Parallel Multi-Perspective Analysis

Operator Context

Hardcoded Behaviors (Always Apply)

• CLAUDE.md Compliance: Read and follow repository CLAUDE.md before execution
• Over-Engineering Prevention: Apply only Priority 1 and Priority 2 synthesized rules. Do not invent improvements beyond what the source material supports. No speculative enhancements.
• True Parallel Independence: All 10 Task invocations MUST be in a single message. Each agent receives ONLY its assigned perspective with zero cross-contamination.
• Artifact Persistence: Save synthesis document and completion report to files. Context is ephemeral; artifacts persist.
• Token Budget Awareness: Estimate total cost before execution. Warn if source material exceeds 5,000 words (drives cost above 50,000 tokens).
• Validate Inputs First: Verify target agent/skill exists and source material is readable before spawning any agents.
• No Behavior Changes: Synthesized rules ADD depth. They NEVER remove or significantly alter existing working patterns in the target.

Default Behaviors (ON unless disabled)

• 10 Perspectives: Use all 10 analytical frameworks (see

  references/perspective-prompts.md

  )
• Priority-Based Application: Apply Must-Have rules first, then Should-Have. Skip Nice-to-Have unless user requests.
• Synthesis Before Application: Collect all 10 reports and synthesize before making any changes to the target.
• Completion Report: Generate detailed report showing impact, changes, and perspective contributions.
• Graceful Degradation: If agents time out, proceed with available results (3+ of 10 sufficient).
• Git Commit: Commit improvements with descriptive message after application.

Optional Behaviors (OFF unless enabled)

• Reduced Perspectives: Use 5 perspectives instead of 10 to halve token cost
• Dry Run Mode: Generate synthesis without applying changes to target
• Compare Mode: Analyze two sources and extract differences

What This Skill CAN Do

• Extract comprehensive insights from complex source material through 10 independent lenses
• Synthesize cross-perspective patterns into prioritized improvement recommendations
• Apply synthesized rules to enhance an existing agent or skill
• Produce detailed reports showing which perspectives contributed to each improvement
• Detect patterns that single-threaded analysis misses due to cognitive anchoring

What This Skill CANNOT Do

• Replace inline analysis for simple or straightforward material (use

  /do-perspectives

  for single-target improvements)
• Operate without sufficient token budget (requires 25,000-63,000 tokens)
• Guarantee all 10 agents complete (network/timeout issues may reduce count)
• Generate value from poor source material (marketing fluff, auto-generated docs)
• Skip the synthesis phase and apply raw per-perspective rules directly

Instructions

Phase 1: VALIDATE INPUTS

• Extract target agent/skill name (first argument)
• Extract source material path (second argument)
• If either argument is missing, report usage:

  /do-parallel <target-name> <source-path>

# For agents
ls agents/{target_name}.md

# For skills
ls skills/{target_name}/SKILL.md

• Determine if target is an agent or skill based on which path exists
• Read target file to understand current state, capture line count
• If target does not exist in either location, stop and report error

## Source Material Assessment

File: [path]
Word count: [N] words
Estimated token cost: [N * 10 * 3] = [total] tokens

Quality indicators:
- [ ] Contains concrete examples (not just abstract claims)
- [ ] Has systematic structure (sections, progression)
- [ ] Demonstrates expertise (technical depth, nuanced explanations)
- [ ] Sufficient length (500+ words minimum)

Assessment: SUITABLE / UNSUITABLE

• Read source file, confirm it is non-empty
• Estimate word count. If over 5,000 words, warn about elevated token cost.
• If material fails 2+ quality indicators, recommend inline analysis instead and ask user to confirm

Phase 2: MULTI-PERSPECTIVE ANALYSIS (TRUE PARALLEL)

1. The FULL source material
2. ONE assigned perspective (from

   references/perspective-prompts.md

   )
3. The target name for contextualized recommendations
4. Instructions to produce 200-500 words of focused analysis

