ma-agents 3.4.9 → 3.5.0

package/skills/generate-backlog/SKILL.md

@@ -0,0 +1,178 @@
+# Generate Backlog
+
+Generate or refresh the `backlog` section of `sprint-status.yaml` from epics and bug story files, while preserving existing sprint assignments and priorities.
+
+## Purpose
+
+This skill reads `epics.md` and `bug-*.md` files and writes the `backlog` and `epics` sections of `sprint-status.yaml`. The `sprints` section is preserved unchanged. This implements the single-source-of-truth model: all unassigned stories and bugs live in the `backlog` section of the unified file rather than a separate `backlog.yaml`.
+
+**Output target:** `_bmad-output/implementation-artifacts/sprint-status.yaml` (`backlog` and `epics` sections only)
+**Never writes:** A standalone `backlog.yaml` file.
+
+---
+
+<workflow>
+
+<step n="1" goal="Load existing sprint-status.yaml state">
+  <action>Check whether `_bmad-output/implementation-artifacts/sprint-status.yaml` exists</action>
+  <check if="file does not exist">
+    <output>ERROR: `sprint-status.yaml` not found. Run `/bmad-sprint-planning` first to bootstrap the file before using `generate-backlog`.</output>
+    <action>Exit workflow</action>
+  </check>
+  <action>Read `_bmad-output/implementation-artifacts/sprint-status.yaml`</action>
+  <action>Parse the `sprints` section (map keyed by sprint-N). For each sprint, collect all item IDs from the sprint's `items` array. Build {{sprint_item_ids}} = flat set of all item IDs across ALL sprints (across all sprint statuses: planning, active, closed).</action>
+  <action>Parse the `backlog` section (array). Build {{existing_backlog_map}} = map from item ID to the full item object (to preserve priority and status during merge).</action>
+  <action>Preserve the top-level metadata fields: {{generated}}, {{project}}, {{project_key}}, {{tracking_system}}, {{story_location}}</action>
+  <action>Preserve the full {{sprints}} section verbatim (will be passed through unchanged on write)</action>
+  <action>Preserve the existing {{epics}} section for status/retrospective merge later</action>
+</step>
+
+<step n="2" goal="Build done-items exclusion set from done/ archive">
+  <action>Glob `_bmad-output/implementation-artifacts/done/*.md` to discover archived story files</action>
+  <action>For each file found, derive the item ID from the filename (strip `.md` extension, use basename)</action>
+  <action>Build {{done_item_ids}} = set of all archived item IDs</action>
+  <check if="no done/ files found">
+    <action>Set {{done_item_ids}} = empty set</action>
+  </check>
+</step>
+
+<step n="3" goal="Extract stories from epics.md">
+  <action>Read `_bmad-output/planning-artifacts/epics.md`</action>
+  <check if="file does not exist">
+    <output>WARNING: `epics.md` not found at `_bmad-output/planning-artifacts/epics.md`. No stories will be extracted from epics. Continuing with bug-only backlog.</output>
+    <action>Set {{epic_stories}} = [] and {{parsed_epics}} = []</action>
+  </check>
+  <action>Parse epics.md to extract:
+    - Each epic: epic number (N from "Epic N" header), epic title, epic status (if present in the file)
+    - Each story under each epic: story number (M from "Story N.M" format), story title
+  </action>
+  <action>For each story, generate the kebab-case item ID: `{epic_number}-{story_number}-{title-slug}` where title-slug is the title lowercased, spaces replaced with hyphens, non-alphanumeric characters (except hyphens) removed, consecutive hyphens collapsed</action>
+  <action>Exclude stories whose derived ID is in {{sprint_item_ids}} (already assigned to a sprint)</action>
+  <action>Exclude stories whose derived ID is in {{done_item_ids}} (archived)</action>
+  <action>Store remaining stories as {{epic_stories}} — list of objects with: id, epic (integer), title, type="story", severity=null</action>
+  <action>Store parsed epics as {{parsed_epics}} — list of objects with: epic_id (e.g., "epic-5"), epic_number (integer), title</action>
+</step>
+
+<step n="4" goal="Extract bugs from bug-*.md files">
+  <action>Glob `_bmad-output/implementation-artifacts/bug-*.md` to discover all bug story files</action>
