Verify that an implementation matches the change artifacts (specs, tasks, design).
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.
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 implementation tasks (tasks artifact exists).
Include the schema used for each change if available.
Mark changes with incomplete tasks as "(In Progress)".
Always announce: "Using change: " and how to override (e.g., /openspec-verify-change <other>).
Check status to understand the schema
openspec status --change "<name>" --json
Parse the JSON to understand:
schemaName: The workflow being used (e.g., "spec-driven")
planningHome, changeRoot, artifactPaths, and actionContext: path and scope context
- Which artifacts exist for this change
Get planning context and load artifacts
openspec instructions apply --change "<name>" --json
This returns the change directory and contextFiles (artifact ID -> array of concrete file paths). Read all available artifacts from contextFiles.
Initialize verification report structure
Create a report structure with three dimensions:
- Completeness: Track tasks and spec coverage
- Correctness: Track requirement implementation and scenario coverage
- Coherence: Track design adherence and pattern consistency
Each dimension can have CRITICAL, WARNING, or SUGGESTION issues.
Verify Completeness
Task Completion:
- If
contextFiles.tasks exists, read every file path in it
- Parse checkboxes:
- [ ] (incomplete) vs - [x] (complete)
- Count complete vs total tasks
- If incomplete tasks exist:
- Add CRITICAL issue for each incomplete task
- Recommendation: "Complete task: " or "Mark as done if already implemented"
Spec Coverage:
- If delta specs exist in
contextFiles.specs:
- Extract all requirements (marked with "### Requirement:")
- For each requirement:
- Search codebase for keywords related to the requirement
- Assess if implementation likely exists
- If requirements appear unimplemented:
- Add CRITICAL issue: "Requirement not found: "
- Recommendation: "Implement requirement X: "
Verify Correctness
Requirement Implementation Mapping:
- For each requirement from delta specs:
- Search codebase for implementation evidence
- If found, note file paths and line ranges
- Assess if implementation matches requirement intent
- If divergence detected:
- Add WARNING: "Implementation may diverge from spec: "
- Recommendation: "Review : against requirement X"
Scenario Coverage:
- For each scenario in delta specs (marked with "#### Scenario:"):
- Check if conditions are handled in code
- Check if tests exist covering the scenario
- If scenario appears uncovered:
- Add WARNING: "Scenario not covered: "
- Recommendation: "Add test or implementation for scenario: "
Verify Coherence
Design Adherence:
- If
contextFiles.design exists:
- Extract key decisions (look for sections like "Decision:", "Approach:", "Architecture:")
- Verify implementation follows those decisions
- If contradiction detected:
- Add WARNING: "Design decision not followed: "
- Recommendation: "Update implementation or revise design.md to match reality"
- If no design.md: Skip design adherence check, note "No design.md to verify against"
Code Pattern Consistency:
- Review new code for consistency with project patterns
- Check file naming, directory structure, coding style
- If significant deviations found:
- Add SUGGESTION: "Code pattern deviation: "
- Recommendation: "Consider following project pattern: "
Generate Verification Report
Summary Scorecard:
## Verification Report: <change-name>
### Summary
| Dimension | Status |
|--------------|------------------|
| Completeness | X/Y tasks, N reqs|
| Correctness | M/N reqs covered |
| Coherence | Followed/Issues |
Issues by Priority:
CRITICAL (Must fix before archive):
- Incomplete tasks
- Missing requirement implementations
- Each with specific, actionable recommendation
WARNING (Should fix):
- Spec/design divergences
- Missing scenario coverage
- Each with specific recommendation
SUGGESTION (Nice to fix):
- Pattern inconsistencies
- Minor improvements
- Each with specific recommendation
Final Assessment:
- If CRITICAL issues: "X critical issue(s) found. Fix before archiving."
- If only warnings: "No critical issues. Y warning(s) to consider. Ready for archive (with noted improvements)."
- If all clear: "All checks passed. Ready for archive."
Verification Heuristics
- Completeness: Focus on objective checklist items (checkboxes, requirements list)
- Correctness: Use keyword search, file path analysis, reasonable inference - don't require perfect certainty
- Coherence: Look for glaring inconsistencies, don't nitpick style
- False Positives: When uncertain, prefer SUGGESTION over WARNING, WARNING over CRITICAL
- Actionability: Every issue must have a specific recommendation with file/line references where applicable
Graceful Degradation
- If only tasks.md exists: verify task completion only, skip spec/design checks
- If tasks + specs exist: verify completeness and correctness, skip design
- If full artifacts: verify all three dimensions
- Always note which checks were skipped and why
Output Format
Use clear markdown with:
- Table for summary scorecard
- Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)
- Code references in format:
file.ts:123
- Specific, actionable recommendations
- No vague suggestions like "consider reviewing"
1---
2name: openspec-verify-change
3description: Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
4allowed-tools: Bash(openspec:*)
5license: MIT
6compatibility: Requires openspec CLI.
7metadata:
8 source: https://skillmd.com/skills/wot-ui/openspec-verify-change
9 author: openspec
10 version: "1.0"
11 generatedBy: "1.9.0"
12---
13
14Verify that an implementation matches the change artifacts (specs, tasks, design).
15
16**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.
17
18**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.
