@ckelsoe/prompt-architect 3.3.1 → 3.5.0

package/skills/prompt-architect/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: prompt-architect
-description: Analyzes and improves prompts using 29 frameworks across 7 intent categories. Use when a user wants to improve, rewrite, structure, or engineer a prompt — including requests like "help me write a better prompt", "improve this prompt", "what framework should I use", "make this prompt more effective", or any prompt engineering task. Recommends the right framework based on intent (create, transform, reason, critique, recover, clarify, agentic), asks targeted questions, and delivers a structured, high-quality result.
+description: Analyzes and improves prompts using 31 frameworks across 7 intent categories. Use when a user wants to improve, rewrite, structure, or engineer a prompt — including requests like "help me write a better prompt", "improve this prompt", "what framework should I use", "make this prompt more effective", or any prompt engineering task. Recommends the right framework based on intent (create, transform, reason, critique, recover, clarify, agentic), asks targeted questions, and delivers a structured, high-quality result.
 license: MIT
 compatibility: Requires no external dependencies. Works with any Agent Skills compatible tool.
 metadata:
   author: ckelsoe
-  version: "3.3.1"
+  version: "3.5.0"
   homepage: https://github.com/ckelsoe/prompt-architect
 ---
 
@@ -40,7 +40,9 @@ Score the prompt *as written*, not as you charitably interpret it — the gap be
 
 ### 2. Intent-Based Framework Selection
 
-With 29 frameworks, identify the user's **primary intent** first, then use the discriminating questions within that category.
+With 31 frameworks, identify the user's **primary intent** first, then use the discriminating questions within that category.
+
+**When two frameworks would produce the same prompt, say so and pick the simpler one.** Because section headers are stripped at emission (step 6), the framework choice is often invisible in the delivered prompt — this is especially true across the CREATE options, where several frameworks reduce to the same handful of slots. When you cannot point to a concrete difference the *emitted* prompt would show, do not manufacture one: name the tie plainly, choose the simpler framework, and move on. A confident rationale for an unobservable choice is exactly the overstatement this skill exists to remove.
 
 ---
 
@@ -98,6 +100,7 @@ With 29 frameworks, identify the user's **primary intent** first, then use the d
 | Multiple distinct approaches to compare | **Tree of Thought** |
 | Verify reasoning didn't overlook conditions | **RCoT** |
 | Linear step-by-step reasoning | **Chain of Thought** |
+| Answer must be robust; sample many paths and majority-vote | **Self-Consistency** |
 
 ---
 
@@ -110,8 +113,9 @@ With 29 frameworks, identify the user's **primary intent** first, then use the d
 | Find the strongest opposing argument | **Devil's Advocate** |
 | Identify failure modes before they happen | **Pre-Mortem** |
 | Verify reasoning didn't miss conditions | **RCoT** |
+| Draft may contain hallucinated facts; verify each claim | **Chain-of-Verification** |
 
-*Self-Refine = any quality. CAI = principle compliance. Devil's Advocate = opposing arguments. Pre-Mortem = failure analysis. RCoT = condition verification.*
+*Self-Refine = any quality. CAI = compliance with an **explicitly stated** standard or requirement set (and aligning the artifact to it — e.g. auditing a plan against a brief's constraints). Devil's Advocate = opposing arguments. Pre-Mortem = failure analysis. RCoT = an answer or plan overlooked a condition **implicit in the problem** (units, edge cases, unstated dependencies). Chain-of-Verification = independent fact-checking of a draft's factual claims.*
 
 ---
 
@@ -131,7 +135,13 @@ Most prompts need exactly one framework. Combine only when the task genuinely ha
 | Multi-step procedure executed with tools | **RISEN + ReAct** | RISEN specifies the steps and success criteria; ReAct governs the tool-use cycle within each step |
 | Business deliverable with a hostile audience | **BROKE + Devil's Advocate** | BROKE sets objective and key results; Devil's Advocate stress-tests them before they reach a stakeholder |
 
