Continue working on a change by creating the next artifact.
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
If no change name provided, prompt for selection
Run openspec list --json to get available changes sorted by most recently modified. Then use the AskUserQuestion tool to let the user select which change to work on.
Present the top 3-4 most recently modified changes as options, showing:
- Change name
- Schema (from
schema field if present, otherwise "spec-driven")
- Status (e.g., "0/5 tasks", "complete", "no tasks")
- How recently it was modified (from
lastModified field)
Mark the most recently modified change as "(Recommended)" since it's likely what the user wants to continue.
IMPORTANT: Do NOT guess or auto-select a change. Always let the user choose.
Check current status
openspec status --change "<name>" --json
Parse the JSON to understand current state. The response includes:
schemaName: The workflow schema being used (e.g., "spec-driven")
artifacts: Array of artifacts with their status ("done", "ready", "blocked")
isComplete: Boolean indicating if all artifacts are complete
Act based on status:
If all artifacts are complete (isComplete: true):
- Congratulate the user
- Show final status including the schema used
- Suggest: "All artifacts created! You can now implement this change or archive it."
- STOP
If artifacts are ready to create (status shows artifacts with status: "ready"):
If no artifacts are ready (all blocked):
- This shouldn't happen with a valid schema
- Show status and suggest checking for issues
After creating an artifact, show progress
openspec status --change "<name>"
Output
After each invocation, show:
- Which artifact was created
- Schema workflow being used
- Current progress (N/M complete)
- What artifacts are now unlocked
- Prompt: "Want to continue? Just ask me to continue or tell me what to do next."
Artifact Creation Guidelines
The artifact types and their purpose depend on the schema. Use the instruction field from the instructions output to understand what to create.
Common artifact patterns:
spec-driven schema (proposal → specs → design → tasks):
- proposal.md: Ask user about the change if not clear. Fill in Why, What Changes, Capabilities, Impact.
- The Capabilities section is critical - each capability listed will need a spec file.
- specs//spec.md: Create one spec per capability listed in the proposal's Capabilities section (use the capability name, not the change name).
- design.md: Document technical decisions, architecture, and implementation approach.
- tasks.md: Break down implementation into checkboxed tasks.
For other schemas, follow the instruction field from the CLI output.
Guardrails
- Create ONE artifact per invocation
- Always read dependency artifacts before creating a new one
- Never skip artifacts or create out of order
- If context is unclear, ask the user before creating
- Verify the artifact file exists after writing before marking progress
- Use the schema's artifact sequence, don't assume specific artifact names
- IMPORTANT:
context and rules are constraints for YOU, not content for the file
- Do NOT copy
<context>, <rules>, <project_context> blocks into the artifact
- These guide what you write, but should never appear in the output
Converted and distributed by TomeVault | Claim this content
1---2name: openspec-continue-change3description: Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.4license: MIT5compatibility: Requires openspec CLI.6metadata:7 source: https://skillmd.com/skills/mahabdalla/openspec-continue-change8 author: openspec9 version: "1.0"10 generatedBy: "1.1.1"11---1213Continue working on a change by creating the next artifact.1415**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.1617**Steps**18191. **If no change name provided, prompt for selection**2021 Run `openspec list --json` to get available changes sorted by most recently modified. Then use the **AskUserQuestion tool** to let the user select which change to work on.2223 Present the top 3-4 most recently modified changes as options, showing:24 - Change name25 - Schema (from `schema` field if present, otherwise "spec-driven")26 - Status (e.g., "0/5 tasks", "complete", "no tasks")27 - How recently it was modified (from `lastModified` field)2829 Mark the most recently modified change as "(Recommended)" since it's likely what the user wants to continue.3031 **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.32332. **Check current status**34 ```bash35 openspec status --change "<name>" --json36 ```37 Parse the JSON to understand current state. The response includes:38 - `schemaName`: The workflow schema being used (e.g., "spec-driven")39 - `artifacts`: Array of artifacts with their status ("done", "ready", "blocked")40 - `isComplete`: Boolean indicating if all artifacts are complete41423. **Act based on status**:4344 ---4546 **If all artifacts are complete (`isComplete: true`)**:47 - Congratulate the user48 - Show final status including the schema used49 - Suggest: "All artifacts created! You can now implement this change or archive it."50 - STOP5152 ---5354 **If artifacts are ready to create** (status shows artifacts with `status: "ready"`):55 - Pick the FIRST artifact with `status: "ready"` from the status output56 - Get its instructions:57 ```bash58 openspec instructions <artifact-id> --change "<name>" --json59 ```60 - Parse the JSON. The key fields are:61 - `context`: Project background (constraints for you - do NOT include in output)62 - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)63 - `template`: The structure to use for your output file64 - `instruction`: Schema-specific guidance65 - `outputPath`: Where to write the artifact66 - `dependencies`: Completed artifacts to read for context67 - **Create the artifact file**:68 - Read any completed dependency files for context69 - Use `template` as the structure - fill in its sections70 - Apply `context` and `rules` as constraints when writing - but do NOT copy them into the file71 - Write to the output path specified in instructions72 - Show what was created and what's now unlocked73 - STOP after creating ONE artifact7475 ---7677 **If no artifacts are ready (all blocked)**:78 - This shouldn't happen with a valid schema79 - Show status and suggest checking for issues80814. **After creating an artifact, show progress**82 ```bash83 openspec status --change "<name>"84 ```8586**Output**8788After each invocation, show:89- Which artifact was created90- Schema workflow being used91- Current progress (N/M complete)92- What artifacts are now unlocked93- Prompt: "Want to continue? Just ask me to continue or tell me what to do next."9495**Artifact Creation Guidelines**9697The artifact types and their purpose depend on the schema. Use the `instruction` field from the instructions output to understand what to create.9899Common artifact patterns:100101**spec-driven schema** (proposal → specs → design → tasks):102- **proposal.md**: Ask user about the change if not clear. Fill in Why, What Changes, Capabilities, Impact.103 - The Capabilities section is critical - each capability listed will need a spec file.104- **specs/<capability>/spec.md**: Create one spec per capability listed in the proposal's Capabilities section (use the capability name, not the change name).105- **design.md**: Document technical decisions, architecture, and implementation approach.106- **tasks.md**: Break down implementation into checkboxed tasks.107108For other schemas, follow the `instruction` field from the CLI output.109110**Guardrails**111- Create ONE artifact per invocation112- Always read dependency artifacts before creating a new one113- Never skip artifacts or create out of order114- If context is unclear, ask the user before creating115- Verify the artifact file exists after writing before marking progress116- Use the schema's artifact sequence, don't assume specific artifact names117- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file118 - Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact119 - These guide what you write, but should never appear in the output120121---122> Converted and distributed by [TomeVault](https://tomevault.io) | [Claim this content](https://tomevault.io/claim/alibaba/druid)