+  <check if="no bug files found">
+    <action>Set {{bug_stories}} = []</action>
+  </check>
+  <action>For each bug file found:
+    - Parse YAML frontmatter to extract: `id` (or derive from filename: `BUG-{basename-without-bug-prefix-and-extension}`), `title`, `severity` (critical/high/medium/low), `status`
+    - If `id` is not in frontmatter, derive from filename: strip `bug-` prefix and `.md` extension, prefix with `BUG-`
+    - If `status` is not in frontmatter, default to `backlog`
+    - Exclude bugs whose ID is in {{sprint_item_ids}} or {{done_item_ids}}
+    - Create bug item: {id, type="bug", epic=null, title, severity, status}
+  </action>
+  <action>Store as {{bug_stories}}</action>
+</step>
+
+<step n="5" goal="Merge with existing backlog — preserve priorities, detect orphans">
+  <action>Build {{all_source_ids}} = set of all IDs from {{epic_stories}} + {{bug_stories}}</action>
+
+  <action>**Orphan detection:** For each item in {{existing_backlog_map}} whose ID is NOT in {{all_source_ids}} AND NOT in {{sprint_item_ids}} AND NOT in {{done_item_ids}}:
+    - Flag the item as orphaned
+    - Collect orphaned items in {{orphaned_items}} list
+    - Keep the orphaned item in the backlog (do NOT auto-remove — human review required)
+  </action>
+
+  <action>**New item detection:** For each item in {{epic_stories}} and {{bug_stories}} whose ID is NOT in {{existing_backlog_map}}:
+    - Assign status = "backlog"
+    - Mark as new in {{new_items}} list
+  </action>
+
+  <action>**Existing item preservation:** For each item in {{epic_stories}} and {{bug_stories}} whose ID IS in {{existing_backlog_map}}:
+    - Preserve the existing item's `priority` and `status` values from {{existing_backlog_map}}
+    - Update title from the source file (in case it was renamed)
+  </action>
+
+  <action>Assemble {{merged_items}} = all items from {{epic_stories}} (with preserved or new priority/status) + all items from {{bug_stories}} (with preserved or new priority/status) + all items from {{orphaned_items}} (with existing priority/status preserved)</action>
+
+  <action>**Backlog-sprint conflict detection:** Set {{backlog_sprint_conflicts}} = list of items that were in {{existing_backlog_map}} AND in {{sprint_item_ids}} (items found in both the backlog and a sprint — data integrity violation corrected by removing them from the backlog; sprint assignment takes precedence)</action>
+</step>
+
+<step n="6" goal="Sort and renumber backlog items by priority">
+  <action>Sort {{merged_items}} by the following criteria (most important first):
+    1. **Critical bugs first:** Items with type="bug" AND severity="critical" rank highest
+       - Among critical bugs: existing items ordered by their current priority (ascending); new critical bugs ordered by their position in the discovered bug file list (alphabetical by filename)
+    2. **Explicit priority (preserved from existing backlog):** Items that existed in the previous backlog are ranked by their preserved priority value (lower number = higher rank)
+    3. **New items by epic order:** New items (not in existing backlog) are ranked by their epic number (ascending), then by story number within the epic (ascending)
+    4. **Bugs without explicit priority:** New bugs (not in existing backlog) are appended after all stories, sorted by severity (high → medium → low → null)
+    5. **Orphaned items:** Orphaned items are appended last, maintaining their relative order
+  </action>
+  <action>Re-number priorities sequentially: assign priority = 1 to the first item, priority = 2 to the second, etc. (position 0 in array = priority 1)</action>
+  <action>Store as {{sorted_backlog}}</action>
+</step>
+
+<step n="7" goal="Build refreshed epics section">
+  <action>For each epic in {{parsed_epics}}:
+    - Look up the epic in the existing {{epics}} section by key (e.g., "epic-5")
+    - If the epic already exists: preserve its `status` and `retrospective` values. Do NOT downgrade status (e.g., if existing status is "in-progress" and the source implies "backlog", keep "in-progress").
