Every execution produces a SUMMARY.md for quick human scanning without reading full outputs.

Each prompt gets its own folder in .prompts/ with its output artifacts, enabling clear provenance and chain detection.

Intake: Determine purpose (Do/Plan/Research/Refine), gather requirements Chain detection: Check for existing research/plan files to reference Generate: Create prompt using purpose-specific patterns Save: Create folder in .prompts/{number}-{topic}-{purpose}/ Present: Show decision tree for running Execute: Run prompt(s) with dependency-aware execution engine Summarize: Create SUMMARY.md for human scanning

.prompts/ ├── 001-auth-research/ │ ├── completed/ │ │ └── 001-auth-research.md # Prompt (archived after run) │ ├── auth-research.md # Full output (XML for Claude) │ └── SUMMARY.md # Executive summary (markdown for human) ├── 002-auth-plan/ │ ├── completed/ │ │ └── 002-auth-plan.md │ ├── auth-plan.md │ └── SUMMARY.md ├── 003-auth-implement/ │ ├── completed/ │ │ └── 003-auth-implement.md │ └── SUMMARY.md # Do prompts create code elsewhere ├── 004-auth-research-refine/ │ ├── completed/ │ │ └── 004-auth-research-refine.md │ ├── archive/ │ │ └── auth-research-v1.md # Previous version │ └── SUMMARY.md

BEFORE analyzing anything, check if context was provided.

IF no context provided (skill invoked without description): → IMMEDIATELY use AskUserQuestion with:

header: "Purpose" question: "What is the purpose of this prompt?" options: "Do" - Execute a task, produce an artifact "Plan" - Create an approach, roadmap, or strategy "Research" - Gather information or understand something "Refine" - Improve an existing research or plan output

After selection, ask: "Describe what you want to accomplish" (they select "Other" to provide free text).

IF context was provided: → Check if purpose is inferable from keywords:

implement, build, create, fix, add, refactor → Do plan, roadmap, approach, strategy, decide, phases → Plan research, understand, learn, gather, analyze, explore → Research refine, improve, deepen, expand, iterate, update → Refine

→ If unclear, ask the Purpose question above as first contextual question → If clear, proceed to adaptive_analysis with inferred purpose

Extract and infer:

Purpose: Do, Plan, Research, or Refine Topic identifier: Kebab-case identifier for file naming (e.g., auth, stripe-payments) Complexity: Simple vs complex (affects prompt depth) Prompt structure: Single vs multiple prompts Target (Refine only): Which existing output to improve

If topic identifier not obvious, ask:

header: "Topic" question: "What topic/feature is this for? (used for file naming)" Let user provide via "Other" option Enforce kebab-case (convert spaces/underscores to hyphens)

For Refine purpose, also identify target output from .prompts/*/ to improve.

Scan .prompts// for existing -research.md and *-plan.md files.

If found:

List them: "Found existing files: auth-research.md (in 001-auth-research/), stripe-plan.md (in 005-stripe-plan/)" Use AskUserQuestion: header: "Reference" question: "Should this prompt reference any existing research or plans?" options: List found files + "None" multiSelect: true

Match by topic keyword when possible (e.g., "auth plan" → suggest auth-research.md).

Generate 2-4 questions using AskUserQuestion based on purpose and gaps.

Load questions from: references/question-bank.md

Route by purpose:

Do → artifact type, scope, approach Plan → plan purpose, format, constraints Research → depth, sources, output format Refine → target selection, feedback, preservation

After receiving answers, present decision gate using AskUserQuestion:

header: "Ready" question: "Ready to create the prompt?" options: "Proceed" - Create the prompt with current context "Ask more questions" - I have more details to clarify "Let me add context" - I want to provide additional information

Loop until "Proceed" selected.

"Creating a {purpose} prompt for: {topic} Folder: .prompts/{number}-{topic}-{purpose}/ References: {list any chained files}"

Then proceed to generation.

