diff --git a/src/core/templates/workflows/apply-change.ts b/src/core/templates/workflows/apply-change.ts
index ec5b59ab1..fb96d9436 100644
--- a/src/core/templates/workflows/apply-change.ts
+++ b/src/core/templates/workflows/apply-change.ts
@@ -6,13 +6,33 @@
  */
 import type { SkillTemplate, CommandTemplate } from '../types.js';
 
-export function getApplyChangeSkillTemplate(): SkillTemplate {
-  return {
-    name: 'openspec-apply-change',
-    description: 'Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.',
-    instructions: `Implement tasks from an OpenSpec change.
-
-**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+// ── Shared instruction body ───────────────────────────────────────────────────
+// Single source of truth for apply workflow instructions.
+// Parameterized by mode so skill-friendly references and command-specific
+// slash commands (/opsx:*) can differ without duplicating the entire body.
+// See: https://github.com/Fission-AI/OpenSpec/issues/1139
+/**
+ * Returns the apply workflow instruction body for the given mode.
+ * Skill mode uses skill-friendly references (e.g. openspec-continue-change skill).
+ * Command mode uses slash command references (e.g. /opsx:continue, /opsx:archive).
+ */
+function getApplyInstructions(mode: 'skill' | 'command'): string {
+  const continueRef = mode === 'command'
+    ? '`/opsx:continue`'
+    : 'the openspec-continue-change skill';
+  const archiveRef = mode === 'command'
+    ? 'You can archive this change with `/opsx:archive`.'
+    : 'Ready to archive this change.';
+  const inputExample = mode === 'command'
+    ? ' (e.g., `/opsx:apply add-auth`)'
+    : '';
+  const overrideExample = mode === 'command'
+  ? ' (e.g., `/opsx:apply <other>`)'
+  : '';
+
+  return `Implement tasks from an OpenSpec change.
+
+**Input**: Optionally specify a change name${inputExample}. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
 
 **Steps**
 
@@ -23,7 +43,7 @@ export function getApplyChangeSkillTemplate(): SkillTemplate {
    - Auto-select if only one active change exists
    - If ambiguous, run \`openspec list --json\` to get available changes and use the **AskUserQuestion tool** to let the user select
 
-   Always announce: "Using change: <name>" and how to override (e.g., \`/opsx:apply <other>\`).
+   Always announce: "Using change: <name>" and how to override${overrideExample}.
 
 2. **Check status to understand the schema**
    \`\`\`bash
@@ -47,7 +67,7 @@ export function getApplyChangeSkillTemplate(): SkillTemplate {
    - Dynamic instruction based on current state
 
    **Handle states:**
-   - If \`state: "blocked"\` (missing artifacts): show message, suggest using openspec-continue-change
+   - If \`state: "blocked"\` (missing artifacts): show message, suggest using ${continueRef}
    - If \`state: "all_done"\`: congratulate, suggest archive
    - Otherwise: proceed to implementation
 
@@ -119,7 +139,7 @@ Working on task 4/7: <task description>
 - [x] Task 2
 ...
 
-All tasks complete! Ready to archive this change.
+${archiveRef}
 \`\`\`
 
 **Output On Pause (Issue Encountered)**
@@ -157,166 +177,34 @@ What would you like to do?
 This skill supports the "actions on a change" model:
 
 - **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
-- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly`,
+- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly`;
+}
+
+/**
+ * Returns the skill template for the apply-change workflow.
+ * Used by skills-only tools (e.g. Antigravity) via SKILL.md discovery.
+ */
+export function getApplyChangeSkillTemplate(): SkillTemplate {
+  return {
+    name: 'openspec-apply-change',
+    description: 'Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.',
+    instructions: getApplyInstructions('skill'),
     license: 'MIT',
     compatibility: 'Requires openspec CLI.',
     metadata: { author: 'openspec', version: '1.0' },
   };
 }
 
