@ckelsoe/prompt-architect 3.0.2 → 3.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/marketplace.json +1 -1
- package/.claude-plugin/plugin.json +1 -1
- package/CHANGELOG.md +264 -264
- package/LICENSE +21 -21
- package/README.md +1064 -1184
- package/adapters/README.md +75 -267
- package/adapters/for-windsurf.md +136 -136
- package/adapters/system-prompt.md +243 -243
- package/package.json +139 -138
- package/scripts/build-skill.js +64 -0
- package/scripts/install.js +4 -54
- package/scripts/test.js +205 -213
- package/scripts/validate-skill.js +350 -350
- package/skills/prompt-architect/SKILL.md +331 -331
- package/skills/prompt-architect/assets/templates/ape_template.txt +5 -5
- package/skills/prompt-architect/assets/templates/bab_template.txt +15 -15
- package/skills/prompt-architect/assets/templates/broke_template.txt +15 -15
- package/skills/prompt-architect/assets/templates/cai-critique-revise_template.txt +18 -18
- package/skills/prompt-architect/assets/templates/care_template.txt +16 -16
- package/skills/prompt-architect/assets/templates/chain-of-density_template.txt +46 -46
- package/skills/prompt-architect/assets/templates/chain-of-thought_template.txt +49 -49
- package/skills/prompt-architect/assets/templates/co-star_template.txt +17 -17
- package/skills/prompt-architect/assets/templates/crispe_template.txt +14 -14
- package/skills/prompt-architect/assets/templates/ctf_template.txt +15 -15
- package/skills/prompt-architect/assets/templates/devils-advocate_template.txt +25 -25
- package/skills/prompt-architect/assets/templates/hybrid_template.txt +101 -101
- package/skills/prompt-architect/assets/templates/least-to-most_template.txt +16 -16
- package/skills/prompt-architect/assets/templates/plan-and-solve_template.txt +7 -7
- package/skills/prompt-architect/assets/templates/pre-mortem_template.txt +27 -27
- package/skills/prompt-architect/assets/templates/race_template.txt +19 -19
- package/skills/prompt-architect/assets/templates/rcot_template.txt +31 -31
- package/skills/prompt-architect/assets/templates/react_template.txt +27 -27
- package/skills/prompt-architect/assets/templates/reverse-role_template.txt +11 -11
- package/skills/prompt-architect/assets/templates/rise-ie_template.txt +23 -23
- package/skills/prompt-architect/assets/templates/rise-ix_template.txt +28 -28
- package/skills/prompt-architect/assets/templates/risen_template.txt +21 -21
- package/skills/prompt-architect/assets/templates/rpef_template.txt +26 -26
- package/skills/prompt-architect/assets/templates/rtf_template.txt +13 -13
- package/skills/prompt-architect/assets/templates/self-refine_template.txt +16 -16
- package/skills/prompt-architect/assets/templates/skeleton-of-thought_template.txt +15 -15
- package/skills/prompt-architect/assets/templates/step-back_template.txt +10 -10
- package/skills/prompt-architect/assets/templates/tidd-ec_template.txt +45 -45
- package/skills/prompt-architect/assets/templates/tree-of-thought_template.txt +30 -30
- package/skills/prompt-architect/references/frameworks/ape.md +200 -200
- package/skills/prompt-architect/references/frameworks/bab.md +242 -242
- package/skills/prompt-architect/references/frameworks/broke.md +242 -242
- package/skills/prompt-architect/references/frameworks/cai-critique-revise.md +230 -230
- package/skills/prompt-architect/references/frameworks/care.md +235 -235
- package/skills/prompt-architect/references/frameworks/chain-of-density.md +479 -479
- package/skills/prompt-architect/references/frameworks/chain-of-thought.md +424 -424
