@ckelsoe/prompt-architect 3.0.0

package/skills/prompt-architect/assets/templates/bab_template.txt

@@ -0,0 +1,15 @@
+BEFORE:
+[Describe the current state — what exists now, what's wrong with it, what needs to change.
+Be specific: quote actual content, describe current problems, name limitations.]
+
+AFTER:
+[Describe the desired end state — what it should look like once transformed.
+Include: qualities it should have, audience/consumer of the result, success criteria.]
+
+BRIDGE:
+[Define the transformation rules — how to get from Before to After.
+Include:
+- What must be preserved (do not change)
+- What should change
+- Any constraints on approach or style
+- Tone, length, or format requirements for the result]

package/skills/prompt-architect/assets/templates/broke_template.txt

@@ -0,0 +1,15 @@
+BACKGROUND:
+[Current situation, why this task exists, relevant history and constraints]
+
+ROLE:
+[Professional persona and expertise to embody]
+
+OBJECTIVE:
+[The specific task and deliverable]
+
+KEY RESULTS:
+[Measurable outcomes this output should help achieve — how success is defined in business terms]
+
+EVOLVE:
+After completing your response, provide 3 specific suggestions for improving
+this output or approach in a follow-up iteration.

package/skills/prompt-architect/assets/templates/cai-critique-revise_template.txt

@@ -0,0 +1,18 @@
+PRINCIPLE:
+[State the specific standard the output must satisfy — be precise and measurable]
+
+INITIAL OUTPUT:
+[The output to evaluate — AI-generated or human-written]
+
+CRITIQUE:
+Identify specific ways the output above violates or falls short of the
+principle stated above.
+- Quote the specific passages that are problematic
+- Explain precisely why each passage violates the principle
+- Focus only on failures against the principle (not general quality)
+
+REVISION:
+Rewrite the output to fully satisfy the principle.
+- Address every critique point identified above
+- Preserve all content that already satisfies the principle
+- Do not introduce new violations of the principle

package/skills/prompt-architect/assets/templates/care_template.txt

@@ -0,0 +1,16 @@
+CONTEXT:
+[Who you are, the situation you're in, and why this task exists]
+
+ASK:
+[The specific request and deliverable]
+
+RULES:
+[Explicit constraints governing the output:
+- What must be included
+- What must be avoided
+- Format and length requirements
+- Tone and reading level standards
+- Quality bar or compliance requirements]
+
+EXAMPLES:
+[1-3 examples showing the desired output format, tone, or quality standard]

package/skills/prompt-architect/assets/templates/chain-of-density_template.txt

@@ -0,0 +1,46 @@
+=== CHAIN OF DENSITY (CoD) TEMPLATE ===
+
+Use when: iterative compression or quality improvement is the goal —
+          summarization, explanation optimization, content densification.
+
+─────────────────────────────────────────────
+SOURCE CONTENT:
+[Paste the content to be refined/compressed here]
+
+─────────────────────────────────────────────
+OPTIMIZATION GOAL:
+[What should improve with each pass?]
+Examples:
+- "Reduce word count by 20% each pass while retaining all key information"
+- "Increase information density — remove filler, make every sentence earn its place"
+- "Improve clarity — each pass should be more direct and easier to understand"
+
+─────────────────────────────────────────────
+NUMBER OF ITERATIONS:
+[How many refinement passes? Typical: 2-4]
+Iteration 1: [First pass — initial improvement]
+Iteration 2: [Second pass — tighten further]
+Iteration 3: [Optional — final polish]
+
+─────────────────────────────────────────────
+ITERATION INSTRUCTIONS:
+For each iteration:
+1. Identify what can be cut, compressed, or clarified
+2. Apply the changes
+3. Verify: does this version better meet the optimization goal than the previous?
+4. Stop when: [define your stopping criterion]
+   Examples: "length < 150 words", "no filler words remain", "3 iterations complete"
+
+─────────────────────────────────────────────
+OUTPUT FORMAT:
+[What format should the final result be in?]
+Examples: paragraph, bullet list, 1-sentence summary, structured sections
+
+─────────────────────────────────────────────
+OPTIONAL — SHOW INTERMEDIATE VERSIONS:
+Set to YES if you want to see each iteration's output.
+Set to NO if you only want the final result.
+
+─────────────────────────────────────────────
+NOTE: Use Self-Refine when the improvement goal is multi-dimensional quality
+(e.g., accuracy + tone + completeness). CoD is specifically for density/compression.

