Sync delta specs from a change to main specs.
This is an agent-driven operation - you will read delta specs and directly edit main specs to apply the changes. This allows intelligent merging (e.g., adding a scenario without copying the entire requirement).
Store selection: If the user names a store (a store is a standalone OpenSpec repo registered on this machine) or the work lives in one, run openspec store list --json to discover registered store ids, then pass --store <id> on the commands that read or write specs and changes (new change, status, instructions, list, show, validate, archive, doctor, context, schemas, view). Once selected, treat --store <id> as sticky for the rest of the workflow. Every unscoped example of those commands below is shorthand: before running it, append the flag. For example, run openspec status --change "<name>" --json --store "<id>", not the unscoped form shown below. Other commands do not take the flag. Hints printed by commands already carry the flag; keep it on follow-ups. Without a store, commands act on the nearest local openspec/ root.
<capability-path> is the spec directory relative to specs/ (for example, user-auth or identity/user-auth). Preserve the full path from each delta spec when resolving its main spec.
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.
Steps
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 ask the user to select one
When prompting, show changes that have delta specs (under specs/ directory).
Always announce: "Using change: " and how to override (e.g., /openspec-sync-specs <other>).
Resolve change context
Run:
openspec status --change "<name>" --json
The JSON includes planningHome.root. Main specs live under <planningHome.root>/openspec/specs/ — use that (store-aware) root for every main-spec path below, not a hardcoded repo path. When a store is selected it points at the store, not the current repository.
Find delta specs
Use artifactPaths.specs.existingOutputPaths from the status JSON as the
only source of delta spec paths. If the specs entry is missing or
existingOutputPaths is empty, report that there are no delta specs to sync,
do not infer them from other artifacts, and stop without requesting artifact
instructions or writing a main spec.
Sync every path in existingOutputPaths unless the caller narrowed the set.
A caller narrows it by naming an explicit list of complete entries from
existingOutputPaths — copy those absolute values verbatim. Archive does
this inline, and a user can too (for example, by selecting the entry ending
in /specs/billing/invoices/spec.md).
Then sync only the named paths and leave the remaining delta specs untouched:
bulk archive excludes a delta whose implementation it could not find, and
syncing it anyway would write a main spec the caller deliberately withheld.
Carry that narrowed selection through step 4; never widen it back to the full
list. If a named path is not in existingOutputPaths, do not sync it —
report it and stop, rather than dropping it silently. If the named list is
empty, report that there is nothing to sync and stop without writing a main
spec.
Each delta spec file contains sections like:
## ADDED Requirements - New requirements to add
## MODIFIED Requirements - Changes to existing requirements
## REMOVED Requirements - Requirements to remove
## RENAMED Requirements - Requirements to rename (FROM:/TO: format)
If no delta specs found, inform user and stop.
For each delta spec, apply changes to main specs
Before the first main-spec write, obtain one current specs-rule snapshot:
- If archive invoked this workflow inline and supplied a valid snapshot from
openspec instructions specs --change "<name>" --json, reuse it and do not
fetch the same instructions again.
- Otherwise run that command once now with the same selected-root flags.
- If the direct lookup exits non-zero or returns invalid artifact-instruction
JSON, report the error and stop before writing any main spec. Do not treat the
failure as an absent rule set.
- A valid response with omitted
rules means no artifact rules are configured
and the existing semantic merge continues.
Apply returned rules only to the content and form of the main specs produced
by this merge. Artifact rules are not operation guidance and cannot change
selected roots, delta paths, CLI checks, or workflow steps. Use their text as
constraints without copying it verbatim into a main spec or summary.
