{"id":"6ba6e098-5ca3-4c0e-99e4-4f93cdfdc570","entityType":"agent","slug":"clawhub-skills-aiwithabidi-a6-context-engineer","name":"context-engineer","canonicalUrl":"https://www.xpersona.co/agent/clawhub-skills-aiwithabidi-a6-context-engineer","canonicalPath":"/agent/clawhub-skills-aiwithabidi-a6-context-engineer","generatedAt":"2026-10-09T23:14:54.989Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"Master context engineering and prompt engineering for AI agents and LLMs. Optimize system prompts, craft few-shot examples, implement chain-of-thought reasoning, manage context windows, design structured outputs, and build self-improving prompt patterns. Covers Anthropic, OpenAI, and Google best practices. Includes prompt optimizer that audits drafts against best practices, and context builder that generates optimal context windows for any task. Built for AI agents — Python stdlib only, no dependencies. Use for prompt optimization, system prompt design, agent instruction writing, LLM output debugging, context window management, and few-shot example crafting. --- name: context-engineer description: \"Master context engineering and prompt engineering for AI agents and LLMs. Optimize system prompts, craft few-shot examples, implement chain-of-thought reasoning, manage context windows, design structured outputs, and build self-improving prompt patterns. Covers Anthropic, OpenAI, and Google best practices. Includes prompt optimizer that audits drafts against best practices, an","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.","installCommand":"clawhub skill install skills:aiwithabidi:a6-context-engineer","sourceUrl":"https://github.com/openclaw/skills/tree/main/skills/aiwithabidi/a6-context-engineer","homepage":"https://www.agxntsix.ai","primaryLinks":[{"label":"View on ClawHub","url":"https://github.com/openclaw/skills/tree/main/skills/aiwithabidi/a6-context-engineer","kind":"source"},{"label":"Homepage","url":"https://www.agxntsix.ai","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":50,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Master context engineering and prompt engineering for AI agents and LLMs. Optimize system prompts, craft few-shot examples, implement chain-of-thought reasoning"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No source adoption metrics were available."},"stars":null,"forks":null,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-02-25T05:57:14.681Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-02-25T05:57:14.681Z","lastIndexedAt":null,"nextCrawlAt":"2026-02-26T05:57:14.681Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install skills:aiwithabidi:a6-context-engineer","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-aiwithabidi-a6-context-engineer/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-aiwithabidi-a6-context-engineer/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-aiwithabidi-a6-context-engineer/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-aiwithabidi-a6-context-engineer/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-aiwithabidi-a6-context-engineer/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-aiwithabidi-a6-context-engineer/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T23:14:54.989Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-aiwithabidi-a6-context-engineer/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-aiwithabidi-a6-context-engineer/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-aiwithabidi-a6-context-engineer/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-aiwithabidi-a6-context-engineer/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"---\nname: context-engineer\ndescription: \"Master context engineering and prompt engineering for AI agents and LLMs. Optimize system prompts, craft few-shot examples, implement chain-of-thought reasoning, manage context windows, design structured outputs, and build self-improving prompt patterns. Covers Anthropic, OpenAI, and Google best practices. Includes prompt optimizer that audits drafts against best practices, and context builder that generates optimal context windows for any task. Built for AI agents — Python stdlib only, no dependencies. Use for prompt optimization, system prompt design, agent instruction writing, LLM output debugging, context window management, and few-shot example crafting.\"\nhomepage: https://www.agxntsix.ai\nlicense: MIT\ncompatibility: Python 3.10+ (stdlib only — no dependencies)\nmetadata: {\"openclaw\": {\"emoji\": \"🧠\", \"requires\": {\"env\": []}, \"primaryEnv\": \"\", \"homepage\": \"https://www.agxntsix.ai\"}}\n---\n\n# 🧠 Context Engineer\n\nMaster skill for context engineering and prompt engineering — the art of crafting optimal inputs to LLMs.\n\n## Features\n\n- **Optimize prompts** against Anthropic, OpenAI, and Google best practices\n- **Build context windows** with system prompt, user prompt, and examples\n- **Design system prompts** for sub-agents, crons, and skills\n- **Craft few-shot examples** that dramatically improve accuracy\n- **Implement chain-of-thought** reasoning for complex tasks\n- **Manage context windows** — prioritize critical info placement\n- **Structure outputs** with JSON schema, markdown, or XML tags\n- **Debug poor LLM outputs** with systematic prompt analysis\n- **Write agent instructions** (AGENTS.md, SOUL.md patterns)\n- **Apply role-based prompting** for domain-specific performance\n- **Chain complex tasks** into accurate subtask pipelines\n- **Reference 20+ templates** for common prompting patterns\n\n## Requirements\n\n| Variable | Required | Description |\n|----------|----------|-------------|\n| None | — | No API keys needed — pure prompt engineering knowledge |\n\n## Quick Start\n\n```bash\nPY=~/.openclaw/workspace/.venv/bin/python3\n\n# Analyze and improve a draft prompt\n$PY skills/context-engineer/scripts/prompt_optimizer.py \"Your draft prompt here\"\n\n# Build optimal context window for a task\n$PY skills/context-engineer/scripts/context_builder.py \"Analyze