-When you combine, load `assets/templates/hybrid_template.txt` and state plainly in your analysis which framework owns which phase. Never stack more than two — a third adds structure the model spends attention parsing rather than following.
+When you combine, load `assets/templates/hybrid_template.txt` and state plainly in your analysis which framework owns which phase. Never stack more than two — beyond that the frameworks' instructions start to overlap and contradict, and no single framework clearly owns any phase.
+
+#### Composable Techniques
+
+Some techniques are not frameworks you choose *between* — they are layers you add *on top of* whichever framework you picked. They answer "how should this prompt be built?", not "which shape is it?", so they never appear in the routing tables above.
+
+- **Few-shot / in-context examples** — showing 2–5 worked input→output examples inside the emitted prompt. This is the highest-leverage technique in prompting and applies to almost any framework, not just the two with a dedicated examples slot (CARE, RISE-IX). After you draft the framework prompt, decide whether examples earn their place; if they do, insert them before the final instruction, in the exact target output format, and end with the actual task. Load `references/techniques/few-shot.md` for when to use it, how many, ordering and recency effects, and the label-space rules — and for the rule that you never invent examples the user or their material did not supply.
 
 ---
 
@@ -143,53 +153,69 @@ One-line per framework (load `references/frameworks/` for full detail):
 **Medium:** RACE | CARE | BAB | BROKE | CRISPE
 **Comprehensive:** CO-STAR | RISEN | TIDD-EC
 **Data:** RISE-IE | RISE-IX
-**Reasoning:** Plan-and-Solve | Chain of Thought | Least-to-Most | Step-Back | Tree of Thought | RCoT
+**Reasoning:** Plan-and-Solve | Chain of Thought | Least-to-Most | Step-Back | Tree of Thought | RCoT | Self-Consistency
 **Structure/Iteration:** Skeleton of Thought | Chain of Density | Iterative Compression
-**Critique/Quality:** Self-Refine | CAI Critique-Revise | Devil's Advocate | Pre-Mortem
+**Critique/Quality:** Self-Refine | CAI Critique-Revise | Devil's Advocate | Pre-Mortem | Chain-of-Verification
 **Meta/Reverse:** RPEF | Reverse Role Prompting
 **Agentic:** ReAct
 
+**Composable technique (layered onto any framework, not selected between):** Few-shot / in-context examples
+
 ### 4. Clarification Questions
 
 Ask targeted questions (3-5 at a time) based on identified gaps:
 
