andurilcode/context-engineering-orchestrator
plugins/craftwork-context-engineering/skills/context-engineering-orchestrator/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add andurilcode/skills context-engineering-orchestratorInstall 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, 8:25 AM43.3s1 file scanned
SKILL.md
- name:
- context-engineering-orchestrator
- description:
- 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.
Context Engineering Orchestrator
This skill routes — it does not reason. Read the user's intent, match it to an entry point below, then execute that skill's SKILL.md.
Step 1 — Match the User's Intent
Read what the user wants to do and match it to the closest entry below. If ambiguous, ask one clarifying question.
| User wants to... | Start with | Then |
|---|---|---|
| Find what context is missing from a codebase | context-gap-analyzer | → agent-instruction-forge if gaps need rules |
| Create or improve agent instruction files (CLAUDE.md, .cursorrules, etc.) | agent-instruction-forge | → rule-quality-evaluator → edd |
| Score or audit existing agent instructions | rule-quality-evaluator | → agent-instruction-forge if score is low |
| Measure whether agent context actually helps | context-eval | → agent-instruction-forge if regression found |
| Iterate on a context harness with tests | edd | → context-eval for measurement |
| Design what goes into a context window | context-cartography | → context-gap-analyzer to validate coverage |
| Debug why an agent is failing / ignoring instructions | context-debugging | → context-gap-analyzer or edd based on findings |
| Extract business logic or domain rules from code | business-logic-extractor | → llms-txt-generator or agent-instruction-forge |
| Process a large document for LLM consumption | deep-document-processor | → llms-txt-generator |
| Generate an llms.txt or LLM-friendly reference | llms-txt-generator | done |
| Find false positives in AI-generated tests | test-challenger | → edd if better assertions needed |
Step 2 — Execute
- Read
skills/[skill-name]/SKILL.md - Apply that skill's full methodology
- When the skill completes, check the "Then" column above for potential follow-ups
Step 3 — Propose Next Steps
Do NOT auto-execute the "Then" skill. Instead, propose it to the user:
Based on [what the skill produced], a natural next step would be:
→ [skill-name]: [1-sentence reason this would help]
Want me to continue with that, or is this what you needed?
If multiple follow-ups are relevant, list them as options. The user chooses — the orchestrator does not chain automatically.
Canonical Chains
These are the most common multi-skill sequences in this group:
Full context engineering lifecycle:
context-gap-analyzer → agent-instruction-forge → rule-quality-evaluator → context-eval → edd
Use when building agent context from scratch or doing a comprehensive audit.
Creating agent instructions:
context-gap-analyzer → agent-instruction-forge → rule-quality-evaluator → edd
Use when the goal is specifically to create or improve instruction files.
Debugging agent failures:
context-debugging → context-gap-analyzer → agent-instruction-forge → edd
Use when an agent is behaving incorrectly and you suspect the context layer.
Building documentation:
business-logic-extractor → llms-txt-generator
deep-document-processor → llms-txt-generator
Use when creating LLM-consumable reference material.
Skill Registry
| Skill | Purpose |
|-------|---------|
| context-gap-analyzer | Find implicit context missing from a codebase |
| agent-instruction-forge | Create instruction rules for coding agents |
| rule-quality-evaluator | Score rules on Seven Properties, detect redundancies |
| context-cartography | Design what goes into an agent's context window |
| context-debugging | Diagnose agent failures originating in the context layer |
| context-eval | Measure whether context changes improve outcomes |
| edd | Eval-Driven Development — TDD for context |
| llms-txt-generator | Generate token-efficient context documents |
| deep-document-processor | Multi-pass reading of large documents |
| business-logic-extractor | Extract domain rules from code |
| test-challenger | Find false positives in AI-generated tests |
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/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
andurilcode/technical-writing
development
VerifiedTrustedCommunity
Apply this skill whenever the user needs to write, draft, review, or improve any form of technical document — including RFCs, design docs, ADRs, runbooks, postmortems, one-pagers, internal announcements, Slack threads, PR descriptions, or any prose that communicates technical information to an audience. Triggers on phrases like 'write a design doc', 'draft an RFC', 'help me write this up', 'document this decision', 'write a runbook', 'review my doc', 'make this clearer', 'I need to announce this', 'how should I communicate this?', 'write a postmortem', 'draft a one-pager', or any situation where technical information needs to be transformed into written communication for a specific audience. Also trigger when the user pastes a draft and asks for feedback, when they need to explain a technical decision to non-technical stakeholders, or when they provide their own template and want the agent to follow it. This skill covers the full spectrum from 2-line Slack msages to multi-page design documents.
4SKILL.mdUpdated Apr 18, 2026