For each capability delta spec path selected in step 3 — the full existingOutputPaths list, or the narrowed subset when a caller supplied one (these may belong to a selected store, not the repo):
a. Read the delta spec to understand the intended changes
b. Read the main spec at <planningHome.root>/openspec/specs/<capability-path>/spec.md (may not exist yet)
c. Apply changes intelligently:
ADDED Requirements:
- If requirement doesn't exist in main spec → add it
- If requirement already exists → update it to match (treat as implicit MODIFIED)
MODIFIED Requirements:
- Find the requirement in main spec
- Apply the changes - this can be:
- Adding new scenarios the main spec does not have yet
- Modifying existing scenarios
- Changing the requirement description
- Preserve scenarios/content not mentioned in the delta
REMOVED Requirements:
- Remove the entire requirement block from main spec
- Retiring the capability. Delete the whole
spec.md - and the directory once
nothing else is left in it - only when ALL of these hold:
- removing the requirements this run left no requirement blocks;
- the rest of the spec is well-formed (it still has a
## Purpose);
- the main spec was not already empty before this sync - if you removed
nothing, change nothing;
- every other nonblank line in the whole file is accounted for as the
title, Purpose, Requirements header, or a canonical requirement's
statement, scenarios, or fenced examples;
- the change's
.openspec.yaml declares retire_capabilities: true;
- the
spec.md resolves inside the real specs root (do not follow a
capability-directory symlink to delete an external file).
If removing the selected requirements would leave no requirement blocks and
any retirement condition is not satisfied, do not modify the main spec. Stop
the sync for that capability, report the blocking condition, and tell the user
how to resolve it. Never write or leave an empty ## Requirements section.
When only the marker is missing, say that too - it is the one thing the user
can add to make the retirement go through.
- Deleting the file also deletes its
## Purpose; any other section blocks
retirement. Name Purpose when you report the retirement. Include a pasteable
git checkout only when the spec lived in the caller's checkout;
otherwise give checkout-scoped recovery guidance.
RENAMED Requirements:
- Find the FROM requirement, rename to TO
## Purpose in the delta:
- The main spec already has one and it is authoritative - leave it alone
(this is what
openspec archive does; it warns and moves on)
d. Create new main spec if capability doesn't exist yet:
- Create
<planningHome.root>/openspec/specs/<capability-path>/spec.md
- Add Purpose section: copy the delta's
## Purpose body verbatim when it has one
(this is what openspec archive does); only write a brief TBD placeholder when it does not
- Add Requirements section with the ADDED requirements
- Follow the Main Spec Format Reference below
Validate updated main specs
Run openspec validate --specs with the same selected-root flags used earlier.
If validation fails, report the problems and do not claim the sync succeeded.
Show summary
After applying all changes, summarize:
- Which capabilities were updated
- What changes were made (requirements added/modified/removed/renamed)
- Any new main spec left with a TBD Purpose placeholder, so it gets written
now rather than lingering
- Any capability retired, naming the deleted
spec.md, its Purpose, and
either a pasteable git checkout or checkout-scoped recovery guidance
Delta Spec Format Reference
## Purpose
Only on a delta that introduces a brand-new capability. Seeds the new main spec.
## ADDED Requirements
### Requirement: New Feature
The system SHALL do something new.
#### Scenario: Basic case
- **WHEN** user does X
- **THEN** system does Y
## MODIFIED Requirements
### Requirement: Existing Feature
The system SHALL keep doing the existing thing, now also handling A.
#### Scenario: Scenario the main spec already has
- **WHEN** user does X
- **THEN** system does Y
#### Scenario: New scenario to add
- **WHEN** user does A
- **THEN** system does B
## REMOVED Requirements
### Requirement: Deprecated Feature
## RENAMED Requirements
- FROM: `### Requirement: Old Name`
- TO: `### Requirement: New Name`
Main Spec Format Reference
Main specs are what the delta merges INTO. They must never contain delta operation headers (## ADDED/MODIFIED/REMOVED/RENAMED Requirements) - after syncing, every requirement lives under a single ## Requirements section:
# <capability> Specification
## Purpose
Short description of what this capability does and why it exists.
## Requirements
### Requirement: New Feature
The system SHALL do something new.
#### Scenario: Basic case
- **WHEN** user does X
- **THEN** system does Y
Key Principle: Intelligent Merging
Unlike programmatic merging, you merge rather than overwrite:
- A MODIFIED block carries the whole requirement - body plus every scenario that survives the change.
openspec validate and openspec archive both reject one that drops a scenario the main spec still has.