package/skills/prompt-architect/assets/templates/chain-of-thought_template.txt

@@ -0,0 +1,49 @@
+=== CHAIN OF THOUGHT (CoT) TEMPLATE ===
+
+Use when: step-by-step reasoning is needed, logic must be shown,
+          or intermediate conclusions feed into the final answer.
+
+─────────────────────────────────────────────
+PROBLEM / QUESTION:
+[State the problem clearly. Include all relevant numbers, conditions,
+or constraints — everything needed to reason from.]
+
+─────────────────────────────────────────────
+REASONING INSTRUCTION:
+Solve this step-by-step. For each step:
+1. State what you're doing and why
+2. Show your work / intermediate calculation / intermediate conclusion
+3. Verify it before moving to the next step
+
+─────────────────────────────────────────────
+STEPS:
+Step 1: [First reasoning step]
+→ Result: [intermediate conclusion or value]
+
+Step 2: [Next reasoning step, building on Step 1]
+→ Result: [intermediate conclusion or value]
+
+Step 3: [Continue as needed...]
+→ Result: [...]
+
+─────────────────────────────────────────────
+VERIFICATION:
+Before finalizing: check that each step follows logically,
+no conditions were overlooked, and the conclusion matches the question asked.
+
+─────────────────────────────────────────────
+FINAL ANSWER:
+[State the answer clearly after the reasoning chain is complete]
+
+─────────────────────────────────────────────
+TRIGGER VARIANTS (zero-shot alternatives):
+
+Simple:     "Think step by step."
+Explicit:   "Solve this step-by-step, showing your reasoning at each stage."
+Verified:   "Work through this step-by-step, verify each step before continuing,
+             then state your final answer."
+Few-shot:   Prefix with 1-2 worked examples before the actual problem.
+
+NOTE: For numerical/calculation problems, prefer Plan-and-Solve (PS+).
+      For multi-hop problems with dependencies, prefer Least-to-Most.
+      CoT is best for linear step-by-step reasoning on a single problem.

package/skills/prompt-architect/assets/templates/co-star_template.txt

@@ -0,0 +1,17 @@
+CONTEXT:
+[Provide background information, situation, and any relevant constraints. What's the setting? What's happened before? What limitations exist?]
+
+OBJECTIVE:
+[State the clear, specific goal you want to achieve. What exactly do you want accomplished? What does success look like?]
+
+STYLE:
+[Specify the writing style, format preferences, and structural approach. Should it follow a particular style guide? What format is needed?]
+
+TONE:
+[Define the emotional quality and attitude. Should it be professional, casual, urgent, friendly, authoritative, empathetic, etc.?]
+
+AUDIENCE:
+[Identify who will consume this output. What's their expertise level? What do they care about? What are their characteristics?]
+
+RESPONSE FORMAT:
+[Specify the expected output structure. How long? What sections? What level of detail? Any specific format requirements?]

package/skills/prompt-architect/assets/templates/crispe_template.txt

@@ -0,0 +1,14 @@
+CAPACITY AND ROLE:
+[Define the expertise level and professional role to embody — be specific about domain and level]
+
+INSIGHT:
+[Background context, relevant data, constraints, and situational knowledge the AI needs]
+
+INSTRUCTIONS:
+[What exactly needs to be done — the specific task and deliverable]
+
+PERSONALITY (STYLE):
+[Tone, voice, communication style, persona — how the output should sound and feel]
+
+EXPERIMENT:
+[Request N variants along a specific dimension — e.g., "Provide 3 versions: one [X], one [Y], one [Z]"]

package/skills/prompt-architect/assets/templates/ctf_template.txt

@@ -0,0 +1,15 @@
+CONTEXT:
+[Describe the situation, background, or circumstances surrounding this task.
+Include relevant details like: current state, constraints, what's already been done,
+why this is needed, and any important background the AI should know.]
+
+TASK:
+[State clearly and specifically what needs to be done. Be explicit about the deliverable.]
+
+FORMAT:
+[Specify exactly how the output should be structured:
+- Overall format (document, code, list, table, etc.)
+- Required sections or components
+- Length constraints
+- Style requirements
+- Any specific formatting rules]