- package/skills/prompt-architect/references/frameworks/co-star.md +256 -256
- package/skills/prompt-architect/references/frameworks/crispe.md +253 -253
- package/skills/prompt-architect/references/frameworks/ctf.md +207 -207
- package/skills/prompt-architect/references/frameworks/devils-advocate.md +206 -206
- package/skills/prompt-architect/references/frameworks/least-to-most.md +226 -226
- package/skills/prompt-architect/references/frameworks/plan-and-solve.md +210 -210
- package/skills/prompt-architect/references/frameworks/pre-mortem.md +197 -197
- package/skills/prompt-architect/references/frameworks/race.md +243 -243
- package/skills/prompt-architect/references/frameworks/rcot.md +203 -203
- package/skills/prompt-architect/references/frameworks/react.md +304 -304
- package/skills/prompt-architect/references/frameworks/reverse-role.md +189 -189
- package/skills/prompt-architect/references/frameworks/rise.md +555 -555
- package/skills/prompt-architect/references/frameworks/risen.md +297 -297
- package/skills/prompt-architect/references/frameworks/rpef.md +195 -195
- package/skills/prompt-architect/references/frameworks/rtf.md +358 -358
- package/skills/prompt-architect/references/frameworks/self-refine.md +205 -205
- package/skills/prompt-architect/references/frameworks/skeleton-of-thought.md +186 -186
- package/skills/prompt-architect/references/frameworks/step-back.md +206 -206
- package/skills/prompt-architect/references/frameworks/tidd-ec.md +470 -470
- package/skills/prompt-architect/references/frameworks/tree-of-thought.md +260 -260
- package/skills/prompt-architect/scripts/framework_analyzer.py +807 -807
- package/skills/prompt-architect/scripts/prompt_evaluator.py +336 -336
- package/adapters/for-cursor.mdc +0 -138
- package/adapters/for-gemini-cli.md +0 -70
- package/adapters/for-github-copilot.md +0 -141
- package/adapters/for-openai-codex-cli.md +0 -158
|
@@ -1,26 +1,26 @@
|
|
|
1
|
-
You are an expert Prompt Engineer performing reverse prompt engineering.
|
|
2
|
-
|
|
3
|
-
TASK:
|
|
4
|
-
Analyze the following [input and] output. Reconstruct the prompt that would
|
|
5
|
-
consistently produce this type of output. Your recovered prompt should be
|
|
6
|
-
reusable — replace specific details with clearly marked [PLACEHOLDER] variables.
|
|
7
|
-
|
|
8
|
-
[INPUT DATA (if applicable — omit if output-only):]
|
|
9
|
-
[Paste the input that produced the output, or remove this section]
|
|
10
|
-
|
|
11
|
-
OUTPUT SAMPLE:
|
|
12
|
-
[Paste the output you want to reverse-engineer]
|
|
13
|
-
|
|
14
|
-
ANALYSIS INSTRUCTIONS:
|
|
15
|
-
Examine the output for:
|
|
16
|
-
- Implied role or persona
|
|
17
|
-
- Tone and voice
|
|
18
|
-
- Structural and formatting patterns
|
|
19
|
-
- Level of detail and scope
|
|
20
|
-
- Implicit constraints (what it did NOT do)
|
|
21
|
-
- Reasoning style
|
|
22
|
-
|
|
23
|
-
RECOVERED PROMPT:
|
|
24
|
-
Generate a reusable prompt template that reliably reproduces this type of output.
|
|
25
|
-
Use [PLACEHOLDER] for variable elements.
|
|
26
|
-
Only proceed when at least 80% confident in the reconstruction.
|
|
1
|
+
You are an expert Prompt Engineer performing reverse prompt engineering.
|
|
2
|
+
|
|
3
|
+
TASK:
|
|
4
|
+
Analyze the following [input and] output. Reconstruct the prompt that would
|
|
5
|
+
consistently produce this type of output. Your recovered prompt should be
|
|
6
|
+
reusable — replace specific details with clearly marked [PLACEHOLDER] variables.