Load purpose-specific patterns:

Do: references/do-patterns.md Plan: references/plan-patterns.md Research: references/research-patterns.md Refine: references/refine-patterns.md

Load intelligence rules: references/intelligence-rules.md

All generated prompts include:

Objective: What to accomplish, why it matters Context: Referenced files (@), dynamic context (!) Requirements: Specific instructions for the task Output specification: Where to save, what structure Metadata requirements: For research/plan outputs, specify XML metadata structure SUMMARY.md requirement: All prompts must create a SUMMARY.md file Success criteria: How to know it worked

For Research and Plan prompts, output must include:

- How confident in findings - What's needed to proceed - What remains uncertain - What was assumed

All prompts must create SUMMARY.md with:

One-liner - Substantive description of outcome Version - v1 or iteration info Key Findings - Actionable takeaways Files Created - (Do prompts only) Decisions Needed - What requires user input Blockers - External impediments Next Step - Concrete forward action

Create folder: .prompts/{number}-{topic}-{purpose}/ Create completed/ subfolder Write prompt to: .prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md Prompt instructs output to: .prompts/{number}-{topic}-{purpose}/{topic}-{purpose}.md

After saving prompt(s), present inline (not AskUserQuestion):

Prompt created: .prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md

What's next?

1. Run prompt now
2. Review/edit prompt first
3. Save for later
4. Other

Choose (1-4): _

Prompts created: - .prompts/001-auth-research/001-auth-research.md - .prompts/002-auth-plan/002-auth-plan.md - .prompts/003-auth-implement/003-auth-implement.md

Detected execution order: Sequential (002 references 001 output, 003 references 002 output)

What's next?

1. Run all prompts (sequential)
2. Review/edit prompts first
3. Save for later
4. Other

Choose (1-4): _

Straightforward execution of one prompt.

Read prompt file contents Spawn Task agent with subagent_type="general-purpose" Include in task prompt: The complete prompt contents Output location: .prompts/{number}-{topic}-{purpose}/{topic}-{purpose}.md Wait for completion Validate output (see validation section) Archive prompt to completed/ subfolder Report results with next-step options

For chained prompts where each depends on previous output.

Build execution queue from dependency order For each prompt in queue: a. Read prompt file b. Spawn Task agent c. Wait for completion d. Validate output e. If validation fails → stop, report failure, offer recovery options f. If success → archive prompt, continue to next Report consolidated results

Show progress during execution:

Executing 1/3: 001-auth-research... ✓ Executing 2/3: 002-auth-plan... ✓ Executing 3/3: 003-auth-implement... (running)

For independent prompts with no dependencies.

Read all prompt files CRITICAL: Spawn ALL Task agents in a SINGLE message This is required for true parallel execution Each task includes its output location Wait for all to complete Validate all outputs Archive all prompts Report consolidated results (successes and failures)

Unlike sequential, parallel continues even if some fail:

Collect all results Archive successful prompts Report failures with details Offer to retry failed prompts

For complex DAGs (e.g., two parallel research → one plan).

Analyze dependency graph from @ references Group into execution layers: Layer 1: No dependencies (run parallel) Layer 2: Depends only on layer 1 (run after layer 1 completes) Layer 3: Depends on layer 2, etc. Execute each layer: Parallel within layer Sequential between layers Stop if any dependency fails (downstream prompts can't run)

Scan prompt contents for @ references to determine dependencies:

Parse each prompt for @.prompts/{number}-{topic}/ patterns Build dependency graph Detect cycles (error if found) Determine execution order

If no explicit @ references found, infer from purpose:

Research prompts: No dependencies (can parallel) Plan prompts: Depend on same-topic research Do prompts: Depend on same-topic plan

Override with explicit references when present.

If a prompt references output that doesn't exist:

Check if it's another prompt in this session (will be created) Check if it exists in .prompts/*/ (already completed) If truly missing: Warn user: "002-auth-plan references auth-research.md which doesn't exist" Offer: Create the missing research prompt first? / Continue anyway? / Cancel? File exists: Check output file was created Not empty: File has content (> 100 chars) Metadata present (for research/plan): Check for required XML tags SUMMARY.md exists: Check SUMMARY.md was created SUMMARY.md complete: Has required sections (Key Findings, Decisions Needed, Blockers, Next Step) One-liner is substantive: Not generic like "Research completed"

If validation fails:

Report what's missing Offer options: Retry the prompt Continue anyway (for non-critical issues) Stop and investigate

Stop the chain immediately:

✗ Failed at 2/3: 002-auth-plan

Completed: - 001-auth-research ✓ (archived)

