AI Skill Report Card

Engineering Agent Context

A-83·Aug 1, 2026·Source: Extension-page
14 / 15

Auditing an existing CLAUDE.md, Skill, or system prompt? Ask these questions for every rule you find:

  1. Is this rule true 100% of the time? If no, delete it and trust the model's judgment instead.
  2. Is this an example meant to teach tool usage? Replace it with a better-designed interface (clearer parameter names, enums, types) instead.
  3. Is this loaded upfront but rarely needed? Move it into a separate Skill file loaded on demand (progressive disclosure).
  4. Is this repeated in multiple places (system prompt + tool description + CLAUDE.md)? Keep it in exactly one place — prefer the tool/skill description closest to where it's used.
  5. Is this a "spec" written as prose? Consider replacing it with code, tests, or a runnable artifact instead.

If you answered "delete/move/replace" more than half the time, your context needs simplification.

Recommendation
Add a concrete before/after example showing full-length CLAUDE.md diffs rather than short snippets, to demonstrate scale-level tradeoffs
13 / 15

Progress:

  • Step 1: Inventory all context sources (system prompt, CLAUDE.md, Skills, tool descriptions, memory)
  • Step 2: Flag contradictory or overly rigid rules ("never do X" / "always do Y")
  • Step 3: Classify each rule: Universal truth / Contextual preference / Redundant / Example-only
  • Step 4: Remove contextual preferences and examples that constrain more than they help
  • Step 5: Redesign tools/interfaces to convey intent (enums, param names) instead of prose examples
  • Step 6: Split long instructions into separate Skill files, referenced only when relevant
  • Step 7: Replace prose specs with code, tests, prototypes, or rubrics where possible
  • Step 8: Re-test behavior; confirm no regression before finalizing
Recommendation
Include a short case where a 'universal truth' rule is correctly kept, to balance the delete-heavy bias with a positive counterexample
Old approachNew approach
Give Claude rigid rulesLet Claude use judgment; state defaults, not absolutes
Give examples of tool usageDesign expressive interfaces (enums, clear params)
Front-load all instructionsUse progressive disclosure; load Skills on demand
Repeat instructions in multiple placesState once, in the tool/skill description itself
Store memory manually in CLAUDE.mdLet automatic memory handle persistence
Simple markdown specsRich references: code, tests, prototypes, rubrics
16 / 20

Example 1: Comment style rule Input: System prompt says "Never write docstrings with multiple paragraphs. No multi-line comment blocks. Max one short line." Output: Replace with "Write code that matches the surrounding style: comment density, naming, and tone should match the existing codebase." (Lets Claude adapt instead of applying a blanket rule that breaks on complex code.)

Example 2: Tool usage via examples Input: Tool description includes 3 worked examples showing how to call a todo tool. Output: Redesign the tool's status parameter as an enum (pending | in_progress | completed) with a constraint that only one item can be in_progress at a time. Remove the examples — the interface now communicates intent directly.

Example 3: CLAUDE.md bloat Input: CLAUDE.md contains a 200-line section on "how to verify your code" mixed with repo overview. Output: Move verification steps into a dedicated verification.skill.md file. CLAUDE.md keeps a one-line pointer: "For code verification steps, see the verification skill." Repo overview stays concise; details live in source code (e.g., a single monolithic types file) rather than being restated in prose.

Example 4: Spec as reference Input: A written paragraph describing a desired UI design. Output: Provide an HTML prototype or existing component code as the reference instead — richer, higher-fidelity, and in a language Claude already understands well.

Recommendation
Add guidance on how to measure success post-audit (e.g., eval regression checklist) to strengthen Step 8 of the workflow
  • Trust judgment over restriction — only keep hard rules for genuinely universal, high-stakes cases (e.g., "never delete files without confirmation").
  • Keep CLAUDE.md short — repo purpose + pointers to Skills/code, not exhaustive rules.
  • Push detail into code and Skills, not prose — code is unambiguous and Claude already understands it well.
  • One source of truth per instruction — don't restate the same guidance in system prompt, skill, and CLAUDE.md.
  • Design tools to be self-explanatory — good parameter naming/typing beats usage examples.
  • Use progressive disclosure aggressively — split long skills into multiple files; load only what's needed per task.
  • Prefer rich references (code, tests, prototypes, rubrics) over plain-text specs whenever possible.
  • Periodically re-audit — as models improve, previously-necessary constraints often become unnecessary friction.
  • Don't hedge every instruction "just in case." Conflicting guidance (e.g., "add docs as appropriate" + "NEVER add comments") forces the model to reconcile contradictions instead of acting.
  • Don't build a single giant knowledge repository assuming the model won't find info otherwise — this bloats context. Use a discoverable tree of files loaded at the right time instead.
  • Don't over-supply examples for tool use — they narrow the model's exploration space rather than expanding it.
  • Don't repeat the same instruction in system prompt and tool description — pick one location.
  • Don't manually manage memory if automatic memory features are available — let the system persist relevant context.
  • Don't assume older best practices still apply — re-validate constraints against current model capabilities before keeping them.
0
Grade A-AI Skill Framework
Scorecard
Criteria Breakdown
Quick Start
14/15
Workflow
13/15
Examples
16/20
Completeness
16/20
Format
14/15
Conciseness
14/15