AI Skill Report Card

Crafting Prompts

Analyzes, crafts, and improves prompts using 19 research-backed techniques (Chain-of-Thought, Structured Output, Few-Shot, Placement, Salience, Roles, Positive Framing, Reasoning-First, Verbalized Sampling, Self-Reflection, plus extended and agentic techniques). Use when improving a prompt, writing a new prompt, critiquing a prompt's weaknesses, explaining a prompting technique, crafting subagent/tool prompts, or optimizing prompts for a specific model (Claude, GPT, DeepSeek, Gemini, Kimi, Qwen).

A88·Aug 26, 2026·Source: Extension-page

Diagnostic practice for prompt engineering, not a checklist service. The default failure mode is "more instructions = better" — wrong past a threshold (IFScale shows instruction overload degrades output). Focus on what to REMOVE and ACTIVATE, not just what to add.

14 / 15

Detect intent and route:

SignalMode
User pastes an existing promptA: Analyze
User describes requirements for a new promptB: Craft
User asks about a specific techniqueC: Teach
User wants a fast improvement, low ceremonyD: Quick Fix
UnclearAsk which mode fits, or show the menu below
Commands:
- A/B/C/D or mode name to begin
- 1-10 or technique name for Teach mode
- *model [name] - model-specific guidance
- *extended - show extended techniques
- *help - show this menu
Recommendation
Add one more full worked example with complete before/after prompt text rather than summarized descriptions, especially for Mode A/B outputs
#TechniqueImpactSummaryFailure if missing
1Chain-of-Thought+40% accuracy"Think step by step before answering"Skips reasoning steps
2Structured Output99%+ complianceConstrain to JSON/XML schemaFormat drift
3Few-Shot Examples+15-30% specificityShow 2-5 input/output examplesCalibration gap
4Placement+50% retrievalCritical info at start/end, not middleBuried instructions
5Salience+23-31% complianceXML tags, caps, explicit labelsConstraints overlooked
6Roles+10-20% domain accuracyAssign persona with expertiseGeneric register
7Positive Framing+15-20% compliance"Do X" not "Don't Y"Constraint confusion
8Reasoning-First-20-30% hallucinationEvidence before conclusionHallucinated conclusions
9Verbalized Sampling+1.6-2.1x diversityMultiple variants with probabilitiesCentroid output (bland average)
10Self-Reflection+15-25% accuracyAsk model to critique and reviseUncaught errors

Extended techniques (load reference/extended/{name}.md when relevant): decomposition, compression, sufficiency, scope, format-spec, uncertainty (epistemic labels: [E]vidence/[L]ogical/[S]peculation/[C]ontrarian), chaining, self-consistency, tree-of-thoughts, react-loop, tool-description-craft, context-engineering, multi-session, negative-space-definition, permission-escalation.

Model guides (load reference/models/{name}.md): claude, openai, deepseek, gemini, kimi, qwen.

15 / 15

Mode A — Analyze

Diagnose why this prompt will underperform. Never just note absence — name the specific failure each gap causes for this task.

Progress:

  • Quote the prompt exactly
  • Score against 10-technique scorecard (+/!/x/-)
  • Identify top 3 improvements with before/after + one-sentence "why"
  • Produce full optimized rewrite
  • Note target model if specified, apply model-specific adjustments

Output template:

PROMPT ANALYSIS
===============
CURRENT PROMPT
--------------
[verbatim]

TECHNIQUE SCORECARD
--------------------
| # | Technique | Status | Issue/Note |
|---|-----------|--------|------------|
... (10 rows, + present / ! partial / x missing / - N/A)

TOP 3 IMPROVEMENTS
-------------------
1. [Technique]: [improvement]
   Before: ...
   After: ...
   Why: [1 sentence]
2. ...
3. ...

OPTIMIZED PROMPT
-----------------
[full rewrite]

QUALITY SUMMARY
- Improvement potential: High/Medium/Low
- Techniques applied: [list]
- Target model: [note adjustments]

Next steps: explain a technique (Mode C)? iterate? targeting a specific model?

Mode B — Craft

Goal: activate expert behavior, not generate "probability-averaged centroid output." Ask before drafting — do not assume:

  1. What task should this prompt accomplish?
  2. What model will run this? (Claude, GPT, DeepSeek, etc.)
  3. What output format do you need?
  4. Any specific constraints or requirements?
  5. Should the prompt default to implementing or recommending? (Action Bias)
  6. Single-turn or part of an agentic workflow? (if agentic → use Agentic Prompting section below)
  7. Who is the audience? Expert peers, beginners, mixed?

Wait for answers. Then select techniques by task type: reasoning→CoT/Reasoning-First; structured data→Structured Output/Format-Spec; complex→Decomposition/Few-Shot; consistency-critical→Self-Reflection.

Output template:

CRAFTED PROMPT
==============
REQUIREMENTS UNDERSTOOD
- Task: ...
- Target model: ...
- Output format: ...
- Constraints: ...

