reprompt Dashboard

Prompt analytics & recommendations

1063
Total Prompts
1063
Unique Prompts
890
Sessions Scanned
1
Sources

Deduplication

Category Distribution

Activity Over Time

Specificity Trend

Top Patterns

PatternFreqCategory
好的,把这次我们在建立前端脚本的时候踩过的坑和经验整理出来,在我们的projects内的文档详细记录,确保任何新项目或者新功能都不会再花时间解决一样的错误12debug
是的“改PowerPoint客户端代码“包括JofC command来实际执行我们的workflow对slides的更新4run
It seems the course is providing free credit but not what you referred above " This email contains instructions for claiming compute credits for the class. If you have questions please email ljbailey@standord.edu, cc cs224n-staff-win2526@cs.stanford.edu, and set the subject line as “CS 224N CREDITS”. A few quick reminders before claiming the credits: These are all the credits for the course. You will use a very small amount of the GCP credits for assignment 4 (roughly $5), and the rest you are free to use on your final project. If you start working on your final project now, make sure to save at least $10 to complete assignment 4. Some best practices for using the credits efficiently: Try testing your code on small subsets of data. For example, you may want to get responses from a model for all 10,000 elements of a dataset. Try your code on just 10 examples first, and manually inspect the responses you get to make sure everything is working as normal. If you are training a model to do something, you can start by trying a small model on a small GPU. Try and test your code locally on your computer at a small scale before running a larger training run on GPU If you are renting a GPU, and are done with it, remember to release the GPU. You don’t want to spend credits on compute you aren’t using. Google Cloud - $50 Important: these credits are required for you to complete assignment 4. Please redeem them as soon as possible in case you have any issues that we need to resolve. If you leave it until right before assignment 4 is due, and cannot claim the credits, we will not give extra late days. To get your google cloud credits, follow the instructions in this document. The link you should use to claim the credits (referenced in step 1 of the document) is below. Please do not share this link with anyone else: https://urldefense.com/v3/__https://gcp.secure.force.com/GCPEDU?cid=NIzat2CxRD0E1NLH3lqvFOg5NzxFOZF0F0trs6JcANqK2kiiRCCWwKVh1L4r*2FkU5*__;JS8!!G92We9drHetJ8EofZw!fQI4SIgpUKptTsp0Umu3LVB3jT4xmu97SH2gjTi9ExKccu4rIioNhPsnnXiAT05gNgbmzAMqXRP6bd8DyfLdzLkDETHAag$ Modal Cloud - $50 Modal allows you to rent GPU resources on demand. To get your Modal credits, follow the instructions in this document. Moonshot AI - $20 Moonshot AI makes the Kimi series of frontier LLMs. You can use these credits to query the Kimi models. Please follow the instructions in this document to claim your credits. Your Moonshot AI credit code is: "3review
Review this implementation plan against the spec. Plan: /Users/chris/projects/autoProjectCompletion/docs/superpowers/plans/2026-03-11-auto-project-completion.md Spec: /Users/chris/projects/autoProjectCompletion/docs/superpowers/specs/2026-03-11-auto-project-completion-design.md Check for: 1. Does the plan cover all spec requirements? 2. Are file paths exact and consistent? 3. Are test steps included for every module? 4. Is TDD followed (test before implementation)? 5. Are commit steps included? 6. Are there any missing modules from the spec? 7. Code quality — any bugs, missing imports, inconsistencies? 8. Does the tech stack match (asyncpg not SQLAlchemy, asyncio not APScheduler)? Return: APPROVED or list of specific issues to fix.3review
以世界顶级软件架构师和UI/UX designer的身份,根据我们文档的记录,联网查找优秀的开源框架和工业界设计,设计一款根据我们已有的项目的文档和已有程序,自动完善进一步能力拓宽并且推送给我们审批的软件,并且要能够智能化自动批准设计和自动启用Claude完成代码,并且利用infra充分测试和推送到git等完善的流程,并且在我们的服务器上自动运行,并推送结果。3test
