fix: remove non-spec trigger: field from skill frontmatter (#1180)

The Agent Skills spec only defines name, description, license,
compatibility, metadata, and allowed-tools as valid frontmatter fields.
The trigger: /graphify line was non-spec, silently ignored by spec-
following hosts, and flagged by agentskills validate CI checks.

- gen.py: removed trigger emission from _render_frontmatter; added
  _is_trigger_line() helper for roundtrip allow-list
- fragments/core/aider.md: removed hardcoded trigger: /graphify
- platforms.toml: removed trigger doc comment and trigger="" entries
- test_skillgen.py: replaced trigger-assertion tests with a single
  test asserting no host has trigger: in frontmatter
- Regenerated all 125 skill artifacts

Routing intent is preserved: the description field already contains
"treated as a graphify query first" and "graphify-out/ exists".

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

graphify/skill-aider.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

graphify/skill-amp.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

graphify/skill-claw.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

graphify/skill-codex.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

graphify/skill-copilot.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

graphify/skill-droid.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

graphify/skill-kilo.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

graphify/skill-opencode.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

graphify/skill-trae.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

graphify/skill-vscode.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

graphify/skill-windows.md

@@ -1,7 +1,6 @@
 ---
 name: graphify-windows
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

graphify/skill.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tests/test_skillgen.py

@@ -365,20 +365,13 @@ def test_all_progressive_hosts_check_and_audit_clean():
         assert probs == [], f"[{key}] audit\n" + "\n".join(probs)
 
 
-def test_kiro_and_pi_omit_the_trigger_line():
-    """kiro and pi render no frontmatter trigger (trigger absent in v8)."""
-    for key in ("kiro", "pi"):
+def test_no_host_has_trigger_in_frontmatter():
+    """No split host emits a trigger: field — not part of Agent Skills spec (#1180)."""
+    for key in ("claude", "codex", "opencode", "kilo", "copilot", "claw", "droid",
+                "amp", "trae", "vscode", "kiro", "pi"):
         core, _ = _platform_artifacts(key)
         head = core.split("---", 2)[1]
-        assert "trigger:" not in head, f"[{key}] unexpectedly has a trigger line"
-
-
-def test_triggered_hosts_keep_the_trigger_line():
-    """The other split hosts keep trigger: /graphify in the frontmatter."""
-    for key in ("opencode", "kilo", "copilot", "claw", "droid", "amp", "trae", "vscode"):
-        core, _ = _platform_artifacts(key)
-        head = core.split("---", 2)[1]
-        assert "trigger: /graphify" in head, f"[{key}] missing trigger line"
+        assert "trigger:" not in head, f"[{key}] unexpectedly has a trigger: line"
 
 
 def test_kilo_renders_its_rules_tail_section():
@@ -466,10 +459,15 @@ def test_monoliths_change_only_the_enum_description_and_chunk_cleanup():
     platforms = gen.load_platforms()
     for key in ("aider", "devin"):
         rendered = gen.render(platforms[key])[0].content.splitlines()
-        original = gen._normalise(gen._git_show(platforms[key].roundtrip_ref)).splitlines()
+        # Strip trigger: lines from the reference — their removal (#1180) is a
+        # permitted diff alongside enum, description, and chunk-cleanup changes.
+        original = [
+            l for l in gen._normalise(gen._git_show(platforms[key].roundtrip_ref)).splitlines()
+            if not gen._is_trigger_line(l)
+        ]
         assert len(rendered) == len(original), f"[{key}] line count changed"
         diff_idx = [i for i, (r, o) in enumerate(zip(rendered, original)) if r != o]
-        # Exactly four lines change: the prose enum guidance, the schema line,
+        # Four lines change: the prose enum guidance, the schema line,
         # the frontmatter description, and the chunk-cleanup rewrite.
         assert len(diff_idx) == 4, f"[{key}] expected 4 changed lines, got {len(diff_idx)}"
         enum_changes = 0

tools/skillgen/expected/graphify__skill-aider.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/expected/graphify__skill-amp.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/expected/graphify__skill-claw.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/expected/graphify__skill-codex.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/expected/graphify__skill-copilot.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/expected/graphify__skill-droid.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/expected/graphify__skill-kilo.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/expected/graphify__skill-opencode.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/expected/graphify__skill-trae.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/expected/graphify__skill-vscode.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/expected/graphify__skill-windows.md

@@ -1,7 +1,6 @@
 ---
 name: graphify-windows
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/expected/graphify__skill.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/fragments/core/aider.md

@@ -1,7 +1,6 @@
 ---
 name: graphify
 description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger: /graphify
 ---
 