+    - If the epic is new (not in existing epics): set status = "backlog", retrospective = "optional"
+  </action>
+  <action>Build {{refreshed_epics}} = map of all epics from the existing file PLUS any newly discovered epics. Existing epics not present in parsed_epics are preserved unchanged (do not remove epics that are no longer in the source, as they may be in-progress or done).</action>
+</step>
+
+<step n="8" goal="Write sprint-status.yaml atomically">
+  <action>Assemble the complete file content:
+    1. Preserve top-level metadata: `generated`, `project`, `project_key`, `tracking_system`, `story_location` (unchanged)
+    2. Set `last_updated` = current ISO-8601 datetime string (e.g., "2026-04-06T10:00:00Z")
+    3. Write `epics` section from {{refreshed_epics}}
+    4. Write `backlog` section from {{sorted_backlog}} (array, ordered by priority)
+    5. Write `sprints` section from the preserved {{sprints}} section (verbatim, NO changes)
+  </action>
+  <action>Validate before writing:
+    - Every backlog item has all 7 required fields: id, type, epic, title, priority, status, severity
+    - priority values are sequential starting from 1 and match array position
+    - No item ID appears in both backlog and any sprint's items array
+    - Every epic has both status and retrospective fields
+  </action>
+  <action>Write the assembled content to `_bmad-output/implementation-artifacts/sprint-status.yaml` as a single atomic write (read-modify-write pattern)</action>
+</step>
+
+<step n="9" goal="Report summary">
+  <output>
+## Generate Backlog — Complete
+
+**Backlog section refreshed in `sprint-status.yaml`**
+
+| Metric | Count |
+|--------|-------|
+| Total stories from epics.md | {{epic_story_count}} |
+| Total bugs from bug-*.md | {{bug_count}} |
+| New items added to backlog | {{new_items_count}} |
+| Existing items preserved | {{preserved_count}} |
+| Items excluded (sprint-assigned) | {{sprint_excluded_count}} |
+| Items excluded (archived in done/) | {{done_excluded_count}} |
+| Items corrected (removed from backlog — already in sprint) | {{backlog_sprint_conflicts.length}} |
+| Total backlog items | {{total_backlog_count}} |
+
+{{#if backlog_sprint_conflicts}}
+⚠️ **Data integrity corrections:**
+The following items were found in both the backlog and a sprint. They have been removed from the backlog (sprint assignment takes precedence):
+{{#each backlog_sprint_conflicts}}
+- {{id}} — {{title}}
+{{/each}}
+
+{{/if}}
+{{#if orphaned_items}}
+### Orphaned Items (WARNING — Human Review Required)
+
+The following items exist in the backlog but were NOT found in `epics.md` or any `bug-*.md` file. They have been kept in the backlog but should be reviewed:
+
+{{#each orphaned_items}}
+- `{{id}}` — {{title}} (priority: {{priority}}, status: {{status}})
+{{/each}}
+
+These items may represent: renamed stories, deleted epics, or manually added items. Remove them manually if they are no longer needed.
+{{/if}}
+
+**Next steps:**
+- Use `/prioritize-backlog` to reorder items
+- Use `/add-to-sprint` to assign items to a sprint
+- Use `/bmad-sprint-planning` to plan a full sprint
+  </output>
+</step>
+
+</workflow>

package/skills/generate-backlog/skill.json

@@ -0,0 +1,7 @@
+{
+  "name": "generate-backlog",
+  "version": "1.0.0",
+  "description": "Generate or refresh the backlog section of sprint-status.yaml from epics and bug stories, preserving existing priorities and sprint assignments",
+  "category": "workflow",
+  "tags": ["backlog", "sprint-management", "epics", "bugs"]
+}

package/skills/modify-sprint/SKILL.md

@@ -0,0 +1,302 @@
+# Modify Sprint Skill
+
+Guided workflow to modify an existing sprint's metadata (name, capacity, dates, status) within the `sprints` section of `sprint-status.yaml`.
