#617 Make skill tool-name references platform-portable

packages/agents/content/_partials/README.md

@@ -40,7 +40,7 @@ The `_partials` directory itself never appears in installed output.
 For each `.md` source file the install pipeline performs, in order:
 
 1. **Expand includes.** `expandIncludes(srcPath, contentDir)` resolves all directive shapes recursively and substitutes slot content.
-2. **Merge frontmatter** (subagents only). Platform-specific frontmatter overrides from `_data/{platform}.yml` are merged into the source's frontmatter.
+2. **Merge frontmatter** (subagents only). Platform-specific frontmatter overrides from `_data/{platform}.yaml` are merged into the source's frontmatter.
 3. **Rewrite tool-name placeholders.** `rewriteToolNames(content, mapping)` replaces each `{tool:NAME}` placeholder using the platform's `_tools:` mapping from the same overlay YAML. An unmapped name is a fatal install error anchored to the source file and line. See [Tool-name placeholders](#tool-name-placeholders).
 4. **Inject the provenance marker.** A `GENERATED FILE` comment is added at the top of the output, with a `Source:` link to the original file.
 5. **Rewrite paths** (skills only, post-write). Bare-relative Markdown links are rewritten to absolute platform paths.
@@ -52,10 +52,10 @@ Expansion runs before the dry-run gate, so missing partials, cycles, and out-of-
 
