acking-you/myclaude-skills/tech-impl-doc

Claude Code and agent skill by acking-you/myclaude-skills

Trust tier 2
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Write or revise technical implementation, architecture, troubleshooting, and system-behavior explanations. Use when claims must be checked against code or runtime evidence, or when an existing technical document needs a focused edit that keeps its structure and scope.

Install

npx vskill@latest install acking-you/myclaude-skills/tech-impl-doc

SKILL.md

Technical Implementation Docs

The user's explicit instructions override every default below.

Scope and edits

Match the user's audience, scope, voice, structure, and length. Infer obvious choices rather than opening with a questionnaire. Produce the smallest document or edit that fully answers the request.

When editing an existing document:

  • Read the current document first.
  • Preserve its organization, voice, and unrelated content.
  • Patch what was asked. Keep an expansion inside the named section; add a new section only when requested or genuinely necessary.
  • Do not rewrite, reorder, or "improve" adjacent material.
  • After editing, reread the result and confirm unrelated text is intact.

Evidence

  • Lead with the answer, decision, or root cause, then give enough evidence to make it trustworthy.
  • Verify implementation-specific claims against source, runtime output, or authoritative docs.
  • Keep verified facts, inferences, and open questions visibly distinct.
  • If a claim cannot be verified, say so, mark it as an assumption, or leave it out. Do not fill gaps with plausible guesses.
  • Define unfamiliar terms near first use, at the reader's level.

Form

  • Prefer cohesive prose. Use lists, tables, or diagrams only when they make relationships materially clearer; diagrams are never required.
  • Use the fewest, shallowest headings that work. No template sections, executive summaries, or code indexes unless they serve this reader.
  • Include commands, paths, line references, failure modes, and trade-offs only when they help the reader reproduce, navigate, decide, or operate safely.
  • Skip generic introductions, boilerplate, and sentences that restate a heading.
  • Before finishing, check for repetition, scope creep, unsupported claims, and needless headings.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
6
Repository forks
1
7-day trend score
10

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 24 Mar 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/acking-you/myclaude-skills/tech-impl-doc/badge)](https://verified-skill.com/skills/acking-you/myclaude-skills/tech-impl-doc)

Something wrong with this skill or its page? Tell us.