Review Chunk 2 (lines 1299-3048) of the implementation plan at: `/Users/chris/projects/claudeAutomation/docs/superpowers/plans/2026-03-11-local-agent-platform.md` The design spec is at: `/Users/chris/projects/claudeAutomation/docs/superpowers/specs/2026-03-11-local-agent-platform-design.md` This chunk covers Tasks 6-10: tool_registry.py, shell+files tools, memory+infra+llm+web tools, skills_loader.py, agent_loop.py. Key context about the project: - Package layout: `local_agent/` (NOT `src/`), entry point `local_agent.interfaces.cli:main` - llm-router: uses `get_async_client()` for async code, `get_model_name` from `llm_router` (not `llm_router.config`). The `track_usage()` function is also in `llm_router`. - `build_registry()` factory in `local_agent/tools/__init__.py` centralizes all tool registration - Memory tool uses `env={**os.environ, "PYTHONPATH": "."}` to preserve PATH - LLM tool uses `get_async_client(route)` since it runs in async agent loop - Agent loop uses `get_async_client("cloud")` for Claude Sonnet Review for: 1. **Critical (C)**: Wrong code that won't compile/run, wrong file paths, import errors 2. **Major (M)**: Logic bugs, security gaps, missing error handling, test gaps 3. **Minor (m)**: Style, naming, non-blocking improvements Output format: ``` ## Chunk 2 Review ### Critical - C1: [description] (line ~N) ### Major - M1: [description] (line ~N) ### Minor - m1: [description] (line ~N) ### Verdict: PASS / FAIL ``` If no issues found in a category, write "None found."3review
Update the bootstrap guide at `/Users/chris/projects/claudeAutomation/docs/bootstrap-guide.md` to reflect recent infrastructure changes. Make these specific changes: 1. **Step 2.2-2.5 — Unified deploy**: Each service section still says to run `deploy.sh` manually. Add a note at the top of "Tier 2: MacBook Services" section (after the heading, before Step 2.0) that says: ``` **Unified deploy (recommended):** After cloning the repo on both machines, use the Makefile: \`\`\`bash cd ~/projects/claudeAutomation make deploy-all # Deploy all services at once make deploy-dashboard # Deploy single service make deploy-changed # Deploy only git-changed modules make status # Verify all services \`\`\` The individual steps below document each service for understanding; in practice, `make deploy-all` handles everything. ``` 2. **Step 2.5 — Dashboard section**: Update the feature list to include task execution: - Change "Dashboard features:" section to: ``` **Dashboard features:** - Project list with rename, launch Claude, and **command execution** (test/deploy/restart via module.yaml) - **Task execution system**: declarative `module.yaml` per project, inline results with output preview - Service health monitoring (launchd status, keepalive tracking) - Audit log viewer - Nexus module registry ``` 3. **Auto-deploy section** (~line 932): Update to mention GitHub Actions runner: - Change the section to mention that `chrishohoho/claudeAutomation` has a GitHub Actions self-hosted runner on MacBook (`macbook-deploy`). On push to main, the workflow automatically: 1. Pulls latest to `~/projects/claudeAutomation/` (so module.yaml files are available) 2. Runs `deploy.py deploy --changed --local` to redeploy changed services 3. Health checks Dashboard - Keep the manual `sync-projects.sh` as fallback 4. **Quick Recovery Cheatsheet** (~line 1027): - Change "Dashboard code not updating" row to: `make deploy-dashboard` (remove the manual cp command) - Add row: `module.yaml not showing in Dashboard` → `ssh chris@100.121.64.48 "cd ~/projects/claudeAutomation && git pull --ff-only origin main"` 5. **Architecture diagram** (~line 13): Update MacBook services count from "6 launchd services" to include GitHub Actions runner. Change line to: ``` │ 7 launchd services: maintenance-agent, infra-daemon, │ │ mcp-permission(:8100), dashboard(:9000), boot-recovery, │ │ caffeinate, github-actions-runner │ ``` 6. **Update "Last updated" date** at the top to 2026-03-09 Do NOT change anything else. Keep the existing structure and content. Only update the parts mentioned above.3review
Did you finish Task 4?3other
请根据我们现在文件夹下的README,确认是否要配置额外的CLAUDEME.md来追踪系统里的Claude Code相关设置和命令,然后推送到GitHub我们的私有库里。“在 Claude Code 里 CLAUDE.md 可以直接引用它(或者把内容合并进 CLAUDE.md),这样每次开 session Claude 自动就知道这些命令和约定,不需要重复解释。 .gitignore 里记得把 .env 和密钥文件排除掉,其他配置文件推上去都没问题。“这是建议的参考3explain
执行 docs/superpowers/plans/2026-03-11-local-agent-platform.md3document