-**For CO-STAR**: Context, audience, tone, style, objective, format?
-**For RISEN**: Role, principles, steps, success criteria, constraints?
-**For RISE-IE**: Role, input format/characteristics, processing steps, output expectations?
-**For RISE-IX**: Role, task instructions, workflow steps, reference examples?
-**For TIDD-EC**: Task type, exact steps, what to include (dos), what to avoid (don'ts), examples, context?
-**For CTF**: What is the situation/background, exact task, output format?
-**For RTF**: Expertise needed, exact task, output format?
-**For APE**: Core action, why it's needed, what success looks like?
-**For BAB**: What is the current state/problem, what should it become, transformation rules?
-**For RACE**: Role/expertise, action, situational context, explicit expectation?
-**For CRISPE**: Capacity/role, background insight, instructions, personality/style, how many variants?
-**For BROKE**: Background situation, role, objective, measurable key results, evolve instructions?
-**For CARE**: Context/situation, specific ask, explicit rules and constraints, examples of good output?
-**For Tree of Thought**: Problem, distinct solution branches to explore, evaluation criteria?
-**For ReAct**: Goal, available tools, constraints and stop condition?
-**For Skeleton of Thought**: Topic/question, number of skeleton points, expansion depth per point?
-**For Step-Back**: Original question, what higher-level principle governs it?
-**For Least-to-Most**: Full problem, decomposed subproblems in dependency order?
-**For Plan-and-Solve**: Problem with all relevant numbers/variables?
-**For Chain of Thought**: Problem, reasoning steps, verification?
-**For Chain of Density**: Source document to summarize, fixed target length, number of iterations?
-**For Iterative Compression**: Content to compress, target length, optimization goal, stopping criterion?
-**For Self-Refine**: Output to improve, feedback dimensions, stop condition?
-**For CAI Critique-Revise**: The principle to enforce, output to critique?
-**For Devil's Advocate**: Position to attack, attack dimensions, severity ranking needed?
-**For Pre-Mortem**: Project/decision, time horizon, domains to analyze?
-**For RCoT**: Question with all conditions, initial answer to verify?
-**For RPEF**: Output sample to reverse-engineer, input data if available?
-**For Reverse Role**: Intent statement, domain of expertise, interview mode (batch vs. conversational)?
+**For CO-STAR**: Paste the material this is built from if any, the situation and constraints behind it, who the audience is and what you want them to do, the tone and style to write in, the output format and length?
+**For RISEN**: Paste the material the procedure runs on if any, the expertise and methodology to adopt, the steps in order, what must be true when it is done, what is out of scope or must not happen?
+**For RISE-IE**: Paste the actual data to be processed (not a description of it), its format and any quirks to expect, the expertise needed, the processing steps in order, what the output must look like?
+**For RISE-IX**: The expertise to embody, what to create and its core requirements, the workflow steps, paste 2-3 actual samples whose style and format the output should match?
+**For TIDD-EC**: Paste the material this task operates on (the message, document, or dataset itself, not a description of it), what kind of task this is and the background that shapes it, the exact steps in order, what must always be included and what must never happen (state each as a prohibition, not a topic), examples of a good result?
+**For CTF**: Paste the artifact this operates on if you have one, the situation and background around it, the exact task and deliverable, the output format?
+**For RTF**: Paste the material the task applies to if any, the expertise needed, the exact task and deliverable, the output format and length?
+**For APE**: Paste the material the action applies to if any, the one action to perform, why it is needed and who uses the result, what a good result looks like?
+**For BAB**: Paste the actual artifact being transformed, what is wrong with it now, what it should become, what rules govern the transformation?
+**For RACE**: Paste the material the task applies to if any, the role and expertise needed, the action to perform, the situational context and audience, what a successful output looks like?
+**For CRISPE**: The expertise and role to embody, paste the data or style sample it should work from, the background it needs, the exact task and deliverable, the tone and how many variants?
+**For BROKE**: Paste the supporting material or performance data if you have it, the current situation and why this task exists, the role to embody, the specific deliverable and the structure and length the response should have, the measurable business outcome it should move?
+**For CARE**: Paste the source document or draft this works from if any, your situation and why this task exists, the specific ask and deliverable, what must be included and what would make this output wrong or unusable, an example of what good looks like?
+**For Tree of Thought**: The decision or problem and its constraints, paste the evidence the branches must be judged against, the 2-5 distinct approaches to compare, the criteria that decide between them?
+**For ReAct**: Does the environment this runs in actually have callable tools — if not, stop and use Chain of Thought instead, which tools are available and how each is invoked, what end state counts as success, what limits apply and when to stop?
+**For Skeleton of Thought**: The topic or question to outline, paste the document, data, or notes the answer must be drawn from if you have any, who the answer is for and what scope it should cover, how far each point should be expanded (a few sentences, a paragraph, full detail)?
+**For Step-Back**: The specific question you want answered, paste the code, document, or design it is about if any, what higher-level principle or concept governs it?
+**For Least-to-Most**: The full problem in one statement, paste the material the subproblems must reason over, what is the simplest thing that must be answered first, what does the final answer depend on?
+**For Plan-and-Solve**: The problem with every number, unit, and constraint written out, paste the dataset or figures the calculation runs on if any, which values are given and which must be derived?
+**For Chain of Thought**: The problem with all its conditions stated, paste the code, data, or document to reason over if any, what the reasoning steps should be?
+**For Self-Consistency**: The problem with all its conditions stated, paste the data or figures it runs on if any, what the single final answer should look like so every sampled run ends in a comparable `FINAL ANSWER:` line, how many samples to run and majority-vote over (the paper uses 40; 5-10 is usually enough)?
+**For Chain of Density**: Paste the full document to summarize, the fixed word budget every summary must hit, how many densification passes (the paper uses 5)?
+**For Iterative Compression**: Paste the content to compress, where it should end up (word count, reading level, single paragraph), what should improve on each pass, how many passes and when to stop?
+**For Self-Refine**: Paste the actual draft to improve, which dimensions the critique should cover (clarity, completeness, tone), what would make this output wrong or unusable?
+**For CAI Critique-Revise**: Paste the actual output to be critiqued, the specific standard it must satisfy stated precisely enough to be checkable, what would make this output wrong or unusable?
+**For Devil's Advocate**: The position, plan, or decision to attack, paste the proposal or memo that sets it out if you have one, which dimensions the attack should cover?
+**For Pre-Mortem**: The project or decision being analyzed with its team, timeline, and goals, paste the plan or proposal document if you have one, how far in the future the imagined failure should be dated?
+**For RCoT**: The question with every condition and constraint written out, paste the document those conditions come from if any, any implicit requirement not yet written into the question (units, deadlines, exclusions, edge cases) that a correct answer must still satisfy?
+**For Chain-of-Verification**: Paste the draft answer to fact-check if you have one, or the factual question to answer carefully, which specific claims are most at risk of being wrong, what a correct final answer must not get wrong?
+**For RPEF**: Paste the actual output sample to reverse-engineer, paste the input that produced it or confirm it is output-only, which details are one-off specifics that should become [PLACEHOLDER] variables?
+**For Reverse Role**: What you want to achieve in one or two sentences, the domain of expertise to consult, questions one at a time or all at once, should it then do the task or synthesize a structured prompt for you to approve?
+
+Every set above asks for the user's own material, because a framework that operates on an
+artifact and never asks for it will invent one. Three frameworks are deliberately exempt:
+**ReAct** (its material arrives as live tool output, not pasted text), **Reverse Role** (it
+elicits everything through the interview and its template has no material slot), and
+**RISE-IX** (its samples land in the EXAMPLES slot, which its own question already covers).
+Do not add a material question to those three.
 