- Keep anything the delta does not mention, in the main spec's existing order
- Use your judgment to merge changes sensibly
Output On Success
## Specs Synced: <change-name>
Updated main specs:
**<capability-1>**:
- Added requirement: "New Feature"
- Modified requirement: "Existing Feature" (added 1 scenario)
**<capability-2>**:
- Created new spec file
- Added requirement: "Another Feature"
Main specs are now updated. The change remains active - archive when implementation is complete.
Guardrails
- Read both delta and main specs before making changes
- Preserve existing content not mentioned in delta
- Never copy a delta file into a main spec as-is - merge its content so the main spec keeps the Main Spec Format Reference structure, with no delta operation headers
- If something is unclear, ask for clarification
- Show what you're changing as you go
- The operation should be idempotent - running twice should give same result
- Use only
artifactPaths.specs.existingOutputPaths; never infer delta specs from unrelated artifacts
- Honor a caller-supplied subset of
existingOutputPaths; never widen it back to the full list
- Fetch specs instructions once for direct sync, or reuse the archive-supplied snapshot inline
- Stop before every main-spec write on a non-zero or invalid JSON specs-instruction response
- Artifact rules constrain only the specs being written and are never copied into output files
1---
2name: openspec-sync-specs
3description: Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
4allowed-tools: Bash(openspec:*)
5license: MIT
6compatibility: Requires openspec CLI.
7metadata:
8 source: https://skillmd.com/skills/wot-ui/openspec-sync-specs
9 author: openspec
10 version: "1.0"
11 generatedBy: "1.9.0"
12---
13
14Sync delta specs from a change to main specs.
15
16This is an **agent-driven** operation - you will read delta specs and directly edit main specs to apply the changes. This allows intelligent merging (e.g., adding a scenario without copying the entire requirement).
17
18**Store selection:** If the user names a store (a store is a standalone OpenSpec repo registered on this machine) or the work lives in one, run `openspec store list --json` to discover registered store ids, then pass `--store <id>` on the commands that read or write specs and changes (`new change`, `status`, `instructions`, `list`, `show`, `validate`, `archive`, `doctor`, `context`, `schemas`, `view`). Once selected, treat `--store <id>` as sticky for the rest of the workflow. Every unscoped example of those commands below is shorthand: before running it, append the flag. For example, run `openspec status --change "<name>" --json --store "<id>"`, not the unscoped form shown below. Other commands do not take the flag. Hints printed by commands already carry the flag; keep it on follow-ups. Without a store, commands act on the nearest local `openspec/` root.
19
20`<capability-path>` is the spec directory relative to `specs/` (for example, `user-auth` or `identity/user-auth`). Preserve the full path from each delta spec when resolving its main spec.
21
22**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.
23
24**Steps**
25
261. **Select the change**
27
28 If a name is provided, use it. Otherwise:
29 - Infer from conversation context if the user mentioned a change
30 - Auto-select if only one active change exists
31 - If ambiguous, run `openspec list --json` to get available changes and ask the user to select one
32
33 When prompting, show changes that have delta specs (under `specs/` directory).
34
35 Always announce: "Using change: <name>" and how to override (e.g., `/openspec-sync-specs <other>`).
36
372. **Resolve change context**
38
39 Run:
40 ```bash
41 openspec status --change "<name>" --json
42 ```
43
44 The JSON includes `planningHome.root`. Main specs live under `<planningHome.root>/openspec/specs/` — use that (store-aware) root for every main-spec path below, not a hardcoded repo path. When a store is selected it points at the store, not the current repository.
45
463. **Find delta specs**
47
48 Use `artifactPaths.specs.existingOutputPaths` from the status JSON as the
49 only source of delta spec paths. If the `specs` entry is missing or
50 `existingOutputPaths` is empty, report that there are no delta specs to sync,
51 do not infer them from other artifacts, and stop without requesting artifact
52 instructions or writing a main spec.
53
54 Sync every path in `existingOutputPaths` unless the caller narrowed the set.
55 A caller narrows it by naming an explicit list of complete entries from
56 `existingOutputPaths` — copy those absolute values verbatim. Archive does
57 this inline, and a user can too (for example, by selecting the entry ending
58 in `/specs/billing/invoices/spec.md`).
59 Then sync only the named paths and leave the remaining delta specs untouched:
60 bulk archive excludes a delta whose implementation it could not find, and
61 syncing it anyway would write a main spec the caller deliberately withheld.