 # /graphify

tools/skillgen/gen.py

@@ -244,7 +244,7 @@ class Platform:
     refs_dst: str | None = None
     name: str = "graphify"
     description: str | None = None
-    trigger: str | None = "/graphify"
+    trigger: str | None = None  # removed — not part of Agent Skills spec (#1180)
     dispatch: str | None = None
     query_variant: str = "cli-inline"
     extraction: str = "verbose"
@@ -283,7 +283,7 @@ def load_platforms() -> dict[str, Platform]:
             refs_dst=cfg.get("refs_dst"),
             name=cfg.get("name", "graphify"),
             description=cfg.get("description"),
-            trigger=cfg.get("trigger", "/graphify"),
+            trigger=cfg.get("trigger"),
             dispatch=cfg.get("dispatch"),
             query_variant=cfg.get("query_variant", "cli-inline"),
             extraction=cfg.get("extraction", "verbose"),
@@ -318,16 +318,14 @@ class RenderedArtifact:
 
 
 def _render_frontmatter(platform: Platform) -> str:
-    """Render the YAML frontmatter from the platform's name/description/trigger.
+    """Render the YAML frontmatter from the platform's name and description.
 
-    The trigger line is omitted when the platform has no trigger (kiro/pi).
+    Only emits fields from the Agent Skills spec (name, description).
     The description is preserved verbatim from platforms.toml — never invented.
     """
     if platform.description is None:
         raise ValueError(f"split platform '{platform.key}' is missing a description")
     lines = ["---", f"name: {platform.name}", f'description: "{platform.description}"']
-    if platform.trigger:
-        lines.append(f"trigger: {platform.trigger}")
     lines.append("---")
     return "\n".join(lines)
 
@@ -718,6 +716,15 @@ def _is_chunk_cleanup_line(line: str) -> bool:
     return line.lstrip().startswith("rm -f") and "find " in line and "-name '.graphify_chunk_" in line
 
 
+def _is_trigger_line(line: str) -> bool:
+    """Whether a line is the non-spec ``trigger:`` frontmatter field (#1180).
+
+    The Agent Skills spec does not include ``trigger:`` — only name/description
+    and a few optional fields. Removing it is a permitted monolith diff.
+    """
+    return line.strip().startswith("trigger:")
+
+
 def monolith_roundtrip(platform: Platform) -> list[str]:
     """Assert a monolith renders diff-clean vs its v8 blob modulo allowed changes.
 
@@ -735,14 +742,17 @@ def monolith_roundtrip(platform: Platform) -> list[str]:
     original = _normalise(_git_show(platform.roundtrip_ref))
 
     rendered_lines = rendered.splitlines()
-    original_lines = original.splitlines()
+    # Strip trigger lines from the original before comparing — they are non-spec
+    # and their removal (#1180) is a permitted diff. Filter here so the line-count
+    # check and the per-line zip both operate on the same reduced set.
+    original_lines = [l for l in original.splitlines() if not _is_trigger_line(l)]
 
     problems: list[str] = []
     if len(rendered_lines) != len(original_lines):
         problems.append(
             f"[{platform.key}] line count differs: rendered {len(rendered_lines)} vs v8 {len(original_lines)} "
-            "(the only allowed changes are the enum line(s) and the description line, "
-            "which must not add or remove lines)"
+            "(the only allowed changes are the enum line(s), the description line, "
+            "the chunk-cleanup rewrite, and trigger: removal — none must add or remove other lines)"
         )
         return problems
 
@@ -750,7 +760,7 @@ def monolith_roundtrip(platform: Platform) -> list[str]:
         if r == o:
             continue
         # The permitted diffs are the enum unification, the unified description,
-        # and the shell-agnostic chunk-cleanup rewrite (#1172).
+        # the shell-agnostic chunk-cleanup rewrite (#1172), and trigger removal (#1180).
         if _is_enum_line(r) or _is_frontmatter_description_line(r) or _is_chunk_cleanup_line(r):
             continue
         problems.append(

tools/skillgen/platforms.toml

@@ -18,7 +18,6 @@
 #   refs_dst      rendered references/ dir, relative to the repo root (split only).
 #   name          frontmatter name (default "graphify"; graphify-windows for windows).
 #   description   frontmatter description, PRESERVED VERBATIM per platform. Required.
-#   trigger       frontmatter trigger (default "/graphify"; omit -> no trigger line).
 #   dispatch      Part-B dispatch fragment basename under fragments/dispatch/.
 #   query_variant cli | cli-inline. Selects both the core query stub and the
 #                 query reference body.
@@ -158,7 +157,6 @@ core = "core"
 skill_dst = "graphify/skill-kiro.md"
 refs_dst = "graphify/skills/kiro/references"
 description = "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger = ""
 dispatch = "agent-tool-disk"
 query_variant = "cli-inline"
 extraction = "compact"
@@ -169,7 +167,6 @@ core = "core"
 skill_dst = "graphify/skill-pi.md"
 refs_dst = "graphify/skills/pi/references"
 description = "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
-trigger = ""
 dispatch = "agent-tool-disk"
 query_variant = "cli-inline"
 extraction = "compact"