1. Structural Analysis
2. Clarity and Precision
3. Technical Explanation Patterns
4. Audience Assumption Patterns
5. Evidence and Citation Strategy
6. Narrative Progression
7. Paragraph and Sentence Architecture
8. Header and Signposting Strategy
9. Complexity Management
10. Limitation and Nuance Handling

Agent running > 5 minutes?
    |
    +-- YES --> Check progress (non-blocking)
    |           |
    |           +-- Making progress? --> Wait 2 more minutes
    |           |
    |           +-- Stuck on web fetch? --> Mark as timed out, proceed
    |
    +-- NO --> Continue waiting

Phase 3: SYNTHESIZE

| Rule | Struct | Clarity | Tech | Audience | Evidence | Narrative | Para | Header | Complex | Nuance | Count |
|------|--------|---------|------|----------|----------|-----------|------|--------|---------|--------|-------|
| [Rule A] | X | X | | X | | X | | | X | | 5 |
| [Rule B] | | | X | | X | | X | X | | X | 4 |

• Patterns appearing in 4+ perspectives are high-confidence findings
• Patterns appearing in 7+ perspectives are near-certain insights
• Group related rules into themes (e.g., "Progressive Disclosure" may appear in Audience, Complexity, and Structure)

• Single-perspective findings that are high-value despite low frequency
• These often represent the unique value of parallel independence
• Example: Only Narrative Progression spots a "hook-payoff" pattern that would strengthen an agent's introduction section

## Priority Rules for [Target]

### Must-Have (Priority 1)
Rules present in 7+ perspectives OR critical impact:
1. [Rule] - Found in: [list of perspectives]
2. [Rule] - Found in: [list of perspectives]

### Should-Have (Priority 2)
Rules present in 4-6 perspectives OR high impact:
1. [Rule] - Found in: [list of perspectives]
2. [Rule] - Found in: [list of perspectives]

### Nice-to-Have (Priority 3)
Rules present in 1-3 perspectives OR moderate impact:
1. [Rule] - Found in: [perspective]
2. [Rule] - Found in: [perspective]

• Write to

  skills/do-parallel/artifacts/synthesis-{target}-{date}.md

• Include the cross-reference matrix, themes, and prioritized rules
• This artifact persists for future reference and can inform later analyses

Phase 4: APPLY

## Before State

Target: [name]
Type: [agent/skill]
Lines: [N]
Sections: [list of H2/H3 sections]
Version: [current version]

## Application Plan

| Rule | Action | Target Section | Risk |
|------|--------|----------------|------|
| [Rule 1] | Add subsection | Operator Context | LOW |
| [Rule 2] | Enhance existing | Instructions Phase 2 | LOW |
| [Rule 3] | Add new section | After Anti-Patterns | MEDIUM |

• Add or enhance sections based on Must-Have recommendations
• Preserve all existing working patterns
• After each rule application, verify target file is still valid markdown

• Add Should-Have enhancements where they integrate naturally
• Do NOT force rules that conflict with existing patterns
• If a Should-Have rule conflicts with an existing pattern, document the conflict in the report and skip

• Create descriptive git commit explaining what was improved and from what source
• Bump version if target is a skill (e.g., 1.0.0 to 1.1.0)

Phase 5: VERIFY AND REPORT

## Integrity Check

YAML frontmatter valid: [YES/NO]
Sections preserved: [list any missing sections]
Before lines: [N]
After lines: [M]
Net change: +[M-N] lines

Verification:
- [ ] All original H2 sections still present
- [ ] All original H3 sections still present
- [ ] No content was deleted (only additions)
- [ ] Markdown renders correctly

references/perspective-prompts.md

• Per-perspective key insights (one sentence each)
• Cross-reference showing which perspectives contributed to each improvement
• Before/after comparison (line counts, section counts)
• Estimated token usage breakdown
• Recommendations for future improvements

• Write to

  skills/do-parallel/artifacts/report-{target}-{date}.md

• Present summary to user in conversation

## Parallel Analysis Complete

Target: [name]
Source: [source path]
Perspectives completed: [N] of 10
Rules extracted: [total across all perspectives]
Rules applied: [Priority 1 count] Must-Have + [Priority 2 count] Should-Have
Lines added: +[count]
New sections: [count]