package/skills/prompt-architect/assets/templates/devils-advocate_template.txt

@@ -0,0 +1,25 @@
+You are a rigorous devil's advocate. Your task is NOT to give a balanced view —
+your task is to generate the strongest possible case against the following position.
+
+POSITION TO ATTACK:
+[State the position, plan, decision, or proposal clearly]
+
+ATTACK INSTRUCTIONS:
+- Do not acknowledge positives or offer a balanced view
+- Attack every assumption the position depends on
+- Identify every logical gap or unsupported claim
+- Surface every significant risk or failure mode
+- Point out what better alternatives are being ignored
+- Be as forceful and specific as possible
+
+ATTACK DIMENSIONS:
+Focus on:
+1. Core assumptions (what must be true for this to work?)
+2. Internal logic (where does the reasoning break down?)
+3. Execution risks (what makes this fail in practice?)
+4. Overlooked alternatives (what better options exist?)
+5. [Add domain-specific dimensions as needed]
+
+SEVERITY RANKING:
+After the full attack, list the THREE MOST FATAL flaws — the ones that,
+if unaddressed, would cause this to fail regardless of execution quality.

package/skills/prompt-architect/assets/templates/hybrid_template.txt

@@ -0,0 +1,101 @@
+=== HYBRID / COMBINED FRAMEWORK TEMPLATE ===
+
+Use this when a single framework doesn't fully cover your needs.
+Include only the sections that add value — remove the rest.
+
+─────────────────────────────────────────────
+COMMON COMBINATION PATTERNS
+─────────────────────────────────────────────
+
+[REQUIREMENTS GATHERING → EXECUTION]
+Reverse Role (interview) → any CREATE framework
+Use when: requirements unclear → gather first → then apply CO-STAR/RISEN/RACE/etc.
+
+[STRESS-TEST PAIR]
+Devil's Advocate + Pre-Mortem
+Use when: high-stakes decision needs both opposing arguments AND failure analysis
+
+[TRANSFORM THEN VERIFY]
+BAB + Self-Refine
+Use when: rewrite existing content → then quality-loop the result
+
+[PRINCIPLES THEN EXECUTE]
+Step-Back + Chain of Thought
+Use when: need to establish first principles before working through a problem
+
+[RECOVER THEN IMPROVE]
+RPEF + Self-Refine
+Use when: recover a lost prompt → then improve the recovered template
+
+[GENERATE THEN ALIGN]
+CO-STAR/RISEN + CAI Critique-Revise
+Use when: create content → then verify it meets an explicit principle/standard
+
+─────────────────────────────────────────────
+HYBRID TEMPLATE STRUCTURE
+─────────────────────────────────────────────
+
+CONTEXT / BACKGROUND:
+[From CTF / CO-STAR / CARE — situation, background, why this task exists]
+
+ROLE:
+[From RTF / RISEN / RACE / CRISPE — expertise or perspective needed]
+
+OBJECTIVE:
+[From CO-STAR / RISEN — specific goal to achieve]
+
+INPUT (if applicable):
+[From RISE-IE — what's being provided, format, characteristics]
+
+INSTRUCTIONS / STEPS:
+[From RISEN / RISE — guiding principles, methodology, step sequence]
+
+CONSTRAINTS / RULES:
+[From CARE / TIDD-EC / RISEN — what must/must not happen, boundaries]
+
+DO:
+[From TIDD-EC — explicit positive guidance]
+
+DON'T:
+[From TIDD-EC — explicit negative guidance]
+
+AUDIENCE (if relevant):
+[From CO-STAR — who this is for, characteristics]
+
+TONE & STYLE (if relevant):
+[From CO-STAR / CRISPE — voice and communication style]
+
+EXAMPLES (if relevant):
+[From RISE-IX / CARE — reference samples]
+
+KEY RESULTS (if relevant):
+[From BROKE — measurable business outcomes]
+
+END GOAL / EXPECTATION:
+[From RISEN / RACE / BROKE — success criteria, final outcome, output format]
+
+FORMAT:
+[From RTF / CTF / APE — exactly how output should be structured]
+
+─────────────────────────────────────────────
+CRITIQUE / VERIFICATION LAYER (optional)
+─────────────────────────────────────────────
+Add after generation if needed:
+
+FEEDBACK DIMENSIONS (Self-Refine):
+Review for: [dimension 1], [dimension 2], [dimension 3]
+Refine addressing all feedback.
+
+OR
+
+PRINCIPLE (CAI Critique-Revise):
+[State the standard] → Critique → Revise.
+
+OR
+
+POSITION ATTACK (Devil's Advocate):
+Argue against the above recommendation as forcefully as possible.
+
+─────────────────────────────────────────────
+NOTE: Use only sections relevant to your task.
+A hybrid with 4 focused sections beats a hybrid that uses all 15.