TECHNIQUES APPLIED
- [Technique]: [why relevant]
...

THE PROMPT
----------
[full prompt]

RATIONALE
---------
[key design choices]

QUALITY SUMMARY
- Techniques applied: [n]/10 core
- Model-specific: Yes/No
- Confidence: High/Medium/Low

Next steps: test and iterate? explain techniques used? different approach?

Mode C — Teach

Load reference/{technique}.md. Present mechanism, a deep worked example, model-specific notes, then a practice exercise.

Mode D — Quick Fix

Speed over depth. Identify the 3 highest-impact improvements, apply immediately, minimal explanation.

QUICK FIX
=========
CHANGES MADE
- [Change 1]: one-liner
- [Change 2]: one-liner
- [Change 3]: one-liner

IMPROVED PROMPT
----------------
[full improved prompt]

Want deeper analysis? Try mode A.
Recommendation
Consider trimming the 'Clarity Over Compulsion' section slightly or merging with Best Practices to tighten length

Tool description optimization (reference/extended/tool-description-craft.md): make implicit context explicit, use human-readable return values, consolidate tools.

Subagent briefing pattern — every subagent prompt needs:

  • Context — what the task is and why it matters
  • Constraints — time budget, scope limits, effort level
  • Output format — exactly what to return
  • Success criteria — how to know it's done

ReAct loop: Reason → Act → Observe → Reason. See reference/extended/react-loop.md.

Action bias — choose one explicitly per prompt:

  • Proactive: "Implement changes rather than suggesting them"
  • Conservative: "Default to research and recommendations"
  • Balanced: "Implement straightforward changes; recommend for complex ones"

Context window management: just-in-time loading over pre-loading. Compaction strategies: summarize, clear tool results, full reset. See reference/extended/context-engineering.md and reference/extended/multi-session.md.

4.6 over-triggers on "CRITICAL: You MUST…" scaffolding. 4.7 follows literal MUST statements too rigidly, ignoring softening context. Same fix, different cause:

  • Drop "CRITICAL: You MUST…" — let instructions stand on their own
  • Reserve CAPS for genuinely load-bearing rules only (e.g., iron laws in debugging skills)
  • Drop anti-laziness pressure ("be thorough", "don't be lazy") — causes overthinking, not more effort
  • Use the effort parameter (xhigh for agentic, high for knowledge work) instead of prompt-level reasoning simulation
  • Drop explicit "think step by step" — adaptive thinking already handles it; competes with native reasoning
  • Soften tool-triggering language: "use when helpful" > "MUST use when X" (literal firing burns tokens)
  • At low/medium effort, 4.7 scopes tightly — add one targeted nudge where depth matters: "This step involves multi-step reasoning. Outline your logic before responding."
  • Critical info at start or end (Placement)
  • Constraints explicit and positive-framed
  • Output format specified
  • Model-specific adjustments applied
  • Action bias declared
  • Context budget considered
15 / 20

Example 1: Input: "Analyze this: 'You are an expert. Summarize the article.'" Output: Scorecard shows Roles=partial (generic "expert," no domain), Structured Output=missing (no format spec → inconsistent length/structure), Placement=N/A (too short to matter). Top improvement: add role specificity ("You are a financial analyst summarizing for a non-technical CFO") + output format (3 bullets, max 50 words each) — because without format spec, summary length will drift across calls.

Example 2: Input: "Craft a prompt for a code review subagent, targeting Claude, agentic workflow" Output: Asks clarifying questions (task scope, output format, action bias, audience) → applies Subagent Briefing Pattern (Context/Constraints/Output/Success criteria) + Reasoning-First (evidence before verdict) + Structured Output (findings as JSON with severity field) + soft tool-triggering language per Claude 4.7 guidance.

Recommendation
Show a concrete bad-vs-good output pair (not just technique description) to make examples section fully concrete per grading standard
  • Diagnose why a gap causes failure for this specific task — never a bare checklist
  • In Craft mode, always wait for answers to elicitation questions before drafting
  • Prefer removing/consolidating instructions over adding more once a prompt is dense
  • Match technique selection to task type, not habit
  • Load model-specific reference files only when a model is named — JIT, not upfront
  • Treating Analyze mode as a scorecard-only exercise (missing the "why it fails" diagnosis)
  • Assuming unstated requirements in Craft mode instead of asking
  • Piling on "CRITICAL/MUST" language for non-load-bearing instructions
  • Adding CoT to reasoning models (o1/o3, R1) — hurts performance, it's already built in
  • Using anti-laziness pressure phrases, which cause overthinking rather than diligence
  • Recommending more instructions as the default fix — check for instruction overload first
0
Grade AAI Skill Framework
Scorecard
Criteria Breakdown
Quick Start
14/15
Workflow
15/15
Examples
15/20
Completeness
19/20
Format
14/15
Conciseness
13/15