 ## Tool-name placeholders
 
-Subagent and skill body text reference tools using the `{tool:NAME}` placeholder so the same source can install for platforms that name their tools differently. `NAME` is the canonical (Claude) tool name (`Read`, `Write`, `Edit`, `Bash`, `Grep`, `Glob`). The install pipeline rewrites each placeholder using the platform's `_tools:` mapping, which lives at the top of each overlay YAML at `content/subagents/_data/{platform}.yml`.
+Subagent and skill body text reference tools using the `{tool:NAME}` placeholder so the same source can install for platforms that name their tools differently. `NAME` is the canonical (Claude) tool name (`Read`, `Write`, `Edit`, `Bash`, `Grep`, `Glob`). The install pipeline rewrites each placeholder using the platform's `_tools:` mapping, which lives at the top of each overlay YAML at `content/subagents/_data/{platform}.yaml`.
 
 ```yaml
-# content/subagents/_data/rovodev.yml
+# content/subagents/_data/rovodev.yaml
 _tools:
   Bash: bash
   Edit: find_and_replace_code

packages/agents/content/skills/_data/artifact-conventions.md

@@ -550,17 +550,17 @@ Each role maps to one of five workflow-function types:
 
 ### Artifact entry fields
 
-| Field       | Required | Description                                                                             |
-| ----------- | -------- | --------------------------------------------------------------------------------------- |
-| `filename`  | yes      | Artifact filename (without directory path)                                              |
-| `role`      | yes      | Filename role segment (e.g., `reviewer`, `code-reviewer`)                               |
-| `roleType`  | yes      | Workflow function (one of: `orchestrator`, `analyst`, `planner`, `author`, `reviewer`)  |
-| `agent`     | yes      | Task tool `subagent_type` value (e.g., `orchestrated-reviewer`, `aspect-code-reviewer`) |
-| `type`      | yes      | Artifact type (e.g., `review`, `change-summary`)                                        |
-| `phase`     | yes      | Phase that produced this artifact (camelCase, matches `phases` object keys)             |
-| `createdAt` | yes      | ISO 8601 timestamp                                                                      |
-| `iteration` | no       | Review iteration number (for `parallelReview` phase)                                    |
-| `note`      | no       | Free-text context about the artifact                                                    |
+| Field       | Required | Description                                                                               |
+| ----------- | -------- | ----------------------------------------------------------------------------------------- |
+| `filename`  | yes      | Artifact filename (without directory path)                                                |
+| `role`      | yes      | Filename role segment (e.g., `reviewer`, `code-reviewer`)                                 |
+| `roleType`  | yes      | Workflow function (one of: `orchestrator`, `analyst`, `planner`, `author`, `reviewer`)    |
+| `agent`     | yes      | {tool:Task} `subagent_type` value (e.g., `orchestrated-reviewer`, `aspect-code-reviewer`) |
+| `type`      | yes      | Artifact type (e.g., `review`, `change-summary`)                                          |
+| `phase`     | yes      | Phase that produced this artifact (camelCase, matches `phases` object keys)               |
+| `createdAt` | yes      | ISO 8601 timestamp                                                                        |
+| `iteration` | no       | Review iteration number (for `parallelReview` phase)                                      |
+| `note`      | no       | Free-text context about the artifact                                                      |
 
 ### Phase values
 
@@ -597,7 +597,7 @@ Companion file in the same run directory. Each line is a JSON object (JSONL form
 
 ### Event types
 
-All 13 valid event types and their required fields. Fields suffixed with `?` are optional — usage fields (`tokens`, `toolUses`, `durationMs`) are present on newer runs where the orchestrator captures Task result metrics; older runs omit them:
+All 13 valid event types and their required fields. Fields suffixed with `?` are optional — usage fields (`tokens`, `toolUses`, `durationMs`) are present on newer runs where the orchestrator captures {tool:Task} result metrics; older runs omit them:
 
 | Event type             | Key fields                                                                                                                                       |
 | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |

packages/agents/content/skills/_data/ticket-source-resolution.md

@@ -6,8 +6,8 @@ Resolve a ticket source argument into ticket content and metadata. Skills that a
 
 | Input form                                                  | Resolution                                                        |
 | ----------------------------------------------------------- | ----------------------------------------------------------------- |
-| URL to a known platform (GitHub, Jira, etc.)                | Use platform CLI or WebFetch to retrieve issue content            |
-| Other URL                                                   | WebFetch the URL content                                          |
+| URL to a known platform (GitHub, Jira, etc.)                | Use platform CLI if available; otherwise, fetch the URL content   |
+| Other URL                                                   | Fetch the URL content                                             |
 | Shorthand reference (`#99`, `issue 99`, `GitHub issue #99`) | Resolve platform (see below), then fetch via platform CLI         |
 | File path                                                   | Read the file                                                     |
 | Plain text                                                  | Use as-is                                                         |

packages/agents/content/skills/find-orchestration-savings/SKILL.md

@@ -22,7 +22,7 @@ Analyze a completed orchestrated run to identify cost-saving opportunities while
 
 2. **Verify the run directory** contains `run-log.jsonl` and `run-index.json`. If either is missing, report and exit.
 
-3. **Dispatch the savings-analyzer subagent** via Task tool:
+3. **Dispatch the savings-analyzer subagent** via {tool:Task}:
    - Model: `haiku`
    - Prompt: Provide the run directory path and the next available sequence number for the artifact filename
    - The subagent reads the event log, applies the analysis framework, and writes the artifact
@@ -31,9 +31,9 @@ Analyze a completed orchestrated run to identify cost-saving opportunities while
 
 ## Auto-trigger integration
 
-This skill is also invoked automatically during Phase 5 (summary) of orchestrated runs. The orchestrate engine dispatches the savings-analyzer subagent as a background Task while the orchestrator writes the run-summary inline. When auto-triggered:
+This skill is also invoked automatically during Phase 5 (summary) of orchestrated runs. The orchestrate engine dispatches the savings-analyzer subagent as a background {tool:Task} while the orchestrator writes the run-summary inline. When auto-triggered:
 
 - The run directory is known from the active run context
 - The sequence number follows the run-summary artifact
 - The model is Haiku (configured via the `savings_analyzer` model key, defaulting to `haiku`)
-- Zero added latency: The analysis runs as a background Task while the orchestrator writes the run summary
+- Zero added latency: The analysis runs as a background {tool:Task} while the orchestrator writes the run summary