 ### 5. Apply Framework
 
 Using gathered information:
 1. Load appropriate template from `assets/templates/`
 2. Map user's information to framework components
-3. Fill missing elements with reasonable defaults
+3. Fill missing elements with reasonable defaults — **with two exceptions, below**
 4. Structure according to framework format
+5. **Decide whether worked examples would materially improve the output**; if so, layer in few-shot examples per `references/techniques/few-shot.md` — this applies to any framework, not only the two with a built-in examples slot. Reach for it especially on classification, extraction, strict-format, and style-matching tasks, and only when the user or their material supplies real examples.
+
+**Never default a fact about the user's world.** Their business, metrics, history, policies, staff, customers, data, or constraints are things only they know. A plausible-sounding default here is a fabrication the user may not notice before sending — asserting "our first price increase in three years" in an email to paying customers, or inventing a phone number in a published review reply. Where such a slot is unanswered, emit a visible `[you fill this in: <what is needed>]` placeholder and list every placeholder in your analysis section.
+
+**Never soften or drop a prohibition.** If the user said something must not happen, it must survive into the emitted prompt as an explicit "Do not…" or "Never…" instruction. It cannot rely on a section header to carry the negation, because headers are stripped at emission (see step 6).
 
 ### 6. Present Improvements
 
@@ -211,14 +237,14 @@ Structure your output in this exact order:
 - **No framework section headers** (no "BEFORE:", "BRIDGE:", "CONTEXT:", etc.) — these are scaffolding, not part of the deliverable
 - **No indentation** beyond what the prompt itself genuinely requires
 - **No markdown formatting** inside the block unless the prompt explicitly needs it (e.g., it asks for tables)
-- The user must be able to copy the entire block contents and paste it verbatim with zero editing
+- The user must be able to copy the entire block contents and paste it verbatim with zero editing — the one exception is `[...]` placeholders for material or facts only the user can supply (see step 5). Keep these to a minimum, make each self-explanatory, and name them in the analysis section so the user knows exactly what to fill in before sending.
 - **Nothing after the code block** — the revised prompt must be the absolute last element in the response. No trailing suggestions, tips, or follow-up text after the closing backticks.
 