+
+> **Scope:** This skill modifies sprint **metadata only** — name, capacity, start date, end date, and status.
+> To assign items to a sprint, use `/add-to-sprint`. To remove items, use `/remove-from-sprint`.
+
+<workflow>
+
+<step n="0" goal="Load configuration and validate file existence">
+  <action>Locate `sprint-status.yaml` at `_bmad-output/implementation-artifacts/sprint-status.yaml`</action>
+  <check if="file does not exist">
+    <output>No sprint-status.yaml found. Run sprint planning first to initialize the file.</output>
+    <action>Exit workflow</action>
+  </check>
+  <action>Read and parse the full file, retaining all three sections: `epics`, `backlog`, and `sprints`</action>
+  <action>Store file contents as {{file_content}} for use in the final atomic write</action>
+</step>
+
+<step n="1" goal="Identify available sprints and select one to modify">
+  <action>Parse the `sprints` section from the loaded file</action>
+  <check if="sprints section is empty ({})">
+    <output>No sprints found. Run `/add-sprint` first to create a sprint.</output>
+    <action>Exit workflow</action>
+  </check>
+  <action>Build sprint list with: sprint ID (map key), name, status, capacity, item count (length of items array), start, end</action>
+  <output>
+## Available Sprints
+
+| # | Sprint ID | Name | Status | Capacity | Items | Start | End |
+|---|---|---|---|---|---|---|---|
+{{#each sprints}}
+| {{@index+1}} | {{sprint_id}} | {{name}} | {{status}} | {{capacity}} | {{item_count}}/{{capacity}} | {{start_or_not_set}} | {{end_or_not_set}} |
+{{/each}}
+
+Note: closed sprints are immutable and cannot be modified.
+  </output>
+  <ask>Select sprint to modify (enter number):</ask>
+  <action>Store selected sprint as {{target_sprint}} and its map key as {{sprint_id}}</action>
+  <check if="{{target_sprint.status}} == 'closed'">
+    <output>Sprint '{{target_sprint.name}}' ({{sprint_id}}) is closed. Closed sprints are immutable (schema constraint 6.7). Only archival operations are permitted.</output>
+    <action>Exit workflow</action>
+  </check>
+</step>
+
+<step n="2" goal="Display current sprint state">
+  <action>Calculate {{item_count}} = length of {{target_sprint.items}} array</action>
+  <action>Calculate {{remaining}} = {{target_sprint.capacity}} - {{item_count}}</action>
+  <output>
+## Sprint: {{target_sprint.name}} ({{sprint_id}})
+
+- Status: {{target_sprint.status}}
+- Capacity: {{target_sprint.capacity}} items ({{item_count}} assigned, {{remaining}} remaining)
+- Start: {{target_sprint.start || "not set"}}
+- End: {{target_sprint.end || "not set"}}
+- Items: {{item_count}} assigned (use /add-to-sprint or /remove-from-sprint to manage items)
+
+### Assigned Items (read-only)
+{{#if items_empty}}
+*(No items assigned yet)*
+{{else}}
+| ID | Title | Type | Status |
+|---|---|---|---|
+{{#each target_sprint.items}}
+| {{id}} | {{title}} | {{type}} | {{status}} |
+{{/each}}
+{{/if}}
+  </output>
+  <action>Initialize {{working_changes}} = empty map to accumulate changes made during this session</action>
+  <action>Initialize working state aliases: {{current_name}} = {{target_sprint.name}}, {{current_capacity}} = {{target_sprint.capacity}}, {{current_start}} = {{target_sprint.start}}, {{current_end}} = {{target_sprint.end}}, {{current_status}} = {{target_sprint.status}}. These aliases are updated in-place as changes are made so Step 3's menu always shows the latest values.</action>
+  <action>Store {{original_name}} = {{target_sprint.name}} (preserved as the display name in the confirmation summary)</action>
+</step>
+
+<step n="3" goal="Present modification menu">
+  <output>
+## What would you like to modify?
