; the remaining
-`~/dev/ailang/skills/` and generalised against this plugin's
+seven skills follow. See `docs/migration.md` for the per-skill
-profile schema. That migration is iteration 1.
+and per-agent migration checklists and the expected final
+layout.

docs/migration.md

@@ -1,20 +1,27 @@
-# skills/
+# Migration
 
-One subdirectory per skill, each containing a `SKILL.md` plus
+This document tracks the migration from AILang's in-tree
-the agent files that skill dispatches under `agents/`. Agents
+`~/dev/ailang/skills/` into this plugin.
-live with their dispatching skill, not in a parallel top-level
-directory — this is what makes the "no orphan agents" rule
-structurally true rather than only documented.
 
-Migration from AILang's in-tree `~/dev/ailang/skills/` runs in
+Each skill is one top-level directory at the repo root,
-iteration 1. The `boss` skill is the migration pilot
+containing a `SKILL.md` plus the agent files it dispatches
-(landed); the remaining seven skills follow once the pattern
+under `agents/`. Agents live with their dispatching skill —
-is approved.
+this is what makes the "no orphan agents" rule structurally
+true rather than only documented.
 
-Expected layout after migration:
+The `boss` skill is the migration pilot (landed); the remaining
+seven skills follow once the pattern is approved.
+
+## Expected layout after migration
 
 ```
-skills/
+~/dev/skills/
+├── README.md
+├── INSTALL.md
+├── install.sh
+├── uninstall.sh
+├── docs/
+├── templates/
 ├── boss/                          (pilot: landed)
 │   └── SKILL.md
 ├── brainstorm/
@@ -55,11 +62,13 @@ skills/
 `boss` has no agents — it is itself the dispatcher of the
 others, not a dispatcher-of-subagents.
 
-`install.sh` symlinks each skill's directory into
+`install.sh` walks the repo root, treats every top-level
-`~/.claude/skills/<name>` and each skill's `agents/`
+directory that contains a `SKILL.md` as a skill, and symlinks
-subdirectory into `~/.claude/agents/<name>`, so Claude Code's
+it into `~/.claude/skills/<name>`; if the skill has an
-flat user-level discovery still finds everything while the
+`agents/` subdirectory, that is symlinked into
-source tree keeps the structural binding.
+`~/.claude/agents/<name>`. Claude Code's flat user-level
+discovery still finds everything while the source tree keeps
+the structural binding.
 
 ## Migration checklist per skill
 

install.sh

@@ -1,9 +1,10 @@
 #!/usr/bin/env bash
 # Install the skills plugin globally into ~/.claude/.
 #
-# For each skill <name> under skills/<name>/, creates symlinks:
+# Each top-level directory that contains a SKILL.md is treated as
-#   ~/.claude/skills/<name>  -> <repo>/skills/<name>
+# a skill. For each such <name>, creates symlinks:
-#   ~/.claude/agents/<name>  -> <repo>/skills/<name>/agents   (if that dir exists)
+#   ~/.claude/skills/<name>  -> <repo>/<name>
+#   ~/.claude/agents/<name>  -> <repo>/<name>/agents   (if that dir exists)
 #
 # Idempotent — existing symlinks pointing to this repo are left
 # alone; existing entries that point elsewhere are reported and
@@ -39,16 +40,15 @@ link_one() {
     echo "link  $dst -> $src"
 }
 
-if [ -d "$REPO_DIR/skills" ]; then
+for d in "$REPO_DIR"/*/; do
-    for s in "$REPO_DIR"/skills/*/; do
+    [ -d "$d" ] || continue
-        [ -d "$s" ] || continue
+    [ -f "$d/SKILL.md" ] || continue
-        name="$(basename "$s")"
+    name="$(basename "$d")"
-        link_one "$s" "$CLAUDE_SKILLS/$name"
+    link_one "${d%/}" "$CLAUDE_SKILLS/$name"
-        if [ -d "$s/agents" ]; then
+    if [ -d "$d/agents" ]; then
-            link_one "$s/agents" "$CLAUDE_AGENTS/$name"
+        link_one "${d%/}/agents" "$CLAUDE_AGENTS/$name"
-        fi
+    fi
-    done
+done
-fi
 
 echo
 echo "Install complete."