skill: codex review P2-1 — verification gate now tests the user's edited file

The original SKILL.md Step 6 told users to run `node harness.mjs` from the
gbrain repo as the mandatory ≥95% gate. But that runs the harness against
the COMMITTED sample variants in evals/functional-area-resolver/variants/,
not the file the user just compressed. The gate could pass while the edit
dropped a sub-skill.

Step 6 now:
- Gate 1 stays at `gbrain routing-eval --json` (structural, runs against
  the user's actual routing-eval.jsonl fixtures).
- Gate 2 is rewritten: copy the user's edited routing file into a tmp
  variants dir, then run `node harness.mjs --variants-dir <tmp>
  --variants my-edit --model opus`. This exercises the harness's existing
  --variants flag (added in commit 472cc686 / T4) but now points at the
  user's actual edit. The harness uses gbrain-bundled fixtures, so this
  is a regression check on shared skills, not a full eval of the user's
  fixture set — and the SKILL.md says so explicitly.

Also adds a "common false negatives" callout: when the user's routing
file doesn't expose the skills gbrain's bundled fixtures target (e.g.
`gmail`, `enrich`), expect strict-scoring fails on those rows; lenient
scoring remains accurate.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

skills/functional-area-resolver/SKILL.md

@@ -237,22 +237,59 @@ stay as individual rows — they're checked on every message, not dispatched.
 Run two gates before committing the compressed file. Do NOT commit if either
 fails.
 
-```bash
+**Gate 1: Structural verification.** Confirms your `routing-eval.jsonl`
-# Structural verification — checks routing-eval.jsonl fixtures still resolve
+fixtures still resolve to the right skills under the compressed routing file.
-gbrain routing-eval --json
+Run from the workspace whose routing file you just edited:
 
-# LLM A/B verification — re-runs the held-out corpus against the variants
+```bash
-# (this is the gate that proves compression didn't drop sub-skills)
+gbrain routing-eval --json
-cd evals/functional-area-resolver
-node harness.mjs
 ```
 
-If the harness's functional-areas variant scores below 95% on the held-out
+If accuracy on your fixtures drops below 95%, revert and tune the area
-corpus, revert the compression and tune the area entries before re-running.
+entries before re-running.
-Common causes of accuracy drops:
+
+**Gate 2: LLM A/B verification on YOUR edited file.** Confirms a frontier
+LLM can still drill into the dispatcher list and reach sub-skills under
+your specific compression. Requires a gbrain repo checkout because the
+harness lives there. Copy your edited routing file into the harness's
+variants directory, then invoke the harness with `--variants` pointing
+at it:
+
+```bash
+# In your agent workspace, identify the routing file you just compressed.
+EDITED=/path/to/your/AGENTS.md       # or skills/RESOLVER.md, whichever you edited
+
+# In your gbrain repo checkout:
+cd /path/to/gbrain/evals/functional-area-resolver
+TMP=$(mktemp -d)/variants && mkdir -p "$TMP"
+cp "$EDITED" "$TMP/my-edit.md"
+
+# Run the harness against your file (sequential, ~75 calls × $0.0076 ≈ $0.57 on Opus).
+ANTHROPIC_API_KEY=... node harness.mjs --variants-dir "$TMP" --variants my-edit \
+                                       --model opus --parallel 3 --yes
+```
+
+The harness uses gbrain's bundled fixture set, so this verifies "did the LLM
+land in the right sub-skill for routing intents the gbrain-bundled fixtures
+cover" — a regression check on shared skills, not a full re-eval of YOUR
+fixture set. For full eval coverage, mirror this skill's
+`fixtures.jsonl` + `fixtures-held-out.jsonl` setup with intents specific
+to your skills.
+
+If the lenient (same-area) score on your variant drops below 95%, revert the
+compression and tune. Common causes:
 - A sub-skill was omitted from the `(dispatcher for: ...)` list.
 - Trigger phrases for an area are too narrow (LLM can't recognize intent).
 - Areas were collapsed too aggressively (too few areas — see Anti-Patterns).
+- ASCII `->` vs Unicode `→` mismatch — the harness now accepts both, but
+  earlier versions only matched Unicode. Pin gbrain to v0.32.3.0+.
+
+Common false negatives on the harness eval (NOT bugs in your compression):
+- The gbrain-bundled fixtures target skill names like `enrich`, `query`,
+  `gmail`, `executive-assistant`. If your routing file doesn't expose
+  those skills at all, expect strict-scoring failures on those fixtures.
+  Lenient scoring stays accurate for any sub-skill present in your
+  `(dispatcher for: ...)` lists.
 
 ### Step 7: Review the diff before committing