+/**
+ * Returns the command template for the opsx apply workflow.
+ * Used by Claude Code and other command-enabled tools via /opsx:apply.
+ */
 export function getOpsxApplyCommandTemplate(): CommandTemplate {
   return {
     name: 'OPSX: Apply',
     description: 'Implement tasks from an OpenSpec change (Experimental)',
     category: 'Workflow',
     tags: ['workflow', 'artifacts', 'experimental'],
-    content: `Implement tasks from an OpenSpec change.
-
-**Input**: Optionally specify a change name (e.g., \`/opsx:apply add-auth\`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
-
-**Steps**
-
-1. **Select the change**
-
-   If a name is provided, use it. Otherwise:
-   - Infer from conversation context if the user mentioned a change
-   - Auto-select if only one active change exists
-   - If ambiguous, run \`openspec list --json\` to get available changes and use the **AskUserQuestion tool** to let the user select
-
-   Always announce: "Using change: <name>" and how to override (e.g., \`/opsx:apply <other>\`).
-
-2. **Check status to understand the schema**
-   \`\`\`bash
-   openspec status --change "<name>" --json
-   \`\`\`
-   Parse the JSON to understand:
-   - \`schemaName\`: The workflow being used (e.g., "spec-driven")
-   - \`planningHome\`, \`changeRoot\`, and \`actionContext\`: planning scope and edit constraints
-   - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
-
-3. **Get apply instructions**
-
-   \`\`\`bash
-   openspec instructions apply --change "<name>" --json
-   \`\`\`
-
-   This returns:
-   - \`contextFiles\`: artifact ID -> array of concrete file paths (varies by schema)
-   - Progress (total, complete, remaining)
-   - Task list with status
-   - Dynamic instruction based on current state
-
-   **Handle states:**
-   - If \`state: "blocked"\` (missing artifacts): show message, suggest using \`/opsx:continue\`
-   - If \`state: "all_done"\`: congratulate, suggest archive
-   - Otherwise: proceed to implementation
-
-   **Workspace guard:** If status JSON reports \`actionContext.mode: "workspace-planning"\` and \`allowedEditRoots\` is empty, explain that full workspace apply is not supported in this slice. Treat linked repos and folders as read-only context, ask the user to select an affected area through an explicit implementation workflow, and STOP before editing files.
-
-4. **Read context files**
-
-   Read every file path listed under \`contextFiles\` from the apply instructions output.
-   The files depend on the schema being used:
-   - **spec-driven**: proposal, specs, design, tasks
-   - Other schemas: follow the contextFiles from CLI output
-
-5. **Show current progress**
-
-   Display:
-   - Schema being used
-   - Progress: "N/M tasks complete"
-   - Remaining tasks overview
-   - Dynamic instruction from CLI
-
-6. **Implement tasks (loop until done or blocked)**
-
-   For each pending task:
-   - Show which task is being worked on
-   - Make the code changes required
-   - Keep changes minimal and focused
-   - Mark task complete in the tasks file: \`- [ ]\` → \`- [x]\`
-   - Continue to next task
-
-   **Pause if:**
-   - Task is unclear → ask for clarification
-   - Implementation reveals a design issue → suggest updating artifacts
-   - Error or blocker encountered → report and wait for guidance
-   - User interrupts
-
-7. **On completion or pause, show status**
-
-   Display:
-   - Tasks completed this session
-   - Overall progress: "N/M tasks complete"
-   - If all done: suggest archive
-   - If paused: explain why and wait for guidance
-
-**Output During Implementation**
-
-\`\`\`
-## Implementing: <change-name> (schema: <schema-name>)
-
-Working on task 3/7: <task description>
-[...implementation happening...]
-✓ Task complete
-
-Working on task 4/7: <task description>
-[...implementation happening...]
-✓ Task complete
-\`\`\`
-
-**Output On Completion**
-
-\`\`\`
-## Implementation Complete
-
-**Change:** <change-name>
-**Schema:** <schema-name>
-**Progress:** 7/7 tasks complete ✓
-
-### Completed This Session
-- [x] Task 1
-- [x] Task 2
-...
-
-All tasks complete! You can archive this change with \`/opsx:archive\`.
-\`\`\`
-
-**Output On Pause (Issue Encountered)**
-
-\`\`\`
-## Implementation Paused
-
-**Change:** <change-name>
-**Schema:** <schema-name>
-**Progress:** 4/7 tasks complete
-
-### Issue Encountered
-<description of the issue>
-
-**Options:**
-1. <option 1>
-2. <option 2>
-3. Other approach
-
-What would you like to do?
-\`\`\`
-
-**Guardrails**
-- Keep going through tasks until done or blocked
-- Always read context files before starting (from the apply instructions output)