Hot Phrases (TF-IDF)

TermAvg TF-IDFDoc Freq
files0.013144
tests0.013117
自动0.01186
task0.010104
prompt0.01090
llm0.010108
search0.010105
patterns0.010100
api0.00989
更新0.00961

Best Prompts

PromptEffectivenessProject
You are implementing Phase 2, Task 1: Deep LLM Layer — Claude API Integration ## Task Description **Files:** - Create: `sidecar/llm/deep.py` - Create: `sidecar/tests/test_deep.py` - Modify: `sidecar/pyproject.toml` (add `anthropic>=0.42` to dependencies) **Implementation:** Create `sidecar/llm/deep.py`: ```python import anthropic class DeepAnalyzer: def __init__( self, api_key: str | None = None, model: str = "claude-sonnet-4-20250514", ): self.client = anthropic.AsyncAnthropic(api_key=api_key) self.model = model def build_prompt(self, running_summary: str, new_transcript: list[dict]) -> str: lines = [] for entry in new_transcript: label = "You" if entry["spk"] == "me" else "Them" lines.append(f"{label}: {entry['text']}") transcript_text = "\n".join(lines) return f"""Analyze this meeting segment: Full context summary: {running_summary} New transcript since last analysis: {transcript_text} Provide: 1. Discussion trajectory - where is this heading? 2. 3 questions/objections the other party might raise next 3. Recommended talking points for each 4. Any risks or opportunities you notice Be concise and actionable.""" def build_summary_prompt(self, previous_summary: str, new_transcript: list[dict]) -> str: lines = [] for entry in new_transcript: label = "You" if entry["spk"] == "me" else "Them" lines.append(f"{label}: {entry['text']}") transcript_text = "\n".join(lines) return f"""Update this meeting summary with new content. Previous summary: {previous_summary if previous_summary else "(meeting just started)"} New transcript: {transcript_text} Write a concise updated summary (3-5 sentences) covering all key points discussed so far.""" async def analyze(self, running_summary: str, new_transcript: list[dict]) -> str: prompt = self.build_prompt(running_summary, new_transcript) message = await self.client.messages.create( model=self.model, max_tokens=500, messages=[{"role": "user", "content": prompt}], ) return message.content[0].text async def summarize(self, previous_summary: str, new_transcript: list[dict]) -> str: prompt = self.build_summary_prompt(previous_summary, new_transcript) message = await self.client.messages.create( model=self.model, max_tokens=200, messages=[{"role": "user", "content": prompt}], ) return message.content[0].text ``` Create `sidecar/tests/test_deep.py`: ```python import pytest from unittest.mock import AsyncMock, MagicMock, patch from llm.deep import DeepAnalyzer class TestDeepAnalyzer: def test_build_prompt(self): analyzer = DeepAnalyzer(api_key="fake-key") prompt = analyzer.build_prompt( running_summary="Discussing Q2 budget cuts.", new_transcript=[ {"spk": "them", "text": "We need to cut 20%."}, {"spk": "me", "text": "That's aggressive."}, ], ) assert "trajectory" in prompt.lower() or "heading" in prompt.lower() assert "questions" in prompt.lower() or "objections" in prompt.lower() assert "cut 20%" in prompt assert "Q2 budget" in prompt def test_build_summary_prompt(self): analyzer = DeepAnalyzer(api_key="fake-key") prompt = analyzer.build_summary_prompt( previous_summary="Discussed hiring plans.", new_transcript=[ {"spk": "them", "text": "Let's also talk about budget."}, ], ) assert "hiring plans" in prompt.lower() assert "budget" in prompt.lower() @pytest.mark.anyio async def test_analyze_with_mock(self): analyzer = DeepAnalyzer(api_key="fake-key") mock_message = MagicMock() mock_message.content = [MagicMock(text="1. Discussion heading toward budget cuts.\n2. They may ask about headcount.\n3. Prepare ROI data.")] mock_client = MagicMock() mock_client.messages = MagicMock() mock_client.messages.create = AsyncMock(return_value=mock_message) with patch.object(analyzer, "client", mock_client): result = await analyzer.analyze( running_summary="Q2 planning.", new_transcript=[{"spk": "them", "text": "Cut costs."