Index of every page on this site: llms.txt
All skills
ntcoding avatar

/lightweight-implementation-analysis-protocol

@21c6101
by Nick Tunentcoding/claude-skillz366 stars
47
Run it yourself

This skill should be used when fixing bugs, implementing features, debugging issues, or making code changes. Ensures understanding of code flow before implementation by: (1) Tracing execution path with specific file:line references, (2) Creating lightweight text diagrams showing class.method() flows, (3) Verifying understanding with user. Prevents wasted effort from assumptions or guessing. Triggers when users request: bug fixes, feature implementations, refactoring, TDD cycles, debugging, code analysis.

Use this Skill: https://skilld.dev/gh/ntcoding/claude-skillz/lightweight-implementation-analysis-protocol

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈139 tokens for metadata: the name and description. ≈390 when used: this file. ≈328 more on demand in 1 file.

Description uses 7.0% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈556 characters, or 7.0%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Lightweight Implementation Analysis Protocol

Quick understanding before implementation - just enough to guide TDD, no more.

When This Activates

Before creating implementation plans, fix plans, or TDD cycles for bugs/features.

The Protocol (3 Quick Steps)

1. Trace the Flow

Answer these:

  • Which event/request triggers this?
  • Which file:line handles it?
  • Where does the error occur (file:line)?

2. Quick Diagram

Simple class.method() flow with relevant data:

Event: EventName
  ↓ (contains: relevant fields)
Class.method() [file:line]
  ↓ (what it does)
Class.method() [file:line] ← 💥 Error here
  ↓
Result: What happens

Keep it short - 5-10 lines max.

3. Verify

Ask: "Here's the flow: [diagram]. Correct?"

Wait for confirmation, then proceed.

Example

Problem: Email validation failing

Event: user.email.updated
  ↓ (email: "invalid@")
UpdateUserEmailHandler.execute() [line 281]
  ↓ (validates email format)
EmailValidator.parse() [line 289] ← 💥 Throws ValidationError
  ↓
Result: Error response

Current: Throws
Should: Use safeParse(), return validation error

Rules

  • Keep it lightweight - This isn't detailed planning, just enough to know what to test
  • Be specific - File:line, not abstractions
  • Get confirmation - Don't proceed without it
  • Skip for trivial changes - Typos, formatting, docs

Anti-Pattern

❌ WRONG: "I'll fix the validation. Here's my plan..." ✅ RIGHT: "Let me trace where the error occurs... [diagram]. Correct?"

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts1mo4 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill provides a protocol for tracing code execution and verifying implementation plans with users. It presents a standard indirect prompt injection surface typical of code analysis tools but contains no malicious intent or dangerous patterns.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

  • Runlayer8mo

    2 files scanned · No issues

Signed by skilld at 21c6101. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Dormantupdated 10 months ago
version
1.0.0

README badge

README badge for ntcoding/claude-skillz/lightweight-implementation-analysis-protocol