|
|
7
|
+
|
|
8
|
+
[INPUT DATA (if applicable — omit if output-only):]
|
|
9
|
+
[Paste the input that produced the output, or remove this section]
|
|
10
|
+
|
|
11
|
+
OUTPUT SAMPLE:
|
|
12
|
+
[Paste the output you want to reverse-engineer]
|
|
13
|
+
|
|
14
|
+
ANALYSIS INSTRUCTIONS:
|
|
15
|
+
Examine the output for:
|
|
16
|
+
- Implied role or persona
|
|
17
|
+
- Tone and voice
|
|
18
|
+
- Structural and formatting patterns
|
|
19
|
+
- Level of detail and scope
|
|
20
|
+
- Implicit constraints (what it did NOT do)
|
|
21
|
+
- Reasoning style
|
|
22
|
+
|
|
23
|
+
RECOVERED PROMPT:
|
|
24
|
+
Generate a reusable prompt template that reliably reproduces this type of output.
|
|
25
|
+
Use [PLACEHOLDER] for variable elements.
|
|
26
|
+
Only proceed when at least 80% confident in the reconstruction.
|
|
@@ -1,13 +1,13 @@
|
|
|
1
|
-
ROLE:
|
|
2
|
-
[Define the expertise or perspective needed for this task]
|
|
3
|
-
|
|
4
|
-
TASK:
|
|
5
|
-
[State clearly and specifically what needs to be done. Be explicit about the deliverable.]
|
|
6
|
-
|
|
7
|
-
FORMAT:
|
|
8
|
-
[Specify exactly how the output should be structured:
|
|
9
|
-
- Overall format (document, code, list, table, etc.)
|
|
10
|
-
- Required sections or components
|
|
11
|
-
- Length constraints
|
|
12
|
-
- Style requirements
|
|
13
|
-
- Any specific formatting rules]
|
|
1
|
+
ROLE:
|
|
2
|
+
[Define the expertise or perspective needed for this task]
|
|
3
|
+
|
|
4
|
+
TASK:
|
|
5
|
+
[State clearly and specifically what needs to be done. Be explicit about the deliverable.]
|
|
6
|
+
|
|
7
|
+
FORMAT:
|
|
8
|
+
[Specify exactly how the output should be structured:
|
|
9
|
+
- Overall format (document, code, list, table, etc.)
|
|
10
|
+
- Required sections or components
|
|
11
|
+
- Length constraints
|
|
12
|
+
- Style requirements
|
|
13
|
+
- Any specific formatting rules]
|
|
@@ -1,16 +1,16 @@
|
|
|
1
|
-
INITIAL OUTPUT:
|
|
2
|
-
[Paste the output to improve, or ask the AI to generate a first draft here]
|
|
3
|
-
|
|
4
|
-
FEEDBACK DIMENSIONS:
|
|
5
|
-
Review the output above for:
|
|
6
|
-
1. [Dimension 1 — e.g., "Clarity: Are there any ambiguous or hard-to-parse sentences?"]
|
|
7
|
-
2. [Dimension 2 — e.g., "Completeness: What important points are missing?"]
|
|
8
|
-
3. [Dimension 3 — e.g., "Tone: Is the voice appropriate for the audience?"]
|
|
9
|
-
4. [Dimension 4 — add or remove as needed]
|
|
10
|
-
|
|
11
|
-
For each dimension: quote specific problematic passages, explain the issue,
|
|
12
|
-
and suggest a concrete improvement.
|
|
13
|
-
|
|
14
|
-
REFINEMENT:
|
|
15
|
-
Rewrite the output addressing every point of your feedback above.
|
|
16
|
-
Show the refined version only.
|
|
1
|
+
INITIAL OUTPUT:
|
|
2
|
+
[Paste the output to improve, or ask the AI to generate a first draft here]
|
|
3
|
+
|
|
4
|
+
FEEDBACK DIMENSIONS:
|
|
5
|
+
Review the output above for:
|
|
6
|
+
1. [Dimension 1 — e.g., "Clarity: Are there any ambiguous or hard-to-parse sentences?"]
|
|
7
|
+
2. [Dimension 2 — e.g., "Completeness: What important points are missing?"]
|
|
8
|
+
3. [Dimension 3 — e.g., "Tone: Is the voice appropriate for the audience?"]