 ### 7. Iterate
 
 - Confirm improvements align with intent
 - Refine based on feedback
-- Switch or combine frameworks if needed (see **Combining Frameworks** below)
+- Switch or combine frameworks if needed (see **Combining Frameworks** above)
 - Continue until satisfactory
 
 ## Framework References
@@ -252,9 +278,14 @@ Detailed framework docs in `references/frameworks/`:
 - `rcot.md` - Reverse Chain-of-Thought: verify by reconstructing the question
 - `rpef.md` - Reverse Prompt Engineering: recover prompt from output (EMNLP 2025)
 - `reverse-role.md` - AI-Led Interview: AI asks you questions first (FATA)
+- `self-consistency.md` - Sample N reasoning paths, majority-vote externally (Wang et al., ICLR 2023)
+- `chain-of-verification.md` - Draft, plan checks, verify independently, revise (Dhuliawala et al., Findings of ACL 2024)
 
 Load these when applying specific frameworks for detailed component guidance, selection criteria, and examples.
 
+**Composable techniques** (layered onto a framework, not selected from the routing tables) live in `references/techniques/`:
+- `few-shot.md` - In-context examples: when to add them, how many, ordering, label-space rules
+
 ## Templates
 
 Every framework has a fill-in template at `assets/templates/<framework>_template.txt`, named after the framework's reference doc (e.g. `co-star.md` → `co-star_template.txt`). RISE has two: `rise-ie_template.txt` and `rise-ix_template.txt`. One extra template, `hybrid_template.txt`, is for combined-framework prompts (see **Combining Frameworks**).
@@ -316,10 +347,10 @@ This example shows the full intent-based flow — detecting intent, using the di
 > - **Same chat**: Tell the assistant: *"Use the revised prompt you just provided as a new instruction and execute it."*
 
 ```
-Rewrite the following job posting. The current version suffers from corporate-speak, passive voice, overly formal tone, and generic language that doesn't reflect actual team culture.
-
 [Paste the current job posting here]
 
+The job posting above suffers from corporate-speak, passive voice, overly formal tone, and generic language that doesn't reflect actual team culture.
+
 The rewritten version should sound like it was written by engineers, for engineers. Early-career developers should read it and think "I want to work there." It should feel honest, direct, and human — not like legal boilerplate.
 
 Follow these rules:
@@ -329,6 +360,8 @@ Follow these rules:
 - Keep all technical requirements and must-haves verbatim — do not change these.
 - Target reading level: conversational, not academic.
 - Length: same or shorter than the original. Cut fluff, don't add it.
+
+Now rewrite the job posting above.
 ```
 
 ---

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

@@ -1,5 +1,16 @@
-ACTION: [What to do — one clear verb-driven instruction]
+SOURCE MATERIAL:
+[Optional — paste the artifact the task operates on here, named concretely (the meeting
+transcript, the function). If the task creates something from scratch, delete this
+bracketed block along with the sentence directly below it.]
+Use the material above as the input for the task described below.
 
-PURPOSE: [Why it's needed — one sentence on how it will be used or who needs it]
+ACTION:
+[One complete imperative sentence naming what to produce, e.g. "Summarize the decisions in
+the transcript above." Never a bare noun phrase like "meeting summary" — nothing else here
+states the task. The two fields below may be fragments.]
 
-EXPECTATION: [What a good result looks like — format, length, quality bar, or tone]
+PURPOSE:
+Calibrate the result to this purpose: [who needs it and what they will do with it].
+
+EXPECTATION:
+A good result meets this standard: [the success bar — length, format, tone, or quality].

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

@@ -1,15 +1,28 @@
+SOURCE MATERIAL:
+[Paste the artifact to be transformed here — the artifact itself, never a description of it.
+Name it concretely and keep it bracketed for the user to fill in, e.g. "[Paste the current
+job posting here]".]
+Use the material above as the material to be transformed for the work described below.
+
 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.]
+This is the state that material is in now, and why it must change:
+[Describe the current state in complete sentences, not a bare noun phrase. Say what exists
+now, what is wrong with it, and what needs to change. Quote the material above wherever a
+specific flaw is visible in it.]
 
 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.]
+This is what it must become once the transformation is complete:
+[Describe the desired end state in complete sentences. Cover the qualities the result must
+have and the criteria that make it successful. Name the audience only if the user identified
+one; otherwise leave "[you fill this in: who will read the result]".]
 