package/skills/prompt-architect/assets/templates/least-to-most_template.txt

@@ -0,0 +1,16 @@
+PROBLEM:
+[The full, complex problem to solve]
+
+DECOMPOSE:
+Break this problem into ordered subproblems, from simplest prerequisite to most complex.
+Each later subproblem should build on the answer to the previous.
+
+Subproblem 1: [Simplest prerequisite — must be answered first]
+Subproblem 2: [Builds on #1]
+Subproblem 3: [Builds on #1-2]
+[Add subproblems as needed]
+Final: [The original problem, now solvable using all prior answers]
+
+SOLVE SEQUENTIALLY:
+Solve each subproblem in order. Use prior answers explicitly as context
+for each subsequent subproblem. Show each solution before moving to the next.

package/skills/prompt-architect/assets/templates/plan-and-solve_template.txt

@@ -0,0 +1,7 @@
+PROBLEM:
+[Your question, calculation, or reasoning problem]
+
+Let's first understand the problem, extract relevant variables and their
+corresponding numerals, and devise a complete plan. Then, let's carry out
+the plan, calculate intermediate values, pay attention to computation,
+and solve the problem step by step.

package/skills/prompt-architect/assets/templates/pre-mortem_template.txt

@@ -0,0 +1,27 @@
+PRE-MORTEM ANALYSIS
+
+PROJECT/DECISION:
+[Describe the project, plan, or decision being analyzed — include team size,
+timeline, resources, key goals, and any relevant constraints]
+
+FAILURE ASSUMPTION:
+It is [DATE — e.g., 12 months from now] and [project/decision] has completely
+and catastrophically failed. It did not achieve [primary goal].
+
+FAILURE NARRATIVE:
+Describe the failure in 2-3 sentences from the perspective of someone
+looking back on it.
+
+FAILURE CAUSES:
+Identify [8-12] specific reasons this failed. For each:
+- CAUSE: [What specifically went wrong — be specific, not generic]
+- DOMAIN: [Technical / People / Market / Financial / External / Timeline]
+- WARNING SIGN: [What was the earliest observable indicator this was happening?]
+
+Cover these domains: technical/product, team/organizational, market/adoption,
+financial/resource, external dependencies, timeline/scope.
+
+PRIORITY ASSESSMENT:
+1. The 3 most LIKELY failure causes given our specific situation
+2. The 3 most PREVENTABLE causes where action now would help most
+3. Any single point of failure that could kill the project alone

package/skills/prompt-architect/assets/templates/race_template.txt

@@ -0,0 +1,19 @@
+ROLE:
+[Define the expertise or persona needed — who should do this task and at what level]
+
+ACTION:
+[State clearly what needs to be done — the task and deliverable]
+
+CONTEXT:
+[Provide the situational background:
+- What's the current state / situation?
+- Who is the audience or recipient of the output?
+- Any relevant constraints or prior decisions?
+- What has already been done?]
+
+EXPECTATION:
+[Define what a successful output looks like:
+- Format and structure requirements
+- Quality bar or success criteria
+- What should be prioritized
+- Length or scope constraints]

