원클릭으로 Manus에서 모든 스킬 실행

context-engineering-orchestrator

스타6

포크2

업데이트2026년 4월 19일 07:00

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.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

AndurilCode

AndurilCode/craftwork

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

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`	→ `context-compressor` if over budget
Optimize / compress context to fit a token budget	`context-compressor`	→ `context-eval` to verify compressed context works
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
On completion, check the "Then" column for follow-ups

Step 3 — Propose Next Steps

Do NOT auto-execute the "Then" skill. Propose it:

Based on [what the skill produced], a natural next step would be:
→ [skill-name]: [1-sentence reason]

Want me to continue with that, or is this what you needed?

Multiple follow-ups → list as options. User chooses; orchestrator never chains 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
`context-compressor`	Maximize signal-per-token under a finite budget
`test-challenger`	Find false positives in AI-generated tests

이 저장소의 다른 Skills

같은 저장소

automate

AndurilCode/craftwork

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-tas

2026-04-196

causal-inference

AndurilCode/craftwork

Apply causal inference whenever the user is interpreting metrics, debugging system behavior, reading A/B test results, or trying to understand whether an observed change was caused by an action or by something else. Triggers on phrases like "X caused Y", "since we deployed this, metrics changed", "the A/B test showed a lift", "why did this metric move?", "is this correlation or causation?", "we changed X and Y improved", "how do we know this worked?", "the data shows…", or any situation where conclusions are being drawn from observational data. Also trigger before any decision based on metric interpretation — confusing correlation with causation leads to interventions that don't work and misattribution of credit. Never assume causation without applying this skill.

2026-04-196

ethical-reasoning

AndurilCode/craftwork

Apply ethical reasoning whenever the user faces a decision, design, or action with moral implications — especially when someone could be harmed, rights could be violated, or values are in tension. Triggers on phrases like "is this the right thing to do?", "what are the ethical implications?", "who could this harm?", "should we build this?", "is this fair?", "what are our obligations?", "value trade-off", "responsible AI". Use proactively when reviewing any high-stakes decision, product design affecting vulnerable populations, or action where the beneficiaries and those bearing costs are different groups.

2026-04-196

execution-planning

AndurilCode/craftwork

Apply execution-planning whenever the user has made a decision and needs to turn it into action — decomposing work, sequencing tasks, estimating timelines, and assigning ownership. Triggers on phrases like "how do we execute this?", "break this into tasks", "what's the project plan?", "create a roadmap", "what are the dependencies?", "who does what by when?", "how long will this take to build?". Use proactively after decision-synthesis or architecture-evaluation produces a committed decision that requires coordinated implementation.

2026-04-196

experimental-design

AndurilCode/craftwork

Apply experimental-design whenever the user needs to test a hypothesis, validate an assumption, or determine whether something actually works. Triggers on phrases like "how do we test this?", "design an experiment", "what would prove this?", "set up an A/B test", "how do we validate this hypothesis?", "what's the right control?", "is this result significant?", "what sample size do we need?". Use proactively when decisions rest on untested assumptions — designing the test before collecting data prevents post-hoc rationalization.

2026-04-196

fairness-auditing

AndurilCode/craftwork

Apply fairness auditing whenever the user describes a system, algorithm, policy, or process that allocates outcomes across groups and wants to know whether it is equitable. Triggers on phrases like "is this fair?", "disparate impact", "bias in the system", "does this discriminate?", "algorithmic fairness", "who's disadvantaged by this?", "equitable outcomes". Use proactively when reviewing any allocation mechanism, scoring system, or automated decision pipeline that affects people differently based on group membership.

2026-04-196

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`	→ `context-compressor` if over budget
Optimize / compress context to fit a token budget	`context-compressor`	→ `context-eval` to verify compressed context works
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
On completion, check the "Then" column for follow-ups

Step 3 — Propose Next Steps

Do NOT auto-execute the "Then" skill. Propose it:

Based on [what the skill produced], a natural next step would be:
→ [skill-name]: [1-sentence reason]

Want me to continue with that, or is this what you needed?

Multiple follow-ups → list as options. User chooses; orchestrator never chains 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
`context-compressor`	Maximize signal-per-token under a finite budget
`test-challenger`	Find false positives in AI-generated tests