Failed: - 002-auth-plan: Output file not created

Not started: - 003-auth-implement

What's next? 1. Retry 002-auth-plan 2. View error details 3. Stop here (keep completed work) 4. Other

Continue others, report all results:

Parallel execution completed with errors:

✓ 001-api-research (archived) ✗ 002-db-research: Validation failed - missing tag ✓ 003-ui-research (archived)

What's next? 1. Retry failed prompt (002) 2. View error details 3. Continue without 002 4. Other

Move prompt file to completed subfolder:

mv .prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md \ .prompts/{number}-{topic}-{purpose}/completed/

Output file stays in place (not moved).

✓ Executed: 001-auth-research ✓ Created: .prompts/001-auth-research/SUMMARY.md

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Auth Research Summary

JWT with jose library and httpOnly cookies recommended

Key Findings

• jose outperforms jsonwebtoken with better TypeScript support • httpOnly cookies required (localStorage is XSS vulnerable) • Refresh rotation is OWASP standard

Decisions Needed

None - ready for planning

Blockers

None

Next Step

Create auth-plan.md ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

What's next? 1. Create planning prompt (auth-plan) 2. View full research output 3. Done 4. Other

Display the actual SUMMARY.md content inline so user sees findings without opening files.

✓ Chain completed: auth workflow

Results: ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 001-auth-research JWT with jose library and httpOnly cookies recommended Decisions: None • Blockers: None

002-auth-plan 4-phase implementation: types → JWT core → refresh → tests Decisions: Approve 15-min token expiry • Blockers: None

003-auth-implement JWT middleware complete with 6 files created Decisions: Review before Phase 2 • Blockers: None ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

All prompts archived. Full summaries in .prompts/*/SUMMARY.md

What's next? 1. Review implementation 2. Run tests 3. Create new prompt chain 4. Other

For chains, show condensed one-liner from each SUMMARY.md with decisions/blockers flagged.

If user wants to re-run an already-completed prompt:

Check if prompt is in completed/ subfolder Move it back to parent folder Optionally backup existing output: {output}.bak Execute normally

If output file already exists:

For re-runs: Backup existing → {filename}.bak For new runs: Should not happen (unique numbering) If conflict detected: Ask user - Overwrite? / Rename? / Cancel?

After successful execution:

Do NOT auto-commit (user controls git workflow) Mention what files were created/modified User can commit when ready

Exception: If user explicitly requests commit, stage and commit:

Output files created Prompts archived Any implementation changes (for Do prompts)

If a prompt's output includes instructions to create more prompts:

This is advanced usage - don't auto-detect Present the output to user User can invoke skill again to create follow-up prompts Maintains user control over prompt creation

Prompt patterns by purpose:

references/do-patterns.md - Execution prompts + output structure references/plan-patterns.md - Planning prompts + plan.md structure references/research-patterns.md - Research prompts + research.md structure references/refine-patterns.md - Iteration prompts + versioning

Shared templates:

references/summary-template.md - SUMMARY.md structure and field requirements references/metadata-guidelines.md - Confidence, dependencies, open questions, assumptions

Supporting references:

references/question-bank.md - Intake questions by purpose references/intelligence-rules.md - Extended thinking, parallel tools, depth decisions

Prompt Creation:

Intake gate completed with purpose and topic identified Chain detection performed, relevant files referenced Prompt generated with correct structure for purpose Folder created in .prompts/ with correct naming Output file location specified in prompt SUMMARY.md requirement included in prompt Metadata requirements included for Research/Plan outputs Quality controls included for Research outputs (verification checklist, QA, pre-submission) Streaming write instructions included for Research outputs Decision tree presented

Execution (if user chooses to run):

Dependencies correctly detected and ordered Prompts executed in correct order (sequential/parallel/mixed) Output validated after each completion SUMMARY.md created with all required sections One-liner is substantive (not generic) Failed prompts handled gracefully with recovery options Successful prompts archived to completed/ subfolder SUMMARY.md displayed inline in results Results presented with decisions/blockers flagged

Research Quality (for Research prompts):

Verification checklist completed Quality report distinguishes verified from assumed claims Sources consulted listed with URLs Confidence levels assigned to findings Critical claims verified with official documentation