package/skills/prompt-architect/assets/templates/rcot_template.txt

@@ -0,0 +1,31 @@
+STEP 1 — INITIAL ANSWER:
+Answer the following question using step-by-step reasoning. Show your work.
+
+QUESTION:
+[Your question with all conditions and constraints]
+
+---
+
+STEP 2 — QUESTION RECONSTRUCTION:
+Looking only at your answer above (do not re-read the original question),
+reconstruct the question that would produce this answer.
+List every condition, constraint, and piece of information the question
+must have contained.
+
+---
+
+STEP 3 — CROSS-CHECK:
+Now compare your reconstructed question to the actual original question.
+Identify:
+- Conditions in the ORIGINAL question MISSING from your reconstruction
+  (these are conditions you overlooked in your reasoning)
+- Conditions in your RECONSTRUCTION not in the original question
+  (assumptions you made that weren't stated)
+- Conditions present in both but interpreted differently
+
+---
+
+STEP 4 — CORRECTION:
+If discrepancies were found, generate a corrected answer that addresses
+every condition in the original question.
+If no discrepancies, confirm the original answer is correct.

package/skills/prompt-architect/assets/templates/react_template.txt

@@ -0,0 +1,27 @@
+GOAL:
+[Define the end state to achieve — what does success look like?]
+
+AVAILABLE TOOLS:
+- [tool_name]: [What it does and how to invoke it]
+- [tool_name]: [What it does and how to invoke it]
+- [tool_name]: [What it does and how to invoke it]
+
+CONSTRAINTS:
+- [Rules, limits, or guardrails on actions]
+- [Stop condition: when to stop and deliver Final Answer]
+- [Optional: max iterations or tool call limit]
+
+APPROACH:
+Use the Thought → Action → Observation cycle until the goal is reached:
+
+Thought: [Reason about current state and what to do next]
+Action: [tool_name] — [specific query or operation]
+Observation: [Result of the action]
+
+Thought: [Reason about the observation — what does it mean? what to do next?]
+Action: [tool_name] — [next operation]
+Observation: [Result]
+
+[Continue cycling until goal is achieved or stop condition is met]
+
+Final Answer: [Deliver the result once goal is reached]

package/skills/prompt-architect/assets/templates/reverse-role_template.txt

@@ -0,0 +1,11 @@
+You are an expert [DOMAIN] consultant / specialist.
+
+My goal: [1-2 sentence description of what you want to achieve]
+
+Before you begin, interview me to understand my specific context, constraints,
+goals, and any relevant background. Ask your questions [one at a time / all at once].
+Only proceed with [the task / generating the full prompt] once you are confident
+you have everything you need.
+
+[Optional: After the interview, synthesize my responses into a complete structured
+prompt using the most appropriate framework, then confirm before executing.]

package/skills/prompt-architect/assets/templates/rise-ie_template.txt

@@ -0,0 +1,23 @@
+ROLE:
+[Define the perspective or expertise needed for this task]
+
+INPUT:
+[Specify what data/content is being provided:
+- Format and structure (CSV, JSON, text, etc.)
+- Key characteristics and fields
+- Any quirks or special considerations
+- What to expect in the data]
+
+STEPS:
+1. [How to process the input - first action]
+2. [Processing step 2 - transformation or analysis]
+3. [Processing step 3 - continue with methodology]
+4. [Add more processing/analysis steps as needed...]
+
+EXPECTATION:
+[Define what the output should look like:
+- Format and structure
+- Required elements and sections
+- Level of detail needed
+- Length or size constraints
+- Specific deliverables]

package/skills/prompt-architect/assets/templates/rise-ix_template.txt

@@ -0,0 +1,28 @@
+ROLE:
+[Define who the AI should embody - persona or expertise level]
+
+INSTRUCTIONS:
+[Specify the main task or directive:
+- What to create or accomplish
+- Core requirements
+- Key guidelines to follow
+- Specific constraints or considerations]
+
+STEPS:
+1. [Approach or methodology step 1]
+2. [Step 2 - how to execute the task]
+3. [Step 3 - continue with workflow]
+4. [Add more steps as needed for the creative/instruction process...]
+
+EXAMPLES:
+[Provide positive examples showing desired output:
+- Reference materials that demonstrate the style
+- Format examples to emulate
+- Successful outputs from similar tasks
+- 2-3 concrete examples recommended]
+
+Example 1: [First reference example demonstrating desired output]
+
+Example 2: [Second reference example showing format/style to match]
+
+[Optional] Example 3: [Third example if additional clarity needed]