|
|
9
|
+
4. [Dimension 4 — add or remove as needed]
|
|
10
|
+
|
|
11
|
+
For each dimension: quote specific problematic passages, explain the issue,
|
|
12
|
+
and suggest a concrete improvement.
|
|
13
|
+
|
|
14
|
+
REFINEMENT:
|
|
15
|
+
Rewrite the output addressing every point of your feedback above.
|
|
16
|
+
Show the refined version only.
|
|
@@ -1,15 +1,15 @@
|
|
|
1
|
-
PHASE 1 — SKELETON:
|
|
2
|
-
Generate a skeleton outline for the following topic or question.
|
|
3
|
-
List only the key points — one per line — in this format:
|
|
4
|
-
N. [Point name] | [One-sentence description of what this point covers]
|
|
5
|
-
Do not expand yet. Skeleton only.
|
|
6
|
-
|
|
7
|
-
TOPIC / QUESTION:
|
|
8
|
-
[Your topic or question]
|
|
9
|
-
|
|
10
|
-
---
|
|
11
|
-
|
|
12
|
-
PHASE 2 — EXPAND:
|
|
13
|
-
Now expand each skeleton point into [2-4 sentences / a paragraph / detailed coverage].
|
|
14
|
-
Each point should be self-contained and complete.
|
|
15
|
-
[Optional: expand points in parallel by sending each as a separate API call]
|
|
1
|
+
PHASE 1 — SKELETON:
|
|
2
|
+
Generate a skeleton outline for the following topic or question.
|
|
3
|
+
List only the key points — one per line — in this format:
|
|
4
|
+
N. [Point name] | [One-sentence description of what this point covers]
|
|
5
|
+
Do not expand yet. Skeleton only.
|
|
6
|
+
|
|
7
|
+
TOPIC / QUESTION:
|
|
8
|
+
[Your topic or question]
|
|
9
|
+
|
|
10
|
+
---
|
|
11
|
+
|
|
12
|
+
PHASE 2 — EXPAND:
|
|
13
|
+
Now expand each skeleton point into [2-4 sentences / a paragraph / detailed coverage].
|
|
14
|
+
Each point should be self-contained and complete.
|
|
15
|
+
[Optional: expand points in parallel by sending each as a separate API call]
|
|
@@ -1,10 +1,10 @@
|
|
|
1
|
-
ORIGINAL QUESTION:
|
|
2
|
-
[The specific question you want answered]
|
|
3
|
-
|
|
4
|
-
STEP-BACK:
|
|
5
|
-
Before answering directly, first answer this higher-level question:
|
|
6
|
-
[Rephrase the original into a more abstract question about underlying principles, concepts, or rules]
|
|
7
|
-
|
|
8
|
-
PRINCIPLE APPLICATION:
|
|
9
|
-
Using the principles/concepts you just described, now answer the original question:
|
|
10
|
-
[Restate original question here]
|
|
1
|
+
ORIGINAL QUESTION:
|
|
2
|
+
[The specific question you want answered]
|
|
3
|
+
|
|
4
|
+
STEP-BACK:
|
|
5
|
+
Before answering directly, first answer this higher-level question:
|
|
6
|
+
[Rephrase the original into a more abstract question about underlying principles, concepts, or rules]
|
|
7
|
+
|
|
8
|
+
PRINCIPLE APPLICATION:
|
|
9
|
+
Using the principles/concepts you just described, now answer the original question:
|
|
10
|
+
[Restate original question here]
|
|
@@ -1,45 +1,45 @@
|
|
|
1
|
-
TASK TYPE:
|
|
2
|
-
[Clear indication of the activity type - e.g., Data Analysis, Customer Support Response, Technical Documentation, Content Translation]
|
|
3
|
-
|
|
4
|
-
INSTRUCTIONS:
|
|
5
|
-
[Specific steps and guidelines to accomplish the task]
|
|
6
|
-
1. [First step or action]
|
|
7
|
-
2. [Second step or action]
|
|
8
|
-
3. [Continue with methodology and sequence]
|
|
9
|
-
4. [Add more steps as needed...]