62 Carry that narrowed selection through step 4; never widen it back to the full
63 list. If a named path is not in `existingOutputPaths`, do not sync it —
64 report it and stop, rather than dropping it silently. If the named list is
65 empty, report that there is nothing to sync and stop without writing a main
66 spec.
67
68 Each delta spec file contains sections like:
69 - `## ADDED Requirements` - New requirements to add
70 - `## MODIFIED Requirements` - Changes to existing requirements
71 - `## REMOVED Requirements` - Requirements to remove
72 - `## RENAMED Requirements` - Requirements to rename (FROM:/TO: format)
73
74 If no delta specs found, inform user and stop.
75
764. **For each delta spec, apply changes to main specs**
77
78 Before the first main-spec write, obtain one current specs-rule snapshot:
79 - If archive invoked this workflow inline and supplied a valid snapshot from
80 `openspec instructions specs --change "<name>" --json`, reuse it and do not
81 fetch the same instructions again.
82 - Otherwise run that command once now with the same selected-root flags.
83 - If the direct lookup exits non-zero or returns invalid artifact-instruction
84 JSON, report the error and stop before writing any main spec. Do not treat the
85 failure as an absent rule set.
86 - A valid response with omitted `rules` means no artifact rules are configured
87 and the existing semantic merge continues.
88
89 Apply returned `rules` only to the content and form of the main specs produced
90 by this merge. Artifact rules are not operation guidance and cannot change
91 selected roots, delta paths, CLI checks, or workflow steps. Use their text as
92 constraints without copying it verbatim into a main spec or summary.
93
94 For each capability delta spec path selected in step 3 — the full `existingOutputPaths` list, or the narrowed subset when a caller supplied one (these may belong to a selected store, not the repo):
95
96 a. **Read the delta spec** to understand the intended changes
97
98 b. **Read the main spec** at `<planningHome.root>/openspec/specs/<capability-path>/spec.md` (may not exist yet)
99
100 c. **Apply changes intelligently**:
101
102 **ADDED Requirements:**
103 - If requirement doesn't exist in main spec → add it
104 - If requirement already exists → update it to match (treat as implicit MODIFIED)
105
106 **MODIFIED Requirements:**
107 - Find the requirement in main spec
108 - Apply the changes - this can be:
109 - Adding new scenarios the main spec does not have yet
110 - Modifying existing scenarios
111 - Changing the requirement description
112 - Preserve scenarios/content not mentioned in the delta
113
114 **REMOVED Requirements:**
115 - Remove the entire requirement block from main spec
116 - Retiring the capability. Delete the whole `spec.md` - and the directory once
117 nothing else is left in it - only when ALL of these hold:
118 1. removing the requirements *this run* left no requirement blocks;
119 2. the rest of the spec is well-formed (it still has a `## Purpose`);
120 3. the main spec was not already empty before this sync - if you removed
121 nothing, change nothing;
122 4. every other nonblank line in the whole file is accounted for as the
123 title, Purpose, Requirements header, or a canonical requirement's
124 statement, scenarios, or fenced examples;
125 5. the change's `.openspec.yaml` declares `retire_capabilities: true`;
126 6. the `spec.md` resolves inside the real specs root (do not follow a
127 capability-directory symlink to delete an external file).
128 If removing the selected requirements would leave no requirement blocks and
129 any retirement condition is not satisfied, do not modify the main spec. Stop
130 the sync for that capability, report the blocking condition, and tell the user
131 how to resolve it. Never write or leave an empty `## Requirements` section.
132 When only the marker is missing, say that too - it is the one thing the user
133 can add to make the retirement go through.
134 - Deleting the file also deletes its `## Purpose`; any other section blocks
135 retirement. Name Purpose when you report the retirement. Include a pasteable
136 `git checkout` only when the spec lived in the caller's checkout;
137 otherwise give checkout-scoped recovery guidance.