package/skills/prompt-architect/assets/templates/risen_template.txt

@@ -0,0 +1,21 @@
+ROLE:
+[Define the expertise level, persona, or perspective to adopt. What knowledge should be demonstrated?]
+
+INSTRUCTIONS:
+[Provide high-level guidance, principles, and overarching direction. What methodology or approach should guide this work?]
+
+STEPS:
+1. [First specific action or stage]
+2. [Second specific action or stage]
+3. [Third specific action or stage]
+[Continue with detailed, sequential steps...]
+
+END GOAL:
+[Define success criteria and final desired outcome. What should be true when complete? How will we know it's done correctly?]
+
+NARROWING:
+- Do NOT: [Specific thing to avoid]
+- Avoid: [Approach or pattern to avoid]
+- Out of scope: [What's not included]
+- Stay within: [Boundaries and constraints]
+- Constraints: [Limitations to respect]

package/skills/prompt-architect/assets/templates/rpef_template.txt

@@ -0,0 +1,26 @@
+You are an expert Prompt Engineer performing reverse prompt engineering.
+
+TASK:
+Analyze the following [input and] output. Reconstruct the prompt that would
+consistently produce this type of output. Your recovered prompt should be
+reusable — replace specific details with clearly marked [PLACEHOLDER] variables.
+
+[INPUT DATA (if applicable — omit if output-only):]
+[Paste the input that produced the output, or remove this section]
+
+OUTPUT SAMPLE:
+[Paste the output you want to reverse-engineer]
+
+ANALYSIS INSTRUCTIONS:
+Examine the output for:
+- Implied role or persona
+- Tone and voice
+- Structural and formatting patterns
+- Level of detail and scope
+- Implicit constraints (what it did NOT do)
+- Reasoning style
+
+RECOVERED PROMPT:
+Generate a reusable prompt template that reliably reproduces this type of output.
+Use [PLACEHOLDER] for variable elements.
+Only proceed when at least 80% confident in the reconstruction.

package/skills/prompt-architect/assets/templates/rtf_template.txt

@@ -0,0 +1,13 @@
+ROLE:
+[Define the expertise or perspective needed for this task]
+
+TASK:
+[State clearly and specifically what needs to be done. Be explicit about the deliverable.]
+
+FORMAT:
+[Specify exactly how the output should be structured:
+- Overall format (document, code, list, table, etc.)
+- Required sections or components
+- Length constraints
+- Style requirements
+- Any specific formatting rules]

package/skills/prompt-architect/assets/templates/self-refine_template.txt

@@ -0,0 +1,16 @@
+INITIAL OUTPUT:
+[Paste the output to improve, or ask the AI to generate a first draft here]
+
+FEEDBACK DIMENSIONS:
+Review the output above for:
+1. [Dimension 1 — e.g., "Clarity: Are there any ambiguous or hard-to-parse sentences?"]
+2. [Dimension 2 — e.g., "Completeness: What important points are missing?"]
+3. [Dimension 3 — e.g., "Tone: Is the voice appropriate for the audience?"]
+4. [Dimension 4 — add or remove as needed]
+
+For each dimension: quote specific problematic passages, explain the issue,
+and suggest a concrete improvement.
+
+REFINEMENT:
+Rewrite the output addressing every point of your feedback above.
+Show the refined version only.

package/skills/prompt-architect/assets/templates/skeleton-of-thought_template.txt

@@ -0,0 +1,15 @@
+PHASE 1 — SKELETON:
+Generate a skeleton outline for the following topic or question.
+List only the key points — one per line — in this format:
+N. [Point name] | [One-sentence description of what this point covers]
+Do not expand yet. Skeleton only.
+
+TOPIC / QUESTION:
+[Your topic or question]
+
+---
+
+PHASE 2 — EXPAND:
+Now expand each skeleton point into [2-4 sentences / a paragraph / detailed coverage].
+Each point should be self-contained and complete.
+[Optional: expand points in parallel by sending each as a separate API call]

package/skills/prompt-architect/assets/templates/step-back_template.txt

@@ -0,0 +1,10 @@
+ORIGINAL QUESTION:
+[The specific question you want answered]
+
+STEP-BACK:
+Before answering directly, first answer this higher-level question:
+[Rephrase the original into a more abstract question about underlying principles, concepts, or rules]
+
+PRINCIPLE APPLICATION:
+Using the principles/concepts you just described, now answer the original question:
+[Restate original question here]