+
+1. Sprint name (current: "{{current_name}}")
+2. Capacity (current: {{current_capacity}})
+3. Start date (current: {{current_start || "not set"}})
+4. End date (current: {{current_end || "not set"}})
+5. Status (current: {{current_status}})
+6. Done -- save all changes and exit
+  </output>
+  <ask>Choice:</ask>
+  <check if="choice == 6 or choice == 'done'">
+    <goto step="4" />
+  </check>
+</step>
+
+<step n="3a" goal="Modify sprint name" if="choice == 1">
+  <ask>New sprint name (current: '{{current_name}}'):</ask>
+  <check if="input is empty">
+    <output>Sprint name cannot be empty. Please enter a valid name.</output>
+    <goto step="3a" />
+  </check>
+  <action>Store {{new_name}} = input</action>
+  <action>Store change: name: {{current_name}} -> {{new_name}} in {{working_changes}}</action>
+  <action>Update current display value: {{current_name}} = {{new_name}}</action>
+  <output>Sprint name updated: '{{old_name}}' -> '{{new_name}}'.</output>
+  <goto step="3" />
+</step>
+
+<step n="3b" goal="Modify capacity" if="choice == 2">
+  <ask>New capacity (positive integer, current: {{current_capacity}}):</ask>
+  <action>Validate input is a positive integer (greater than zero, no decimals, no non-numeric characters)</action>
+  <check if="input is NOT a positive integer">
+    <output>Invalid capacity. Must be a positive integer greater than zero.</output>
+    <goto step="3b" />
+  </check>
+  <action>Store {{new_capacity}} = validated integer input</action>
+  <action>Calculate {{item_count}} = length of {{target_sprint.items}} array</action>
+  <check if="{{new_capacity}} < {{item_count}}">
+    <output>Sprint has {{item_count}} items but new capacity would be {{new_capacity}} ({{new_capacity}} < {{item_count}}). Capacity is advisory -- items will not be removed.</output>
+    <ask>Options:
+- [a] Apply anyway (capacity is advisory per schema section 4.2)
+- [s] Skip -- keep current capacity
+- [r] Remove items first (direct to /remove-from-sprint)
+
+Choice:</ask>
+    <check if="choice == 's'">
+      <goto step="3" />
+    </check>
+    <check if="choice == 'r'">
+      <output>Run `/remove-from-sprint` to remove items, then re-run `/modify-sprint`.</output>
+      <action>Exit workflow</action>
+    </check>
+    <!-- if 'a', proceed with the change -->
+  </check>
+  <action>Calculate {{new_remaining}} = {{new_capacity}} - {{item_count}}</action>
+  <action>Store change: capacity: {{current_capacity}} -> {{new_capacity}} in {{working_changes}}</action>
+  <action>Update current display value: {{current_capacity}} = {{new_capacity}}</action>
+  <output>Capacity updated: {{old_capacity}} -> {{new_capacity}} ({{new_remaining}} slots remaining with {{item_count}} assigned items).</output>
+  <goto step="3" />
+</step>
+
+<step n="3c" goal="Modify start date" if="choice == 3">
+  <ask>New start date (ISO format YYYY-MM-DD, or press Enter to clear):</ask>
+  <check if="input is empty">
+    <action>Store {{new_start}} = "" (clears the date)</action>
+  </check>
+  <check if="input is not empty">
+    <action>Validate input matches ISO date format YYYY-MM-DD (regex: ^\d{4}-\d{2}-\d{2}$) and represents a valid calendar date</action>
+    <check if="invalid format">
+      <output>Invalid date format. Use YYYY-MM-DD (e.g., 2026-05-01).</output>
+      <goto step="3c" />
+    </check>
+    <action>Store {{new_start}} = input</action>
+  </check>
+  <action>Store change: start: {{current_start || "not set"}} -> {{new_start || "not set"}} in {{working_changes}}</action>
+  <action>Update current display value: {{current_start}} = {{new_start}}</action>
+  <output>Start date updated: '{{old_start || "not set"}}' -> '{{new_start || "not set"}}'.</output>
