andurilcode/skill-router
plugins/craftwork-all/skills/skill-router/SKILL.md
Scan ALL available skills before any non-trivial request. Prevents skill blindness, tunnel vision, and wrong-skill selection. Entry point for all skill-assisted work.
$ install --global
skillsauthnpx skillsauth add andurilcode/skills skill-routerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 18, 2026, 8:24 AM21.6s1 file scanned
SKILL.md
- name:
- skill-router
- description:
- Scan ALL available skills before any non-trivial request. Prevents skill blindness, tunnel vision, and wrong-skill selection. Entry point for all skill-assisted work.
Skill Router
Attention-recovery and composition layer. Does NOT perform tasks — scans, matches, plans. All work done by routed skills.
Protocol
STEP 1 — Intent Decomposition
Request: [one-sentence restatement]
Deliverable: [artifact or answer]
Secondary needs: [implicit — analysis, validation, formatting, org dynamics]
Domain: [technical / creative / analytical / organizational / mixed]
Complexity: [simple (1 skill) / composed (2-3) / orchestrated (4+)]
Rules: analysis + production = two skill needs. Decision = reasoning + output. Organizational dynamics (adoption, buy-in) = separate need even if unstated.
STEP 2 — Exhaustive Skill Scan
Read EVERY skill description. Do not stop after first match.
Score each: PRIMARY (core intent, output worse without it) ORTING** (secondary need, quality boost) · IRRELEVANT
Zero PRIMARY matches = you skimmed. Re-read.
Primary: [skill]: [which intent component]
Supporting: [skill]: [what quality dimension]
Excluded: [skill]: [why not, non-obvious only]
STEP 3 — Composition Pattern
| Intent shape | Pattern | |---|---| | Pure analysis/diagnosis/decision | SINGLE or ORCHESTRATED | | Pure production (write/create/build) | SINGLE — match output format | | Analysis → production | PIPELINE — analytical skill → production skill | | Multi-lens review/audit | PARALLEL → CONVERGE — different quality dimensions | | Compression/summarization | SINGLE or PIPELINE (chain if large input) | | Ideation/brainstorming | SINGLE or PARALLEL creative skills | | File transformation | SINGLE — match target format | | Complex multi-faceted | ORCHESTRATED — split analysis + production phases |
STEP 4 — Emit Plan, Execute
SKILL ROUTER — PLAN
Intent: [onettern]
Skills: [ordered list with roles]
---
Executing Step 1: [skill-name]
Read first skill's SKILL.md, begin. Pipeline: carry output forward. Parallel: execute sequentially then synthesize.
Calibration
Skip for: greetings, factual questions, follow-ups mid-execution, user naming a specific skill.
Always invoke for: new substantive requests, temptation to answer from raw capability when skills exist, multi-domain requests.
Mid-execution: if a skill was missed — pause, re-run Step 2, amend, resume.
Attention Decay Countermeasures
- Never stop after first match — second-best skill often makes the difference
- Re-read last 5 skill entries deliberately (attention worst at list end)
- For each IRRELEVANT score, articulate why in one sentence — can't? Re-score
- Prefer composition over omission — reading one extra SKILL.md is cheap
- List excluded skills — makes decision auditable
Related Skills
andurilcode/kaizen
development
VerifiedTrustedCommunity
Apply kaizen continuous improvement philosophy to any codebase — identifying waste, unevenness, and overburden at the code level and producing small, actionable improvement opportunities. Triggers on '/kaizen', 'kaizen this codebase', 'continuous improvement audit', 'find waste in this code', 'what small improvements can we make?', 'improve this codebase incrementally', 'code health check', 'codebase hygiene', 'tech debt sweep', or any request to find incremental improvement opportunities in code. Also trigger when the user says 'clean up', 'tidy up', 'make this codebase better', or expresses frustration about code quality without wanting a full rewrite. This is NOT a code review skill for PRs or diffs — kaizen operates on the codebase as a whole or a focus area, looking for systemic improvement opportunities. Use this skill even for small codebases — the philosophy scales down gracefully.
4SKILL.mdUpdated Apr 18, 2026
andurilcode/automate
tools
VerifiedTrustedCommunity
Build automation scripts and pipelines that use coding-agent CLIs (Claude Code, Codex, Gemini CLI, GitHub Copilot CLI) in headless/non-interactive mode as the AI engine, or delegate work to cloud agents (`gh agent-task`) that open pull requests asynchronously. Use this skill whenever the user wants to write a shell script, CI job, cron task, batch processor, webhook handler, or any automation that shells out to `claude`, `codex`, `gemini`, `copilot`, or `gh agent-task` — single-turn prompts, multi-turn agentic loops, parallel fan-out across files/folders, structured JSON outputs consumed by downstream tools, or cloud-delegated tasks that produce PRs. Trigger on phrases like "script that uses Claude", "automate with Claude Code", "headless Claude", "batch process files with an LLM", "pipeline with codex exec", "gemini -p", "copilot --autopilot", "gh agent-task create", "GitHub Action that calls Claude", "cron job to review PRs", "agent loop in bash", "dispatch an agent task to open a PR", "fleet-wide agent-task across repos", or any request to integrate a coding agent CLI into an automated workflow. Also trigger when the user describes the shape of a pipeline (fan-out, map-reduce, review-then-fix, extract-then-summarize, ticket-to-PR, scheduled fleet upgrade) and AI is the engine, even if they don't name the CLI explicitly.
4SKILL.mdUpdated Apr 18, 2026
andurilcode/context-engineering-orchestrator
development
VerifiedTrustedCommunity
Entry point for context engineering work. Routes to the right skill based on what the user needs — creating instructions, debugging agent failures, building documentation, or measuring outcomes. Use this when the user's goal involves agent context but they haven't named a specific skill.
4SKILL.mdUpdated Apr 18, 2026
andurilcode/topic-explainer
documentation
VerifiedTrustedCommunity
Apply this skill whenever the user asks to have a topic, concept, technology, or idea explained to them. Triggers on phrases like 'explain X to me', 'what is X?', 'how does X work?', 'teach me about X', 'help me understand X', 'break down X', 'ELI5', 'explain like I'm five', 'give me an overview of X', 'I don't understand X', 'walk me through X', or any situation where the user wants to learn or understand something rather than produce an artifact. Also trigger when someone pastes a concept and asks for clarification, when they ask 'why' something works a certain way, or when they need a refresher on a topic they've encountered before. This skill does NOT apply to 'write documentation about X' (use technical-writing) or 'analyze X' (use reasoning skills). This skill is for when the human is the learner.
4SKILL.mdUpdated Apr 18, 2026