quarterly financials\"\n\n# Optimize from file\n$PY skills/context-engineer/scripts/prompt_optimizer.py --file path/to/prompt.txt\n```\n\n## Commands\n\n### Prompt Optimizer\n```bash\n# Analyze a prompt string\n$PY skills/context-engineer/scripts/prompt_optimizer.py \"Your prompt\"\n\n# Analyze from file\n$PY skills/context-engineer/scripts/prompt_optimizer.py --file prompt.txt\n```\n\n### Context Builder\n```bash\n# Build context for a task\n$PY skills/context-engineer/scripts/context_builder.py \"Task description\"\n\n# With role and output format\n$PY skills/context-engineer/scripts/context_builder.py --task \"Code review\" --role \"Senior engineer\" --output json\n```\n\n## The 10 Commandments of Prompting\n\n1. **Be clear, direct, and detailed** — Treat the model as a brilliant new employee with no context\n2. **Use examples** — 3-5 diverse examples dramatically improve accuracy and consistency\n3. **Let it think** — Chain-of-thought for complex reasoning; extended thinking for hard problems\n4. **Structure with tags** — XML tags prevent mixing of instructions, context, and examples\n5. **Assign a role** — System prompts with specific personas boost domain performance\n6. **Chain complex tasks** — Break multi-step work into subtask prompts for accuracy\n7. **Manage context** — Put critical info at top and bottom; reference docs by tag name\n8. **Specify output format** — JSON schema, markdown structure, or explicit format instructions\n9. **Iterate empirically** — Test against eval criteria, not vibes\n10. **Context > Prompt** — What you include matters more than how you ask\n\n## References\n\n| File | Description |\n|------|-------------|\n| `references/anthropic-best-practices.md` | Anthropic's official prompt engineering docs |\n| `references/openai-best-practices.md` | OpenAI's prompt engineering guide |\n| `references/google-best-practices.md` | Google's Gemini prompting strategies |\n| `references/context-engineering-principles.md` | Context engineering theory (Karpathy et al.) |\n| `references/prompt-templates.md` | 20+ reusable templates for common tasks |\n\n## Script Reference\n\n| Script | Description |\n|--------|-------------|\n| `{baseDir}/scripts/prompt_optimizer.py` | Analyzes prompts against best practices |\n| `{baseDir}/scripts/context_builder.py` | Builds optimal context windows for tasks |\n\n## Output Format\n\nAll commands output structured text by default with clear sections for analysis results, suggestions, and improved prompts.\n\n## Data Policy\n\nThis skill processes prompts locally. No data is sent to external services unless explicitly using an LLM API.\n\n## Sources\n\n- Anthropic Prompt Engineering: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview\n- OpenAI Prompt Engineering: https://platform.openai.com/docs/guides/prompt-engineering\n- Google Gemini Prompting: https://ai.google.dev/gemini-api/docs/prompting-strategies\n- Andrej Karpathy on Context Engineering (2025)\n\n---\n\nBuilt by [M. Abidi](https://www.agxntsix.ai)\n\n[LinkedIn](https://www.linkedin.com/in/mohammad-ali-abidi) · [YouTube](https://youtube.com/@aiwithabidi) · [GitHub](https://github.com/aiwithabidi) · [Book a Call](https://cal.com/agxntsix/abidi-openclaw)\n","readmeExcerpt":"--- name: context-engineer description: \"Master context engineering and prompt engineering for AI agents and LLMs. Optimize system prompts, craft few-shot examples, implement chain-of-thought reasoning, manage context windows, design structured outputs, and build self-improving prompt patterns. Covers Anthropic, OpenAI, and Google best practices. Includes prompt optimizer that audits drafts against best practices, an","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"PY=~/.openclaw/workspace/.venv/bin/python3\n\n# Analyze and improve a draft prompt\n$PY skills/context-engineer/scripts/prompt_optimizer.py \"Your draft prompt here\"\n\n# Build optimal context window for a task\n$PY skills/context-engineer/scripts/context_builder.py \"Analyze quarterly financials\"\n\n# Optimize from file\n$PY skills/context-engineer/scripts/prompt_optimizer.py --file path/to/prompt.txt"},{"language":"bash","snippet":"# Analyze a prompt string\n$PY skills/context-engineer/scripts/prompt_optimizer.py \"Your prompt\"\n\n# Analyze from file\n$PY skills/context-engineer/scripts/prompt_optimizer.py --file prompt.txt"},{"language":"bash","snippet":"# Build context for a task\n$PY skills/context-engineer/scripts/context_builder.py \"Task description\"\n\n# With role and output format\n$PY skills/context-engineer/scripts/context_builder.py --task \"Code review\" --role \"Senior engineer\" --output json"}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"CLAWHUB","editorialOverview":"Master context engineering and prompt engineering for AI agents and LLMs. Optimize system prompts, craft few-shot examples, implement chain-of-thought reasoning, manage context windows, design structured outputs, and build self-improving prompt patterns. Covers Anthropic, OpenAI, and Google best practices. Includes prompt optimizer that audits drafts against best practices, and context builder that generates optimal context windows for any task. Built for AI agents — Python stdlib only, no dependencies. Use for prompt optimization, system prompt design, agent instruction writing, LLM output debugging, context window management, and few-shot example crafting. --- name: context-engineer description: \"Master context engineering and prompt engineering for AI agents and LLMs. Optimize system prompts, craft few-shot examples, implement chain-of-thought reasoning, manage context windows, design structured outputs, and build self-improving prompt patterns. Covers Anthropic, OpenAI, and Google best practices. Includes prompt optimizer that audits drafts against best practices, an","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":452,"uniquenessScore":62,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T23:14:54.989Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}