zuhair-01/claude-skills-and-systems/analysis-lane-router
Claude Code and agent skill by zuhair-01/claude-skills-and-systems
- community
Checking that the SKILL.md file is still in the repository.
Pick the right lane BEFORE any analysis, study, research, investigate, audit, evaluate, teardown, or learn task — study a body of content vs research unknown facts vs audit against a standard vs investigate a root cause vs evaluate options vs learn from repeated findings. Use whenever the ask starts with analyze, analyse, study, teardown, decode, research, investigate, audit, evaluate, compare, or learn — and whenever it is unclear which of those lanes a task belongs to.
Install
npx vskill@latest install zuhair-01/claude-skills-and-systems/analysis-lane-routerSKILL.md
The same SKILL.md was published earlier as zuhair-01/claude-skills-and-systems/analysis-lane-router.
Analysis Lane Router — right lane before work
Universal Quality-OS gate #1: study ≠ research ≠ audit ≠ investigate ≠ evaluate ≠ learn. Picking the wrong lane wastes the whole run. Decide the lane in ONE step, then use the lane owner:
| Lane | The goal | Route to (existing owner) | |
|---|---|---|---|
| Study / teardown | Master a body of content (PDF, course, codebase, creator's system) → understanding + reusable vault notes | study kits (teardown pattern), codebase-onboarding, vault notes | |
| Research | Unknown external facts, cited | research-ops → deep-research / exa-search / parallel-web | |
| Audit | Check something against a standard/policy/checklist | security-audit, domain audit skills, reality-checker | |
| Investigate | Root-cause a bug/regression/unexpected behavior | systematic-debugging, investigate | |
| Evaluate | Compare/score options against criteria | agent-eval, statistical-analysis, rubrics | |
| Learn | Turn a repeated finding into durable capability | continuous-learning-v2, learn, skill-creator |
Decision questions (answer in order):
- Is the target a body of content to MASTER (study) or an unknown fact to FIND (research)?
- Is there a standard to check AGAINST (audit) or a broken thing to root-cause (investigate)?
- Are we CHOOSING between options with a score (evaluate)?
- Has this finding appeared ≥2 times already (learn — promote it)?
Mixed ask → split into lanes and run each; every lane's output follows the analysis-contract skill (evidence labels + output shape + rubric gate).
House precedents: creator teardowns (Kallaway, Motion//Prompt, Jev) = Study lane; the Motion//Prompt teardown is the shape of a good study output; fresh-facts briefs = Research lane with E1/E2/E3 labels.
Do not create a new skill for a lane that exists; do not bulk-install external skill sets for lanes (Overseer library + selective junctions only — see the plan's Phase 4 verdict table).
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/analysis-lane-router/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
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
[](https://verified-skill.com/skills/zuhair-01/claude-skills-and-systems/analysis-lane-router)