一键导入
verify
Manifest verification runner. Spawns parallel verifiers for Global Invariants and Acceptance Criteria. Called by /do, not directly by users.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Manifest verification runner. Spawns parallel verifiers for Global Invariants and Acceptance Criteria. Called by /do, not directly by users.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | verify |
| description | Manifest verification runner. Spawns parallel verifiers for Global Invariants and Acceptance Criteria. Called by /do, not directly by users. |
Orchestrate verification of all criteria from a Manifest by spawning parallel verifiers. Report results grouped by type.
User request: $ARGUMENTS
Format: <manifest-file-path> <execution-log-path> [--scope=files]
If paths missing: Return error "Usage: /verify "
| Principle | Rule |
|---|---|
| Orchestrate, don't verify | Spawn agents to verify. You coordinate results, never run checks yourself. |
| ALL criteria, no exceptions | Every INV-G* and AC-. criterion MUST be verified. Skipping any criterion is a critical failure. |
| Maximize parallelism | Launch all verifiers in a SINGLE message with multiple Task tool calls. Never launch one at a time. |
| Globals are critical | Global Invariant failures mean task failure. Highlight prominently. |
| Actionable feedback | Pass through file:line, expected vs actual, fix hints. |
| Type | What | Handler |
|---|---|---|
bash | Shell commands (tests, lint, typecheck) | criteria-checker |
codebase | Code pattern checks | criteria-checker |
subagent | Specialized reviewer agents | Named agent (e.g., code-bugs-reviewer) |
research | External info (API docs, dependencies) | criteria-checker |
manual | Set aside for human verification | /escalate |
Note: criteria-checker handles any automated verification requiring commands, file analysis, reasoning, or web research.
| Type | Pattern | Failure Impact |
|---|---|---|
| Global Invariant | INV-G{N} | Task fails |
| Acceptance Criteria | AC-{D}.{N} | Deliverable incomplete |
| Process Guidance | PG-{N} | Not verified (guidance only) |
Note: PG-* items guide HOW to work. Followed during /do, not checked by /verify.
| Condition | Action |
|---|---|
| Any Global Invariant failed | Return all failures, globals highlighted |
| Any AC failed | Return failures grouped by deliverable |
| All automated pass, manual exists | Return manual criteria, hint to call /escalate |
| All pass | Call /done |
Report verification results grouped by Global Invariants first, then by Deliverable.
On failure - Show for each failed criterion:
On success with manual - List manual criteria with how-to-verify from manifest, suggest /escalate.
On full success - Call /done.
Manifest builder. Plan work, scope tasks, spec out requirements. Converts needs into Deliverables + Invariants with verification criteria.
Sync plugins from configured source repos to OpenCode format. Usage: /sync-plugins [repo:plugin...] or /sync-plugins --all
Manifest executor. Iterates through Deliverables satisfying Acceptance Criteria, then verifies all ACs and Global Invariants pass.
Creates personalized X/Twitter growth strategy through guided interview. Based on algorithm-derived principles (exposure equation, phase model). Use when asked about X growth, Twitter strategy, building audience, or social media presence.
Completion marker. Outputs hierarchical execution summary showing Global Invariants respected and all Deliverables completed.
Structured escalation with evidence. Surfaces blocking issues for human decision, referencing the Manifest hierarchy.