|
|
10
|
-
|
|
11
|
-
DO:
|
|
12
|
-
[Specify actions, language, structures, and information that MUST be included]
|
|
13
|
-
- [Required action or element #1]
|
|
14
|
-
- [Language or tone to use]
|
|
15
|
-
- [Structure or format to follow]
|
|
16
|
-
- [Information that must be present]
|
|
17
|
-
- [Add more as needed...]
|
|
18
|
-
|
|
19
|
-
DON'T:
|
|
20
|
-
[Highlight actions, elements, or approaches to AVOID]
|
|
21
|
-
- [Error or mistake to prevent #1]
|
|
22
|
-
- [Inappropriate language or approach to avoid]
|
|
23
|
-
- [Common pitfall to prevent]
|
|
24
|
-
- [Limitation or boundary not to cross]
|
|
25
|
-
- [Add more as needed...]
|
|
26
|
-
|
|
27
|
-
EXAMPLES:
|
|
28
|
-
[Provide concrete examples of desired outcomes]
|
|
29
|
-
|
|
30
|
-
Example 1 (Good):
|
|
31
|
-
[Detailed example showing desired output, format, tone, and structure]
|
|
32
|
-
|
|
33
|
-
Example 2 (Optional - Additional Good Example):
|
|
34
|
-
[Another example demonstrating quality and approach]
|
|
35
|
-
|
|
36
|
-
[Optional] Example 3 (What to Avoid):
|
|
37
|
-
[Counter-example showing what NOT to do, if helpful]
|
|
38
|
-
|
|
39
|
-
CONTEXT:
|
|
40
|
-
[Background information and user-provided content that affects the task]
|
|
41
|
-
- [Relevant background information]
|
|
42
|
-
- [Business or domain constraints]
|
|
43
|
-
- [User-provided data or content to reference]
|
|
44
|
-
- [Situational factors affecting the task]
|
|
45
|
-
- [Standards or guidelines that apply]
|
|
1
|
+
TASK TYPE:
|
|
2
|
+
[Clear indication of the activity type - e.g., Data Analysis, Customer Support Response, Technical Documentation, Content Translation]
|
|
3
|
+
|
|
4
|
+
INSTRUCTIONS:
|
|
5
|
+
[Specific steps and guidelines to accomplish the task]
|
|
6
|
+
1. [First step or action]
|
|
7
|
+
2. [Second step or action]
|
|
8
|
+
3. [Continue with methodology and sequence]
|
|
9
|
+
4. [Add more steps as needed...]
|
|
10
|
+
|
|
11
|
+
DO:
|
|
12
|
+
[Specify actions, language, structures, and information that MUST be included]
|
|
13
|
+
- [Required action or element #1]
|
|
14
|
+
- [Language or tone to use]
|
|
15
|
+
- [Structure or format to follow]
|
|
16
|
+
- [Information that must be present]
|
|
17
|
+
- [Add more as needed...]
|
|
18
|
+
|
|
19
|
+
DON'T:
|
|
20
|
+
[Highlight actions, elements, or approaches to AVOID]
|
|
21
|
+
- [Error or mistake to prevent #1]
|
|
22
|
+
- [Inappropriate language or approach to avoid]
|
|
23
|
+
- [Common pitfall to prevent]
|
|
24
|
+
- [Limitation or boundary not to cross]
|
|
25
|
+
- [Add more as needed...]