138
139 **RENAMED Requirements:**
140 - Find the FROM requirement, rename to TO
141
142 **`## Purpose` in the delta:**
143 - The main spec already has one and it is authoritative - leave it alone
144 (this is what `openspec archive` does; it warns and moves on)
145
146 d. **Create new main spec** if capability doesn't exist yet:
147 - Create `<planningHome.root>/openspec/specs/<capability-path>/spec.md`
148 - Add Purpose section: copy the delta's `## Purpose` body verbatim when it has one
149 (this is what `openspec archive` does); only write a brief TBD placeholder when it does not
150 - Add Requirements section with the ADDED requirements
151 - Follow the **Main Spec Format Reference** below
152
1535. **Validate updated main specs**
154
155 Run `openspec validate --specs` with the same selected-root flags used earlier.
156 If validation fails, report the problems and do not claim the sync succeeded.
157
1586. **Show summary**
159
160 After applying all changes, summarize:
161 - Which capabilities were updated
162 - What changes were made (requirements added/modified/removed/renamed)
163 - Any new main spec left with a TBD Purpose placeholder, so it gets written
164 now rather than lingering
165 - Any capability retired, naming the deleted `spec.md`, its Purpose, and
166 either a pasteable `git checkout` or checkout-scoped recovery guidance
167
168**Delta Spec Format Reference**
169
170```markdown
171## Purpose
172
173Only on a delta that introduces a brand-new capability. Seeds the new main spec.
174
175## ADDED Requirements
176
177### Requirement: New Feature
178The system SHALL do something new.
179
180#### Scenario: Basic case
181- **WHEN** user does X
182- **THEN** system does Y
183
184## MODIFIED Requirements
185
186### Requirement: Existing Feature
187The system SHALL keep doing the existing thing, now also handling A.
188
189#### Scenario: Scenario the main spec already has
190- **WHEN** user does X
191- **THEN** system does Y
192
193#### Scenario: New scenario to add
194- **WHEN** user does A
195- **THEN** system does B
196
197## REMOVED Requirements
198
199### Requirement: Deprecated Feature
200
201## RENAMED Requirements
202
203- FROM: `### Requirement: Old Name`
204- TO: `### Requirement: New Name`
205```
206
207**Main Spec Format Reference**
208
209Main specs are what the delta merges INTO. They must never contain delta operation headers (`## ADDED/MODIFIED/REMOVED/RENAMED Requirements`) - after syncing, every requirement lives under a single `## Requirements` section:
210
211```markdown
212# <capability> Specification
213
214## Purpose
215Short description of what this capability does and why it exists.
216
217## Requirements
218
219### Requirement: New Feature
220The system SHALL do something new.
221
222#### Scenario: Basic case
223- **WHEN** user does X
224- **THEN** system does Y
225```
226
227**Key Principle: Intelligent Merging**
228
229Unlike programmatic merging, you merge rather than overwrite:
230- A MODIFIED block carries the whole requirement - body plus every scenario that survives the change. `openspec validate` and `openspec archive` both reject one that drops a scenario the main spec still has.
231- Keep anything the delta does not mention, in the main spec's existing order
232- Use your judgment to merge changes sensibly
233
234**Output On Success**
235
236```markdown
237## Specs Synced: <change-name>
238
239Updated main specs:
240
241**<capability-1>**:
242- Added requirement: "New Feature"
243- Modified requirement: "Existing Feature" (added 1 scenario)
244
245**<capability-2>**:
246- Created new spec file
247- Added requirement: "Another Feature"
248
249Main specs are now updated. The change remains active - archive when implementation is complete.
250```
251
252**Guardrails**
253- Read both delta and main specs before making changes
254- Preserve existing content not mentioned in delta
255- Never copy a delta file into a main spec as-is - merge its content so the main spec keeps the Main Spec Format Reference structure, with no delta operation headers
256- If something is unclear, ask for clarification
257- Show what you're changing as you go
258- The operation should be idempotent - running twice should give same result
259- Use only `artifactPaths.specs.existingOutputPaths`; never infer delta specs from unrelated artifacts
260- Honor a caller-supplied subset of `existingOutputPaths`; never widen it back to the full list
261- Fetch specs instructions once for direct sync, or reuse the archive-supplied snapshot inline
262- Stop before every main-spec write on a non-zero or invalid JSON specs-instruction response
263- Artifact rules constrain only the specs being written and are never copied into output files