+  <goto step="3" />
+</step>
+
+<step n="3d" goal="Modify end date" if="choice == 4">
+  <ask>New end date (ISO format YYYY-MM-DD, or press Enter to clear):</ask>
+  <check if="input is empty">
+    <action>Store {{new_end}} = "" (clears the date)</action>
+  </check>
+  <check if="input is not empty">
+    <action>Validate input matches ISO date format YYYY-MM-DD (regex: ^\d{4}-\d{2}-\d{2}$) and represents a valid calendar date</action>
+    <check if="invalid format">
+      <output>Invalid date format. Use YYYY-MM-DD (e.g., 2026-05-31).</output>
+      <goto step="3d" />
+    </check>
+    <action>Store {{new_end}} = input</action>
+  </check>
+  <action>Determine effective start: use {{current_start}} if not changed, else use newly entered start</action>
+  <check if="{{new_end}} is not empty AND {{effective_start}} is not empty AND {{new_end}} < {{effective_start}}">
+    <output>Warning: End date ({{new_end}}) is before start date ({{effective_start}}). This may be intentional.</output>
+  </check>
+  <action>Store change: end: {{current_end || "not set"}} -> {{new_end || "not set"}} in {{working_changes}}</action>
+  <action>Update current display value: {{current_end}} = {{new_end}}</action>
+  <output>End date updated: '{{old_end || "not set"}}' -> '{{new_end || "not set"}}'.</output>
+  <goto step="3" />
+</step>
+
+<step n="3e" goal="Modify status" if="choice == 5">
+  <action>Determine valid transitions based on {{current_status}}:
+    - If `planning`: valid next state is `active` only
+    - If `active`: valid next state is `closed` only
+    - If `closed`: no transitions available (immutable)
+  </action>
+  <output>
+Current status: {{current_status}}
+{{#if current_status == 'planning'}}Valid transitions: planning -> active{{/if}}
+{{#if current_status == 'active'}}Valid transitions: active -> closed{{/if}}
+{{#if current_status == 'closed'}}No transitions available. Closed sprints are immutable.{{/if}}
+  </output>
+  <check if="{{current_status}} == 'closed'">
+    <output>Sprint '{{current_name}}' is closed. Closed sprints are immutable (schema constraint 6.7). Only archival operations are permitted.</output>
+    <goto step="3" />
+  </check>
+  <ask>New status:</ask>
+  <action>Validate transition:
+    - planning -> active: allowed (proceed to single-active-sprint check)
+    - active -> closed: allowed (with warning about /close-sprint)
+    - planning -> closed: REJECTED (skip)
+    - active -> planning: REJECTED (backward)
+    - closed -> anything: REJECTED (immutable -- already handled above)
+    - same state -> same state: REJECTED (no change)
+    - any unrecognized value: REJECTED
+  </action>
+  <check if="transition is invalid (backward, skip, or unrecognized)">
+    <output>Invalid status transition: {{current_status}} -> {{requested_status}}. Sprint status transitions are forward-only: planning -> active -> closed.</output>
+    <goto step="3e" />
+  </check>
+  <check if="requested_status == 'closed'">
+    <output>Warning: To properly close a sprint with item disposition (archiving done items, returning incomplete items to backlog), use `/close-sprint` instead. This will only update the status field.</output>
+    <ask>Continue with status-only change? [y/n]</ask>
+    <check if="answer == 'n'">
+      <output>Status change cancelled. Use `/close-sprint` for full sprint close lifecycle.</output>
+      <goto step="3" />
+    </check>
+  </check>
+  <check if="requested_status == 'active'">
+    <action>Scan all other sprints in the `sprints` map for any sprint with status: active</action>
+    <check if="another active sprint found">