|
|
26
|
+
|
|
27
|
+
EXAMPLES:
|
|
28
|
+
[Provide concrete examples of desired outcomes]
|
|
29
|
+
|
|
30
|
+
Example 1 (Good):
|
|
31
|
+
[Detailed example showing desired output, format, tone, and structure]
|
|
32
|
+
|
|
33
|
+
Example 2 (Optional - Additional Good Example):
|
|
34
|
+
[Another example demonstrating quality and approach]
|
|
35
|
+
|
|
36
|
+
[Optional] Example 3 (What to Avoid):
|
|
37
|
+
[Counter-example showing what NOT to do, if helpful]
|
|
38
|
+
|
|
39
|
+
CONTEXT:
|
|
40
|
+
[Background information and user-provided content that affects the task]
|
|
41
|
+
- [Relevant background information]
|
|
42
|
+
- [Business or domain constraints]
|
|
43
|
+
- [User-provided data or content to reference]
|
|
44
|
+
- [Situational factors affecting the task]
|
|
45
|
+
- [Standards or guidelines that apply]
|
|
@@ -1,30 +1,30 @@
|
|
|
1
|
-
PROBLEM:
|
|
2
|
-
[Define what needs to be solved:
|
|
3
|
-
- What decision or problem are we addressing?
|
|
4
|
-
- What constraints apply?
|
|
5
|
-
- What does a good solution need to achieve?]
|
|
6
|
-
|
|
7
|
-
EXPLORE THESE BRANCHES:
|
|
8
|
-
Branch 1: [Name of approach/strategy]
|
|
9
|
-
Branch 2: [Name of approach/strategy]
|
|
10
|
-
Branch 3: [Name of approach/strategy]
|
|
11
|
-
[Add or remove branches as needed — 2 to 5 is optimal]
|
|
12
|
-
|
|
13
|
-
For each branch, analyze:
|
|
14
|
-
- Describe the approach
|
|
15
|
-
- Work through the core reasoning
|
|
16
|
-
- Identify key strengths
|
|
17
|
-
- Identify key weaknesses or risks
|
|
18
|
-
- Note any edge cases or assumptions
|
|
19
|
-
|
|
20
|
-
EVALUATION CRITERIA:
|
|
21
|
-
[Define how branches will be compared:
|
|
22
|
-
- What matters most? (list in priority order)
|
|
23
|
-
- Any hard constraints that eliminate certain branches?
|
|
24
|
-
- Is there one best answer, or does it depend on context?]
|
|
25
|
-
|
|
26
|
-
CONCLUSION:
|
|
27
|
-
[Synthesize the analysis:
|
|
28
|
-
- Select the best branch with clear reasoning
|
|
29
|
-
- OR explain trade-offs if the answer is context-dependent
|
|
30
|
-
- State the single biggest assumption that could change the recommendation]
|
|
1
|
+
PROBLEM:
|
|
2
|
+
[Define what needs to be solved:
|
|
3
|
+
- What decision or problem are we addressing?
|
|
4
|
+
- What constraints apply?
|
|
5
|
+
- What does a good solution need to achieve?]
|
|
6
|
+
|
|
7
|
+
EXPLORE THESE BRANCHES:
|
|
8
|
+
Branch 1: [Name of approach/strategy]
|
|
9
|
+
Branch 2: [Name of approach/strategy]
|
|
10
|
+
Branch 3: [Name of approach/strategy]
|
|
11
|
+
[Add or remove branches as needed — 2 to 5 is optimal]
|
|
12
|
+
|
|
13
|
+
For each branch, analyze:
|
|
14
|
+
- Describe the approach
|
|
15
|
+
- Work through the core reasoning
|
|
16
|
+
- Identify key strengths
|
|
17
|
+
- Identify key weaknesses or risks
|
|
18
|
+
- Note any edge cases or assumptions
|
|
19
|
+
|
|
20
|
+
EVALUATION CRITERIA:
|
|
21
|
+
[Define how branches will be compared:
|
|
22
|
+
- What matters most? (list in priority order)
|
|
23
|
+
- Any hard constraints that eliminate certain branches?
|
|
24
|
+
- Is there one best answer, or does it depend on context?]
|
|
25
|
+
|
|
26
|
+
CONCLUSION:
|
|
27
|
+
[Synthesize the analysis:
|
|
28
|
+
- Select the best branch with clear reasoning
|
|
29
|
+
- OR explain trade-offs if the answer is context-dependent
|
|
30
|
+
- State the single biggest assumption that could change the recommendation]
|