 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]
+Follow these rules when carrying out the transformation:
+[State each rule as a self-contained imperative carrying its own verb — "Preserve every salary
+and benefits detail exactly as written", not "salary details". Write prohibitions as
+"Do not…" or "Never…". Cover:
+- What must be preserved unchanged, and what should change
+- Any constraint on approach, style, tone, length, or format]
+
+Now [state the transformation as an imperative naming the material, e.g. "rewrite the job
+posting above"].

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

@@ -1,15 +1,40 @@
+This is a business task with a defined success bar. Everything below describes one
+deliverable.
+
+SOURCE MATERIAL:
+[Optional — paste the material this task works from here, named specifically: the current
+process document, the performance data, the existing draft. If you have nothing to paste,
+delete this bracketed block along with the sentence directly below it.]
+Use the material above as the factual basis for the work described below.
+
 BACKGROUND:
-[Current situation, why this task exists, relevant history and constraints]
+Here is the situation this task arises from:
+[Describe the current state as narrative prose: what the organization is, what is
+happening now, and why this task exists. Add prior attempts and constraints only where the
+user supplied them; never invent them.]
 
 ROLE:
-[Professional persona and expertise to embody]
+Take on this professional persona for the work:
+[One second-person sentence beginning "You are…", naming the domain expertise and level of
+experience this task requires.]
 
 OBJECTIVE:
-[The specific task and deliverable]
+Your task is to do the following:
+[One imperative sentence naming what to analyze or produce and what the finished artifact
+is.]
+
+OUTPUT FORMAT:
+Deliver your response in this shape:
+[Name the sections the response should contain, its approximate length or item count, and
+how much supporting detail each part carries.]
 
 KEY RESULTS:
-[Measurable outcomes this output should help achieve — how success is defined in business terms]
+Your response will be judged on whether it can plausibly move the measurable outcomes
+below. They are the success bar, not tasks to carry out:
+[List each outcome as a statement naming the metric and its target. Add a baseline or time
+frame only where the user gave one; never invent one — write "[you fill this in: current
+value of <metric>]" instead.]
 
 EVOLVE:
-After completing your response, provide 3 specific suggestions for improving
-this output or approach in a follow-up iteration.
+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

@@ -1,18 +1,26 @@
+You are enforcing a stated principle against an existing piece of writing. This is a
+two-phase task: write a critique, then write a revision. Do not skip the critique and go
+straight to the rewrite, and do not merge the two.
+
 PRINCIPLE:
-[State the specific standard the output must satisfy — be precise and measurable]
+The principle to enforce is this:
+[State the standard the output must satisfy — one principle or a small set — as complete
+sentences whose compliance a reader could check. Be precise and measurable.]
 
-INITIAL OUTPUT:
-[The output to evaluate — AI-generated or human-written]
+SOURCE MATERIAL:
+[Paste the output to be critiqued here — AI-generated or human-written.]
+Use the material above as the text to be critiqued and revised for the work described
+below.
 
 CRITIQUE:
-Identify specific ways the output above violates or falls short of the
-principle stated above.
+Before rewriting anything, identify the specific ways the material above violates or falls
+short of the principle.
 - 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)
+- Focus only on failures against the principle, not general quality
 
 REVISION:
-Rewrite the output to fully satisfy the principle.
+Then rewrite the material above so it fully satisfies the principle.
 - Address every critique point identified above
 - Preserve all content that already satisfies the principle
-- Do not introduce new violations of the principle
+- Do not introduce new violations

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

@@ -1,3 +1,7 @@
+SOURCE MATERIAL:
+[Optional — include only if this task works from material you already have. Paste the source document, data, or draft this task operates on here. If you have nothing to paste, delete this bracketed block along with the sentence directly below it.]
+Use the material above as the factual basis for the work described below.
+
 CONTEXT:
 [Who you are, the situation you're in, and why this task exists]
 

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

@@ -1,33 +1,39 @@
 === CHAIN OF DENSITY (CoD) TEMPLATE ===
 
+Everything down to the first divider rule is guidance for whoever assembles this
+prompt and never belongs in the finished prompt. The prompt itself runs from that
+divider to the end of the file: fill in every bracketed field there, and drop the
+section headers and divider rules when emitting it. 'Step 1.', 'Step 2.' and
+'Guidelines:' are literal labels in this protocol, not headings — keep them exactly
+as written. [TARGET] is the fixed word budget and [N] the number of summaries, both
+as bare numerals; substitute the same numeral at every occurrence of each.
+
 Use when: summarizing a document and you want maximum information in a fixed
           length — articles, papers, reports, executive summaries, abstracts.
 