19
20**Steps**
21
221. **Select the change**
23
24 If a name is provided, use it. Otherwise:
25 - Infer from conversation context if the user mentioned a change
26 - Auto-select if only one active change exists
27 - If ambiguous, run `openspec list --json` to get available changes and ask the user to select one
28
29 When prompting, show changes that have implementation tasks (tasks artifact exists).
30 Include the schema used for each change if available.
31 Mark changes with incomplete tasks as "(In Progress)".
32
33 Always announce: "Using change: <name>" and how to override (e.g., `/openspec-verify-change <other>`).
34
352. **Check status to understand the schema**
36 ```bash
37 openspec status --change "<name>" --json
38 ```
39 Parse the JSON to understand:
40 - `schemaName`: The workflow being used (e.g., "spec-driven")
41 - `planningHome`, `changeRoot`, `artifactPaths`, and `actionContext`: path and scope context
42 - Which artifacts exist for this change
43
443. **Get planning context and load artifacts**
45
46 ```bash
47 openspec instructions apply --change "<name>" --json
48 ```
49
50 This returns the change directory and `contextFiles` (artifact ID -> array of concrete file paths). Read all available artifacts from `contextFiles`.
51
524. **Initialize verification report structure**
53
54 Create a report structure with three dimensions:
55 - **Completeness**: Track tasks and spec coverage
56 - **Correctness**: Track requirement implementation and scenario coverage
57 - **Coherence**: Track design adherence and pattern consistency
58
59 Each dimension can have CRITICAL, WARNING, or SUGGESTION issues.
60
615. **Verify Completeness**
62
63 **Task Completion**:
64 - If `contextFiles.tasks` exists, read every file path in it
65 - Parse checkboxes: `- [ ]` (incomplete) vs `- [x]` (complete)
66 - Count complete vs total tasks
67 - If incomplete tasks exist:
68 - Add CRITICAL issue for each incomplete task
69 - Recommendation: "Complete task: <description>" or "Mark as done if already implemented"
70
71 **Spec Coverage**:
72 - If delta specs exist in `contextFiles.specs`:
73 - Extract all requirements (marked with "### Requirement:")
74 - For each requirement:
75 - Search codebase for keywords related to the requirement
76 - Assess if implementation likely exists
77 - If requirements appear unimplemented:
78 - Add CRITICAL issue: "Requirement not found: <requirement name>"
79 - Recommendation: "Implement requirement X: <description>"
80
816. **Verify Correctness**
82
83 **Requirement Implementation Mapping**:
84 - For each requirement from delta specs:
85 - Search codebase for implementation evidence
86 - If found, note file paths and line ranges
87 - Assess if implementation matches requirement intent
88 - If divergence detected:
89 - Add WARNING: "Implementation may diverge from spec: <details>"
90 - Recommendation: "Review <file>:<lines> against requirement X"
91
92 **Scenario Coverage**:
93 - For each scenario in delta specs (marked with "#### Scenario:"):
94 - Check if conditions are handled in code
95 - Check if tests exist covering the scenario
96 - If scenario appears uncovered:
97 - Add WARNING: "Scenario not covered: <scenario name>"
98 - Recommendation: "Add test or implementation for scenario: <description>"
99
1007. **Verify Coherence**
101
102 **Design Adherence**:
103 - If `contextFiles.design` exists:
104 - Extract key decisions (look for sections like "Decision:", "Approach:", "Architecture:")
105 - Verify implementation follows those decisions
106 - If contradiction detected:
107 - Add WARNING: "Design decision not followed: <decision>"
108 - Recommendation: "Update implementation or revise design.md to match reality"
109 - If no design.md: Skip design adherence check, note "No design.md to verify against"
110
111 **Code Pattern Consistency**:
112 - Review new code for consistency with project patterns
113 - Check file naming, directory structure, coding style
114 - If significant deviations found:
115 - Add SUGGESTION: "Code pattern deviation: <details>"
116 - Recommendation: "Consider following project pattern: <example>"
117
1188. **Generate Verification Report**
119
120 **Summary Scorecard**:
121 ```markdown
122 ## Verification Report: <change-name>
123
124 ### Summary
125 | Dimension | Status |
126 |--------------|------------------|
127 | Completeness | X/Y tasks, N reqs|
128 | Correctness | M/N reqs covered |
129 | Coherence | Followed/Issues |
130 ```
131
132 **Issues by Priority**:
133
134 1. **CRITICAL** (Must fix before archive):
135 - Incomplete tasks
136 - Missing requirement implementations
137 - Each with specific, actionable recommendation
138
139 2. **WARNING** (Should fix):
140 - Spec/design divergences
141 - Missing scenario coverage
142 - Each with specific recommendation
143
144 3. **SUGGESTION** (Nice to fix):
145 - Pattern inconsistencies
146 - Minor improvements
147 - Each with specific recommendation
148
149 **Final Assessment**:
150 - If CRITICAL issues: "X critical issue(s) found. Fix before archiving."
151 - If only warnings: "No critical issues. Y warning(s) to consider. Ready for archive (with noted improvements)."
152 - If all clear: "All checks passed. Ready for archive."
153
154**Verification Heuristics**
155
156- **Completeness**: Focus on objective checklist items (checkboxes, requirements list)
157- **Correctness**: Use keyword search, file path analysis, reasonable inference - don't require perfect certainty
158- **Coherence**: Look for glaring inconsistencies, don't nitpick style
159- **False Positives**: When uncertain, prefer SUGGESTION over WARNING, WARNING over CRITICAL
160- **Actionability**: Every issue must have a specific recommendation with file/line references where applicable
161
162**Graceful Degradation**
163
164- If only tasks.md exists: verify task completion only, skip spec/design checks
165- If tasks + specs exist: verify completeness and correctness, skip design
166- If full artifacts: verify all three dimensions
167- Always note which checks were skipped and why
168
169**Output Format**
170
171Use clear markdown with:
172- Table for summary scorecard
173- Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)
174- Code references in format: `file.ts:123`
175- Specific, actionable recommendations
176- No vague suggestions like "consider reviewing"