-- If task is ambiguous, pause and ask before implementing
-- If implementation reveals issues, pause and suggest artifact updates
-- Keep code changes minimal and scoped to each task
-- Update task checkbox immediately after completing each task
-- Pause on errors, blockers, or unclear requirements - don't guess
-- Use contextFiles from CLI output, don't assume specific file names
-
-**Fluid Workflow Integration**
-
-This skill supports the "actions on a change" model:
-
-- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
-- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly`
+    content: getApplyInstructions('command'),
   };
-}
+}
\ No newline at end of file
diff --git a/test/core/templates/skill-templates-parity.test.ts b/test/core/templates/skill-templates-parity.test.ts
index f851082e5..c658cda75 100644
--- a/test/core/templates/skill-templates-parity.test.ts
+++ b/test/core/templates/skill-templates-parity.test.ts
@@ -33,14 +33,14 @@ const EXPECTED_FUNCTION_HASHES: Record<string, string> = {
   getExploreSkillTemplate: 'e2765fae6c2e960f4ce07058cfdaa547ff3435d454eacd5e924e38139e97ad52',
   getNewChangeSkillTemplate: 'b0c26f0b65380062e586505c08c72230e59dccea89e6acca7b673f01cba70d5a',
   getContinueChangeSkillTemplate: 'fbc6c379ed3dd39f59f52b10584b8df5b1dc08b5422bcf1c6d6255a944d22a11',
-  getApplyChangeSkillTemplate: 'e746f230c2513a5fd40842bde494bb3cdb3c5f7c1bcece101f92090983d4ff55',
+  getApplyChangeSkillTemplate: 'dfea2100cda95078883d047743edef647de584f1c259b10d778a5a5a59c36810',
   getFfChangeSkillTemplate: '50e68fbb49b76d2690b614bffa9e6210e45539fb74419fc2e4311158b6d38485',
   getSyncSpecsSkillTemplate: '9f02b41227db70875b89eefeb275c769142607dc5b2593f4e606794aed2fdbad',
   getOnboardSkillTemplate: '4f4b60fea6e3fc7d2185815b2808fad51535fdd00cd4401b32d1536f32fa2b6d',
   getOpsxExploreCommandTemplate: '4d5e64e3ede6703113cf2fd23b797371ef2407b702478b4f7240fc81cbf2d3a5',
   getOpsxNewCommandTemplate: '757f72e2d9a1a6794b2188704fd39dd2ab65428899b4b361c76cc15a5e4f2ccc',
   getOpsxContinueCommandTemplate: '62f8863edda2bfe4e210f8bc3095fd4369aaaaf7772a5cba9602d0f0bca1d0c9',
-  getOpsxApplyCommandTemplate: '812feefd32a4d9d468e03e456d06e3d2d08d1118d29cce4911f0be59cdd30bfc',
+  getOpsxApplyCommandTemplate: 'b287fea929855c7d8dad05ddc1663475672f143b0ee92eb2da9321497c504123',
   getOpsxFfCommandTemplate: 'f775b242bcfd56594c431c7f31a0129208a1bacfdb2427074d412543072ef7ca',
   getArchiveChangeSkillTemplate: 'bdf022ae2cdef1feef4d641a068bef3a7fc5d98a323f7ce9f77ac578fe8d20c6',
   getBulkArchiveChangeSkillTemplate: 'fdb1715804e86de85be96222b8efeb9d5b350c6d5c19e343e244655deff8e62b',
@@ -59,7 +59,7 @@ const EXPECTED_GENERATED_SKILL_CONTENT_HASHES: Record<string, string> = {
   'openspec-explore': '28d900ef82b325beb65e69ee6435949adcfdf14a4314638e7006e6dc359b92d4',
   'openspec-new-change': 'c99989810f982d72eefc74a35f2282b71f1956f23f61b83aaa58fa3dd921716f',
   'openspec-continue-change': 'c00e2a60f79cd60197094cc59762babe5ee6a2dc1e859a0ede3f436a775ccecf',
-  'openspec-apply-change': 'd849442efd925b9247651e254a5cd696945321610cca5a9432ad420430554548',
+  'openspec-apply-change': 'abee399a8a404c5791850ba5807525ad9cd0501d99e9290202c2dae3b5a0d696',
   'openspec-ff-change': '9d9b1995b6f4adb3da570676f7d11fee4cd1cf6c5df8ec83c033e02783a544df',
   'openspec-sync-specs': '2e0f67ec6fadffc6107b4b1a28eef23a99a6649e5fae706897ea1dd9deb852a8',
   'openspec-archive-change': '8d14af2c8b2e4358308ac9fc14f75db42a4b41a07e175825035852a82479793e',
@@ -169,4 +169,27 @@ describe('skill templates split parity', () => {
       expect(content, dirName).not.toContain('mv openspec/changes');
     }
   });
+
+  it('apply skill and command share the same normalized body', () => {
+    const skillInstructions = getApplyChangeSkillTemplate().instructions;
+    const commandContent = getOpsxApplyCommandTemplate().content;
+
+  function normalize(text: string): string {
+  return text
+    .trim()
+    .replace(/the openspec-continue-change skill/g, 'CONTINUE_REF')
+    .replace(/`\/opsx:continue`/g, 'CONTINUE_REF')
+    .replace(/Ready to archive this change\./g, 'ARCHIVE_REF')
+    .replace(/You can archive this change with `\/opsx:archive`\./g, 'ARCHIVE_REF')
+    .replace(/ \(e\.g\., `\/opsx:apply add-auth`\)/g, '')
+    .replace(/ \(e\.g\., `\/opsx:apply <other>`\)/g, '')
+    .replace(/\s+/g, ' ');
+}
+
+    expect(normalize(skillInstructions)).toBe(normalize(commandContent));
+  });
+  it('generated apply skill does not contain /opsx: references', () => {
+    const skillInstructions = getApplyChangeSkillTemplate().instructions;
+    expect(skillInstructions).not.toContain('/opsx:');
+  });
 });