 NOT for: general rewriting (use Self-Refine), or progressive shortening to a
          target word count (use Iterative Compression). CoD holds length FIXED
-         and raises density. If your text is getting shorter, this is the
+         and raises density — if your text is getting shorter, this is the
          wrong template.
 
 Based on Adams et al., "From Sparse to Dense: GPT-4 Summarization with Chain of
-Density Prompting" (arXiv 2309.04269, NewSum @ EMNLP 2023).
-
-─────────────────────────────────────────────
-SOURCE ARTICLE:
-[Paste the full document to be summarized here]
+Density Prompting" (arXiv 2309.04269, NewSum @ EMNLP 2023). The paper's settings are
+[TARGET] = 80 and [N] = 5; fewer summaries works, more gives diminishing returns. Use
+those if the user gave no numbers of their own.
 
-─────────────────────────────────────────────
-TARGET LENGTH:
-[The fixed word budget every summary must hit. Paper uses ~80 words.]
+The padded first summary is intentional, not a mistake — the filler is the slack that
+later iterations convert into entities. A dense first summary leaves no room and the
+chain stalls.
 
 ─────────────────────────────────────────────
-NUMBER OF ITERATIONS:
-[Paper uses 5. Fewer works; more gives diminishing returns.]
+SOURCE MATERIAL:
+[Paste the full document to be summarized here.]
+Use the material above as the article to be summarized for the work described below.
 
 ─────────────────────────────────────────────
-THE PROMPT — copy from here down, with the fields above filled in:
-
-You will generate increasingly concise, entity-dense summaries of the above
-article.
+You will generate increasingly concise, entity-dense summaries of the article above.
+Produce [N] summaries in total, each denser than the last, all in a single response.
+Every summary must be exactly [TARGET] words long.
 
 Repeat the following 2 steps [N] times.
 
@@ -45,9 +51,9 @@ A missing entity is:
 
 Guidelines:
 - The first summary should be long (4-5 sentences, ~[TARGET] words) yet highly
-  non-specific, containing little information beyond the entities marked as
-  missing. Use overly verbose language and fillers (e.g., "this article
-  discusses") to reach ~[TARGET] words.
+  non-specific, containing little information beyond the entities marked as missing.
+  Use overly verbose language and fillers (e.g., "this article discusses") to reach
+  ~[TARGET] words.
 - Make every word count: re-write the previous summary to improve flow and make
   space for additional entities.
 - Make space with fusion, compression, and removal of uninformative phrases like
@@ -60,17 +66,10 @@ Guidelines:
 
 Remember, use the exact same number of words for each summary.
 
-Answer in JSON. The JSON should be a list (length [N]) of dictionaries whose keys
-are "Missing_Entities" and "Denser_Summary".
-
-─────────────────────────────────────────────
-CHOOSING THE OUTPUT:
-Do not automatically take the last summary. In the paper's human evaluation,
-step 2 (30.8% of first-place votes) and step 3 (23.0%) were preferred over the
-sparse step 1 (8.3%). Past a point, density costs readability. Compare the steps
-and pick deliberately.
+Answer in JSON. The JSON should be a list (length [N]) of dictionaries whose keys are
+"Missing_Entities" and "Denser_Summary".
 
-─────────────────────────────────────────────
-NOTE: The deliberately padded first summary is intentional, not a mistake. The
-filler is the slack that later iterations convert into entities. A dense first
-summary leaves no room and the chain stalls.
+After the JSON, and outside it, add one short paragraph naming which summary you
+recommend and why. Do not default to the last one: in the paper's human evaluation,
+summary 2 (30.8% of first-place votes) and summary 3 (23.0%) were preferred over the
+sparse summary 1 (8.3%), because past a point density costs readability.

