Implement findings from verification reports with scope-based parallel workflow
Implements verification findings using parallel workflow. Triggers on `/revise` commands to process collation reports, handling common issues immediately while validating exclusive issues through cross-check.
/plugin marketplace add cipherstash/cipherpowers/plugin install cipherpowers@cipherpowersThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Systematic implementation of verification findings. Separates what to fix (verify) from how to fix it (revise). Enables parallel workflow where common issues can be implemented while cross-check validates exclusive issues.
Announce at start: "I'm using the revising-findings skill to implement [scope] issues from verification."
| Scope | What's Implemented | When Available |
|---|---|---|
common | Issues both reviewers found (VERY HIGH confidence) | Immediately after collation |
exclusive | VALIDATED exclusive issues only | After cross-check completes |
all | Common + VALIDATED exclusive | After cross-check completes |
Exclusive issue states:
Before revising:
/verify)exclusive or all scope: cross-check must be completeFind most recent collation:
ls -la .work/*-collated*.md | tail -1
If no collation found:
Error: No collation report found. Run `/verify` first.
Determine what to implement:
| User Request | Scope | Requirements |
|---|---|---|
/revise | all | Cross-check complete |
/revise common | common | None (immediate) |
/revise exclusive | exclusive | Cross-check complete |
/revise all | all | Cross-check complete |
For exclusive or all scope:
Read collation report metadata:
Cross-check Status: PENDING → Warn user, suggest /revise commonCross-check Status: COMPLETE → ContinueWarning message:
Cross-check still running. Options:
1. `/revise common` - Start with high-confidence issues now
2. Wait for cross-check to complete
For common scope:
For exclusive scope:
Cross-check: VALIDATEDCross-check: INVALIDATED automaticallyCross-check: UNCERTAINFor all scope:
For each UNCERTAIN exclusive issue:
UNCERTAIN: "[Issue description]"
- Source: Reviewer #[1/2]
- Cross-check: [findings]
Implement? [Y/n/skip all]
Agent selection:
| Issue Type | Agent | Focus |
|---|---|---|
| Code fixes | cipherpowers:code-agent | Apply code changes |
| Documentation | cipherpowers:technical-writer | Update docs |
| Test coverage | cipherpowers:code-agent | Add tests |
| Security fixes | cipherpowers:code-agent | Security patches |
Dispatch pattern:
Task tool:
subagent_type: [agent from table]
description: "Implement [issue summary]"
prompt: "Implement this fix from verification:
Issue: [description]
Location: [file/location]
Action: [what to do]
Make minimal, focused changes."
Parallel dispatch: Independent issues can be dispatched in parallel.
After all implementations:
Completion message:
Revise complete.
Implemented:
- Common issues: X/Y
- Exclusive (VALIDATED): X/Y
- Exclusive (UNCERTAIN): X/Y (user approved)
- Skipped (INVALIDATED): X
Run `/verify` again to confirm fixes?
All issues from collation have been addressed.
Run `/verify` to confirm, or continue with other work.
No [common/exclusive] issues to implement.
[For common: All issues were exclusive - wait for cross-check]
[For exclusive: All exclusive issues were INVALIDATED]
If user wants to proceed without cross-check:
/revise all --force
Warning: Implementing exclusive issues without validation.
INVALIDATED issues may be included. Proceed? [y/N]
/verify docs
↓
Collation complete
↓
/revise common ← Starts immediately
↓ ↓
[Implementing] [Cross-check runs]
↓ ↓
Done Cross-check complete
↓
/revise exclusive
↓
All done
exclusive/all scope/cipherpowers:verify - Produces collation reportsdual-verification skill - The verification workflow/cipherpowers:execute - Uses revise for fix implementationcommon scope works immediately (no waiting)exclusive requires cross-check completeThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.