}], ) assert isinstance(result, str) assert len(result) > 0 @pytest.mark.anyio async def test_summarize_with_mock(self): analyzer = DeepAnalyzer(api_key="fake-key") mock_message = MagicMock() mock_message.content = [MagicMock(text="Discussed Q2 budget. Agreed to 15% cuts.")] mock_client = MagicMock() mock_client.messages = MagicMock() mock_client.messages.create = AsyncMock(return_value=mock_message) with patch.object(analyzer, "client", mock_client): result = await analyzer.summarize( previous_summary="", new_transcript=[ {"spk": "them", "text": "Cut 15%."}, {"spk": "me", "text": "Agreed."}, ], ) assert isinstance(result, str) assert len(result) > 0 ``` **Steps:** 1. READ `sidecar/pyproject.toml` first, then add `"anthropic>=0.42"` to the dependencies list 2. Create the implementation and test files 3. Run `cd /Users/chris/projects/voiceScript/sidecar && uv sync --all-extras` 4. Run `uv run pytest tests/test_deep.py -v` 5. All 4 tests should PASS 6. Run full suite to check regressions: `uv run pytest tests/ -v --timeout=120` 7. Commit: `git add sidecar/llm/deep.py sidecar/tests/test_deep.py sidecar/pyproject.toml && git commit -m "feat: add Claude deep analyzer for strategic insights + predicted questions"` Working directory: `/Users/chris/projects/voiceScript` **IMPORTANT:** Preserve ALL existing pyproject.toml content when adding the new dependency.100%subagents
Design a comprehensive anti-hallucination / cross-validation module for a Claude Code + Ollama + Windmill infrastructure. This is an architectural design task — produce a detailed, implementable plan. ## Context The user has the following infrastructure: - **Claude Code CLI** with Continuous Claude (32 agents, 109 skills, 30 hooks) - **Ollama** on a remote PC (100.76.181.84:11434) with qwen3:14b and qwen3.5:27b - **Windmill** workflow engine (localhost:8000) with PostgreSQL - **MacBook** (100.121.64.48) as a lightweight service node with Windmill Worker - **Memory system** with PostgreSQL + BGE embeddings for storing/recalling learnings - **Hook architecture** supporting PreToolUse, PostToolUse, UserPromptSubmit, SessionStart, Stop events ## Available Tools (from research) ### Hallucination Detection Models: 1. **Bespoke-MiniCheck** (7B) — Available on Ollama (`ollama run bespoke-minicheck`), 77.4% F1, ~200ms. Non-commercial license. 2. **Vectara HHEM 2.1** — <600MB, runs on CPU, best-in-class F1, Apache 2.0 3. **LettuceDetect** — Token-level detection, ModernBERT-based, MIT, 79.2% F1 4. **Claude Citations API** — Built-in, 15% recall boost, standard pricing ### Existing Patterns to Reuse: - `compiler-in-the-loop.ts` — PostToolUse hook that calls external LLM - `memory-awareness.ts` — UserPromptSubmit hook that injects context - `import-validator.ts` — PostToolUse validation with additionalContext - `convomind/llm_client.py` — CircuitBreaker + SQLite cache + Ollama client - `inforadar/llm.py` — Clean async Ollama client - `embedding_service.py:418` — OllamaEmbeddingProvider - `recall_learnings.py` / `store_learning.py` — Memory store/recall with dedup ## Design Requirements 1. **Accuracy first** — minimize false negatives (missed hallucinations) 2. **Opt-in per program** — each program/script can decide whether to use verification 3. **Economic** — prefer local models (Ollama, CPU models) over API calls 4. **Multi-layer** — different verification depth for different situations 5. **Integrate with existing infrastructure** — hooks, skills, Windmill, memory system 6. **Support both sync (inline) and async (background) verification** ## Architecture to Design Design a module called `veritas` (or similar) with these layers: ### Layer 1: Prompt Engineering (always on, free) - System prompt patterns that reduce hallucination - "Permit uncertainty" and "cite sources" instructions - Already partially exists in `claim-verification.md` rule ### Layer 2: Self-Consistency Check (local, cheap) - Use Ollama qwen3:14b for quick cross-examination - Generate a response, then ask a second model/prompt to verify key claims - ~2-5 seconds overhead ### Layer 3: Dedicated Verification Models (local, accurate) - Bespoke-MiniCheck on Ollama for claim-level fact checking - Vectara HHEM 2.1 on CPU for NLI-based consistency scoring - ~1-3 seconds overhead per claim ### Layer 4: Claude Citations API (for document-grounded tasks) - When working with source documents, use Citations API - Highest accuracy but costs tokens ### Integration