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

@@ -8,6 +8,14 @@ PROBLEM / QUESTION:
 [State the problem clearly. Include all relevant numbers, conditions,
 or constraints — everything needed to reason from.]
 
+─────────────────────────────────────────────
+SOURCE MATERIAL:
+[Optional — paste the material the problem refers to here (the code, data,
+document, or transcript to reason over). If the problem stated above is fully
+self-contained, delete this bracketed block and the sentence below it.]
+The reasoning that follows must work from the material above, not from
+assumptions about it.
+
 ─────────────────────────────────────────────
 REASONING INSTRUCTION:
 Solve this step-by-step. For each step:

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

@@ -0,0 +1,26 @@
+SOURCE MATERIAL:
+[Optional — paste the draft answer you want fact-checked here, OR the factual
+question you want answered with verification built in. If you are asking a fresh
+question rather than checking an existing draft, delete this bracketed block and
+the sentence directly below it.]
+Treat the material above as the subject to be verified in the steps below.
+
+Work through the following four steps in order, in a single response.
+
+First, write a baseline answer to the question. Do not polish it — this draft is
+what you will fact-check. (If a draft was supplied above, treat that draft as your
+baseline answer instead of writing a new one.)
+
+Second, list the specific factual claims your draft makes — every name, date,
+quantity, entity, and list member — and write one short verification question for
+each claim. Each question must target one claim and be answerable on its own; do
+not write a single broad question that re-asks the whole task.
+
+Third, answer each verification question independently. Do not look back at your
+draft while answering these questions — answer each one on its own, as if seeing
+it fresh, so your checks are not biased into agreeing with whatever the draft
+already says.
+
+Fourth, write a final verified answer. Keep every claim your independent answers
+confirmed, correct every claim they contradicted, and drop any claim you could
+not verify. Note briefly what changed from the draft.

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

@@ -1,3 +1,11 @@
+SOURCE MATERIAL:
+[OPTIONAL — include only if the content is built from material the user already has.
+If so, emit a literal paste instruction naming the specific artifact, e.g. "[Paste the Q3 revenue report here]"
+or "[Paste the blog post whose voice should be matched here]" — never a generic word like "content" —
+then one line of prose tying it to what follows, e.g. "Use the material above as the factual and stylistic
+basis for what you produce; do not invent details it does not support."
+If the content is written entirely from scratch, omit this section — do not emit an empty placeholder.]
+
 CONTEXT:
 [Provide background information, situation, and any relevant constraints. What's the setting? What's happened before? What limitations exist?]
 

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

@@ -1,3 +1,9 @@
+SOURCE MATERIAL:
+[Optional — paste the material the briefing draws on here, named concretely (the customer
+research deck, the writing sample whose voice should be matched). If you have nothing to
+paste, delete this bracketed block along with the sentence directly below it.]
+Use the material above as the factual and stylistic basis for the work described below.
+
 CAPACITY AND ROLE:
 [Define the expertise level and professional role to embody — be specific about domain and level]
 

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

@@ -1,3 +1,11 @@
+SOURCE MATERIAL:
+[Optional — include only if this task operates on material you already have. Paste the
+specific artifact here and name it in this line, e.g. "Paste the legacy authentication
+function here", "Paste the revised requirements doc here" — the artifact itself, not a
+description of it. If this task generates from scratch, delete this bracketed block along
+with the sentence directly below it.]
+Use the material above as the basis for the task described below.
+
 CONTEXT:
 [Describe the situation, background, or circumstances surrounding this task.
 Include relevant details like: current state, constraints, what's already been done,

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

@@ -4,6 +4,13 @@ your task is to generate the strongest possible case against the following posit
 POSITION TO ATTACK:
 [State the position, plan, decision, or proposal clearly]
 
+SUPPORTING MATERIAL (optional):
+[Optional — paste the proposal, design doc, strategy memo, or other document
+that sets out this position here. If you have nothing to paste, delete this
+bracketed block and the sentence below it.]
+Treat the document above as the detailed source of the position's claims,
+assumptions, and reasoning.
+
 ATTACK INSTRUCTIONS:
 - Do not acknowledge positives or offer a balanced view
 - Attack every assumption the position depends on