Full report: skills/do-parallel/artifacts/report-{target}-{date}.md
Synthesis: skills/do-parallel/artifacts/synthesis-{target}-{date}.md

Examples

Example 1: Improve Agent from Article

/do-parallel technical-journalist-writer expert-writing-guide.md

1. Validate target agent exists, read source article (VALIDATE)
2. Spawn 10 agents analyzing article from 10 perspectives (ANALYZE)
3. Synthesize: 5 Must-Have rules, 7 Should-Have rules (SYNTHESIZE)
4. Apply Priority 1 and 2 rules to agent file (APPLY)
5. Generate report showing +180 lines added (VERIFY) Result: Agent enhanced with synthesized writing patterns from 10 independent analyses

Example 2: Improve Skill from Documentation

/do-parallel systematic-debugging postgres-debugging-guide.md

1. Validate skill exists, assess documentation quality (VALIDATE)
2. Launch 10 parallel analyses of PostgreSQL debugging patterns (ANALYZE)
3. Synthesize database-specific debugging rules (SYNTHESIZE)
4. Add new patterns to debugging skill references (APPLY)
5. Report: 8 of 10 perspectives contributed new rules (VERIFY) Result: Debugging skill gains domain-specific PostgreSQL patterns

Token Budget Management

Cost Breakdown

When Cost Is Justified

• Source material is difficult and hard to grasp from a single reading
• Multiple independent interpretations could reveal hidden patterns
• The target agent/skill is high-impact and warrants deep investment
• Token budget has room for 30,000-60,000 tokens

• Source material is straightforward with obvious patterns
• A single reading captures the key insights
• Token budget is constrained
• Routine incremental improvement is the goal

Cost Estimation Formula

Estimated tokens = (source_words * 3 * 10) + 15,000

Example: 2,000-word article
  = (2,000 * 3 * 10) + 15,000
  = 60,000 + 15,000
  = ~75,000 tokens (HIGH - consider trimming source or reducing perspectives)

Example: 800-word article
  = (800 * 3 * 10) + 15,000
  = 24,000 + 15,000
  = ~39,000 tokens (ACCEPTABLE)

Error Handling

Error: "Target Agent/Skill Not Found"

1. List available agents with

   ls agents/*.md

2. List available skills with

   ls skills/*/SKILL.md

3. Retry with exact name matching repository

Error: "Source Material Too Short or Empty"

1. Verify file path is absolute and file exists
2. If material is under 500 words, it likely lacks sufficient patterns
3. Consider using inline analysis instead of parallel (lower cost, similar value for thin material)

Error: "Agents Timing Out"

1. Check if source exceeds 10,000 words (reduce or split)
2. After 5 minutes, check agent progress with non-blocking query
3. Proceed with completed perspectives if 3+ have returned
4. See graceful degradation table in Phase 2, Step 3

Error: "Synthesis Has Insufficient Rules"

1. Review agent outputs for quality (are they 200-500 words with concrete patterns?)
2. If most outputs are thin, the source material is unsuitable for parallel analysis
3. Consider switching to inline analysis with a focused prompt
4. Report to user: "Source material did not yield sufficient patterns for 10-perspective analysis"

Anti-Patterns

Anti-Pattern 1: Using Parallel for Simple Material

/do-perspectives

Anti-Pattern 2: Applying All Rules Without Prioritization

Anti-Pattern 3: Skipping Synthesis Phase

Anti-Pattern 4: Running Without Budget Awareness

References

• Anti-Rationalization - Prevents shortcut rationalizations
• Verification Checklist - Pre-completion checks
• Pipeline Architecture - Phase-gated pipeline design
• Gate Enforcement - Phase transition rules

Domain-Specific Anti-Rationalization

Reference Files

• ${CLAUDE_SKILL_DIR}/references/perspective-prompts.md

  : All 10 perspective templates, synthesis format, completion report template, and source material guidance