+      <output>Sprint '{{other_sprint_name}}' ({{other_sprint_id}}) is already active. Only one sprint can be active at a time (schema constraint 6.4). Close it first or cancel this change.</output>
+      <ask>Options:
+- [c] Cancel status change
+- [x] Exit to run /close-sprint on {{other_sprint_id}} first
+
+Choice:</ask>
+      <check if="choice == 'c'">
+        <goto step="3" />
+      </check>
+      <check if="choice == 'x'">
+        <output>Run `/close-sprint` on {{other_sprint_id}} first, then re-run `/modify-sprint`.</output>
+        <action>Exit workflow</action>
+      </check>
+    </check>
+  </check>
+  <action>Store change: status: {{current_status}} -> {{requested_status}} in {{working_changes}}</action>
+  <action>Update current display value: {{current_status}} = {{requested_status}}</action>
+  <output>Status updated: {{old_status}} -> {{requested_status}}.</output>
+  <goto step="3" />
+</step>
+
+<step n="4" goal="Confirmation -- review and confirm all changes">
+  <check if="{{working_changes}} is empty">
+    <output>No modifications made.</output>
+    <action>Exit workflow</action>
+  </check>
+  <output>
+## Modification Summary -- Please Confirm
+
+Sprint: {{sprint_id}} ("{{original_name}}")
+
+Changes:
+{{#each working_changes}}
+- {{field}}: {{old_value}} -> {{new_value}}
+{{/each}}
+
+All other sprint data (items, other sprints, epics, backlog) will be preserved unchanged.
+  </output>
+  <ask>Confirm changes? [y] Yes / [n] Cancel / [e] Edit more</ask>
+  <check if="choice == 'n'">
+    <output>Changes discarded.</output>
+    <action>Exit workflow</action>
+  </check>
+  <check if="choice == 'e'">
+    <goto step="3" />
+  </check>
+  <!-- if 'y', proceed to Step 5 -->
+</step>
+
+<step n="5" goal="Persist changes to sprint-status.yaml">
+  <action>Re-read `_bmad-output/implementation-artifacts/sprint-status.yaml` to get the latest file state before writing</action>
+  <action>Locate the target sprint entry at `sprints.{{sprint_id}}` in the re-read file</action>
+  <action>Apply all confirmed changes to the target sprint entry:
+    - If name was changed: update `name` field
+    - If capacity was changed: update `capacity` field
+    - If start was changed: update `start` field
+    - If end was changed: update `end` field
+    - If status was changed: update `status` field
+  </action>
+  <action>Preserve the sprint's `items` array exactly as-is (no modifications)</action>
+  <action>Preserve all other sprint entries in the `sprints` map exactly as-is</action>
+  <action>Preserve the `epics` section exactly as-is</action>
+  <action>Preserve the `backlog` section exactly as-is</action>
+  <action>Preserve the `generated` field exactly as-is (never change)</action>
+  <action>Set `last_updated` to the current ISO-8601 timestamp</action>
+  <action>Write the complete updated file in a single atomic write to `_bmad-output/implementation-artifacts/sprint-status.yaml`</action>
+  <output>
+Sprint modified successfully!
+
+Sprint: {{sprint_name}} ({{sprint_id}})
+{{#each working_changes}}
+- {{field}}: {{new_value}}
+{{/each}}
+
+Next Steps:
+- Use /add-to-sprint to assign backlog items to this sprint
+- Use /remove-from-sprint to remove items from this sprint
+- Use /sprint-status-view to view sprint progress
+- Use /close-sprint to close this sprint when complete
+  </output>
+</step>
+
+</workflow>

package/skills/modify-sprint/skill.json

@@ -0,0 +1,7 @@
+{
+  "name": "modify-sprint",
+  "version": "1.0.0",
+  "description": "Guided workflow to modify an existing sprint's metadata (name, capacity, dates, status) within the sprints section of sprint-status.yaml",
+  "category": "workflow",
+  "tags": ["sprint-management", "modify-sprint", "capacity", "metadata"]
+}