agile-context-engineering 0.5.0 → 0.5.1

package/skills/research-story-wiki/SKILL.md

@@ -1,92 +1,101 @@
----
-name: research-story-wiki
-description: Research and curate wiki references relevant to a story's technical solution
-argument-hint: "story=<file-path|github-url>"
-disable-model-invocation: true
-allowed-tools: Read, Bash, Write, Edit, AskUserQuestion, Glob, Grep, Agent
-model: opus
-effort: max
-context: fork
-agent: ace-wiki-mapper
----
-
-# Research Story Wiki
-
-Research the project's engineering wiki to identify documents directly relevant to implementing a story.
-
-## When to Use
-
-- After `/ace:plan-story` pass 1 -- once story business requirements (sections 1-8) are complete
-- Anytime a story needs its Relevant Wiki section populated or refreshed
-- When story scope changed and wiki references need re-evaluation
-- Called as part of `/ace:plan-story` pipeline (pass 2)
-
-## Input
-
-### Required
-
-- **`story`** -- Story source:
-  - **File path**: Path to a markdown file containing the story (from plan-story command)
-  - **GitHub URL or issue number**: e.g., `story=#95` or `story=https://github.com/owner/repo/issues/95`
-  - Must be a valid, accessible file or GitHub issue.
-  - Contains the user story, description, and acceptance criteria.
-  - **The story's requirements define which wiki docs are relevant.**
-  - If not valid, stop and prompt the user.
-
-## Environment Context (preprocessed)
-
-!`node "${CLAUDE_SKILL_DIR}/script.js" init "$ARGUMENTS" 2>/dev/null`
-
-## Supporting Resources
-
-Read ALL of these before starting the workflow:
-
-- **Workflow**: Read [workflow.xml](workflow.xml) -- complete orchestration process with all steps
-- **Story wiki template**: Read [story-wiki-template.xml](story-wiki-template.xml) -- output format for the wiki section
-- **UI formatting**: Read `${CLAUDE_SKILL_DIR}/../../shared/utils/ui-formatting.md` -- ACE output formatting rules
-
-## Process
-
-Use the `ace-wiki-mapper` agent for wiki exploration and curation.
-
-The Environment Context above contains the preprocessed INIT JSON -- use it directly instead of running the init script manually. The workflow's step 1 setup can skip the init bash call since that data is already available.
-
-Read all supporting resources listed above, then execute the workflow defined in [workflow.xml](workflow.xml) end-to-end. Preserve all workflow gates (validation, approvals, commits).
-
-The research process:
-1. ALWAYS curates the four system-wide docs with story-specific reasons
-2. Identifies affected subsystems from story content and feature context
-3. Spawns parallel ace-wiki-mapper agents to scan subsystem wiki docs
-4. Compiles a categorized, deduplicated list of relevant references
-
-All output is written to the story file -- populating the Relevant Wiki section placeholder left by pass 1.
-
-## Artifacts
-
-```
-Modifies in-place: the story file at
-.ace/artifacts/product/<id-epic_name>/<id-feature_name>/<id-story_name>/<id-story_name>.md
-(adds/replaces the ## Relevant Wiki section)
-```
-
-## Example Usage
-
-```
-# Example with file path story
-/ace:research-story-wiki \
-  story=.ace/artifacts/product/e1-auth/f3-oauth/s1-buttons/s1-buttons.md
-
-# Example with GitHub issue number
-/ace:research-story-wiki story=#95
-
-# Example with full GitHub URL
-/ace:research-story-wiki \
-  story=https://github.com/owner/repo/issues/95
-```
-
-## Next Steps
-
-- Continue with story refinement -- external analysis (pass 3) or technical solution (pass 5)
-- `/ace:research-external-solution story=... external-codebase=...` -- Analyze external reference systems
-- `/ace:plan-story story=...` -- Continue the full story pipeline
-- `/ace:help` -- Check project initialization status
+---
+name: research-story-wiki
+description: Research and curate wiki references relevant to a story's technical solution
+argument-hint: "story=<file-path|github-url>"
+disable-model-invocation: true
+allowed-tools: Read, Bash, Write, Edit, AskUserQuestion, Glob, Grep, Agent
+model: opus
+effort: max
+context: fork
+agent: ace-wiki-mapper
+---
+
+## Environment Context (preprocessed)
+
+!`node "${CLAUDE_SKILL_DIR}/script.js" init "$ARGUMENTS" 2>/dev/null`
+
+## Supporting Resources (auto-loaded)
+
+!`cat "${CLAUDE_SKILL_DIR}/workflow.xml"`
+
+!`cat "${CLAUDE_SKILL_DIR}/story-wiki-template.xml"`
+
+!`cat "${CLAUDE_SKILL_DIR}/../../shared/utils/ui-formatting.md"`
+
+```xml
+<command>
+
+    <execution-time>
+        <runs-after>
+            <trigger>After /ace:plan-story pass 1 — once story business requirements (sections 1-8) are complete</trigger>
+            <trigger>Anytime — when a story needs its Relevant Wiki section populated or refreshed</trigger>
+        </runs-after>
+        <use-when>
+            <condition>Story has sections 1-8 complete but no Relevant Wiki section</condition>
+            <condition>Story scope changed and wiki references need re-evaluation</condition>
+            <condition>Called as part of /ace:plan-story pipeline (pass 2)</condition>
+        </use-when>
+    </execution-time>
+
+    <input>
+        <flags>
+        </flags>
+
+        <parameters>
+            <required>
+                <param name="story" type="file | github-url">
+                    Story source — can be either:
+                    - **File path**: Path to a markdown file containing the story (from plan-story command)
+                    - **GitHub URL or issue number**: GitHub story reference
+                    Must be a valid, accessible file or GitHub issue.
+                    Contains the user story, description, and acceptance criteria.
+                    **The story's requirements define which wiki docs are relevant.**
+                    If not valid, stop and prompt the user.
+                </param>
+            </required>
+        </parameters>
+    </input>
+
+    <execution-context>
+        <!-- All supporting files are auto-loaded in the Supporting Resources section above.
+             The model does NOT need to Read these files — they are already in context. -->
+    </execution-context>
+
+    <output>
+        <objective>
+            Research the project's engineering wiki to identify documents that are
+            directly relevant to implementing this story. The output is a curated
+            `## Relevant Wiki` section that gets written into the story file
+            (and GitHub issue if applicable).
+
+            This section serves as the implementation context index — when an agent
+            starts implementing this story, it loads every document listed here.
+
+            The research process:
+            1. ALWAYS curates the four system-wide docs with story-specific reasons
+            2. Identifies affected subsystems from story content and feature context
+            3. Spawns parallel ace-wiki-mapper agents to scan subsystem wiki docs
+            4. Compiles a categorized, deduplicated list of relevant references
+
+            All output is written to the story file — populating the Relevant Wiki
+            section placeholder left by pass 1.
+        </objective>
+
+        <artifacts>
+            Modifies in-place: the story file at
+            .ace/artifacts/product/&lt;id-epic_name&gt;/&lt;id-feature_name&gt;/&lt;id-story_name&gt;/&lt;id-story_name&gt;.md
+            (adds/replaces the ## Relevant Wiki section)
+        </artifacts>
+    </output>
+
+    <process>
+        For this command use the `ace-wiki-mapper` agent
+        that's specialized in wiki exploration and curation.
+
+        Execute the research-story-wiki workflow from
+        `workflow.xml` end-to-end.
+        Preserve all workflow gates (validation, approvals, commits).
+    </process>
+
+    <example-usage>
+        ```