Points: 1. **PostToolUse hook** — verify factual claims in tool outputs 2. **`/verify` skill** — on-demand verification of any text 3. **Windmill async job** — batch verification of documents/outputs 4. **Memory integration** — store verified/refuted facts for future recall 5. **Python SDK** — `from veritas import verify(text, context)` for any program ### Deployment: - Core library: Python package at `~/tools/veritas/` - Hook: TypeScript at `~/.claude/hooks/src/veritas-hook.ts` - Skill: `~/.claude/skills/verify/SKILL.md` - Windmill script: verification workflow - Ollama model: bespoke-minicheck pre-pulled on PC - HHEM model: pre-downloaded on MacBook (CPU inference) ## Deliverables Produce a detailed architecture document covering: 1. System overview with ASCII diagram 2. Component specifications (each layer) 3. API design (Python SDK interface) 4. Integration specifications (hooks, skills, Windmill) 5. Deployment plan (what goes where) 6. Cost/performance analysis 7. Implementation order (what to build first) Consider the HaluGate pattern (conditional routing — skip verification for creative/coding queries, full verification for factual queries) to save compute. Think deeply about edge cases: - What happens when Ollama PC is offline? - How to handle verification timeout? - How to avoid infinite verification loops? - How to handle conflicting verification results? - Cache strategy for repeated verifications?100%subagents
You are fixing a critical issue: FTS5's default unicode61 tokenizer does not segment Chinese text into words, making Chinese BM25 search non-functional. ## The Problem SQLite FTS5's `unicode61` tokenizer splits text by whitespace/punctuation. Chinese has no spaces between words, so "推荐用FastAPI写代码" becomes one giant token instead of ["推荐", "用", "FastAPI", "写", "代码"]. BM25 search for "FastAPI" works (it's surrounded by non-ASCII), but searching for "推荐" fails. ## The Solution Use jieba for Chinese word segmentation. Register a custom SQLite function that segments text before FTS insertion and search. ### Step 1: Add jieba dependency ```bash uv add jieba ``` ### Step 2: Create tokenizer module **src/wechatsync/db/tokenizer.py**: ```python import jieba import re def segment_for_fts(text: str) -> str: """Segment Chinese text with jieba for FTS5 indexing. Inserts spaces between Chinese words while preserving non-Chinese tokens (English words, numbers, URLs). """ if not text: return "" # jieba.cut handles mixed Chinese/English well words = jieba.cut(text, cut_all=False) return " ".join(w.strip() for w in words if w.strip()) ``` ### Step 3: Register in SQLite connections Modify **src/wechatsync/db/sqlite.py**: - In both `init_db()` and `get_connection()`, after connecting: ```python from wechatsync.db.tokenizer import segment_for_fts conn.create_function("segment", 1, segment_for_fts) ``` ### Step 4: Modify FTS triggers In the SCHEMA DDL in sqlite.py, change the AFTER INSERT triggers to segment content: ```sql -- Old: CREATE TRIGGER IF NOT EXISTS messages_ai AFTER INSERT ON messages BEGIN INSERT INTO messages_fts(rowid, content, sender_name) VALUES (new.id, new.content, new.sender_name); END; -- New: CREATE TRIGGER IF NOT EXISTS messages_ai AFTER INSERT ON messages BEGIN INSERT INTO messages_fts(rowid, content, sender_name) VALUES (new.id, segment(new.content), new.sender_name); END; -- Same for knowledge_fts trigger: CREATE TRIGGER IF NOT EXISTS knowledge_ai AFTER INSERT ON knowledge_items BEGIN INSERT INTO knowledge_fts(rowid, title, summary, tags) VALUES (new.id, segment(new.title), segment(new.summary), new.tags); END; ``` ### Step 5: Segment search queries Modify **src/wechatsync/search/engine.py** `bm25_search()`: - Before passing query to FTS MATCH, segment it: ```python from wechatsync.db.tokenizer import segment_for_fts segmented_query = segment_for_fts(query) ``` - Use segmented_query in the MATCH clause ### Step 6: Write tests **tests/test_tokenizer.py**: - test_segment_chinese: "推荐用Cursor写代码" → segments with spaces, both "推荐" and "Cursor" are separate tokens - test_segment_english: "FastAPI is great" → stays mostly the same - test_segment_mixed: "张三推荐的Python框架" → Chinese words separated, "Python" preserved - test_segment_empty: "" → "" - test_segment_url: "看这个 https://example.com" → URL preserved **tests/test_chinese_search.py**: - test_chinese_fts_search: Insert Chinese message, search with Chinese keyword, verify found - test_chinese_knowledge_search: Insert Chinese knowledge item, search with Chinese keyword, verify found - test_mixed_language_search: Insert mixed Chinese/English, search in either language works ### Step 7: Verify existing tests still pass Run full test suite: `uv run pytest tests/ -v` ### Step 8: Commit ```bash git add -A && git commit -m "fix: add jieba Chinese tokenization for FTS5 search" ``` ## Context Project at /Users/chris/projects/weChat微信自动化/. 236 tests passing. Key files: - src/wechatsync/db/sqlite.py — schema DDL + init_db/get_connection - src/wechatsync/search/engine.py — bm25_search function IMPORTANT: The trigger change means existing tests that create DBs will now need the segment function registered. Make sure init_db registers it. All test fixtures use init_db so they should get it automatically. NOTE: jieba prints "Building prefix dict from the default dictionary..." on first use. You can suppress this with `jieba.setLogLevel(logging.WARNING)` in the tokenizer module. Work from: /Users/chris/projects/weChat微信自动化/100%subagents
You are a top-tier LLM/SLM infrastructure researcher. Do comprehensive web research on the current state of Small Language Models (SLMs) for local/edge deployment in 2026. This is RESEARCH ONLY — do not write any code. Search for and compile findings on: 1. **Top SLM models in 2026** (1B-10B parameters range): - Qwen 3.5 variants (we already have qwen3.5:35b-a3b, qwen3.5:9b, qwen3.5:27b on Ollama) - Phi-4/Phi-4-mini (Microsoft) - Gemma 3 (Google) - Llama 4 Scout/Maverick (Meta) - SmolLM2 (Hugging Face) - Any other notable SLMs released in 2025-2026 - Compare: quality, speed, VRAM usage, best use cases 2. **SLM routing/orchestration frameworks**: - LLM routers (RouteLLM, Martian, etc.) - When to use big model vs small model (cost/quality routing) - Semantic Router, LiteLLM proxy, anything that helps route between local SLM and cloud API - Model cascading patterns (try small first, escalate to big) 3. **Edge/local deployment patterns**: - Ollama latest capabilities (tool calling, structured output, vision) - vLLM for local serving - llama.cpp / llama-cpp-python advances - Quantization best practices (GGUF Q4/Q5/Q8, AWQ, GPTQ) - Speculative decoding with small+large model pairs 4. **Practical SLM use cases that work well**: - Text classification/routing - Summarization - Code completion (local) - Embedding generation - Structured data extraction (JSON mode) - Tool calling / function calling - RAG query rewriting - What does NOT work well with SLMs (complex reasoning, long context, etc.) 5. **Industry patterns for hybrid local+cloud architectures**: - Privacy-first routing (sensitive data → local, rest → cloud) - Cost optimization (80% local, 20% cloud for hard queries) - Latency optimization patterns - Fallback/cascade architectures Please provide detailed findings with specific model names, framework names, and links where possible. Focus on what's practical and production-ready, not just research papers.100%subagents
Research the current working career page APIs for Netflix and Meta as of March 2026. ## Netflix - The old Workday URL `https://netflix.wd1.myworkdayjobs.com/wday/cxs/netflix/jobs/jobs` returns 404 - Search the web for Netflix's current career page: jobs.netflix.com or similar - Find the actual API endpoint or data source that powers their job search - Test different URL patterns like: - https://jobs.netflix.com/api/search - https://explore.jobs.netflix.net/api/apply/v2/jobs - Netflix might use a custom platform now, not Workday - I need: endpoint URL, request method, parameters for searching "software engineer" jobs ## Meta - metacareers.com blocks all non-browser HTTP requests with 400 - Look for alternative approaches that DON'T require Playwright: - Does Meta have a public job API? - Can we use the Facebook Graph API for job listings? - Is there a jobs RSS feed? - Can we scrape the server-rendered HTML with the right headers/cookies? - Check if `www.metacareers.com/jobs?q=software+engineer` works with specific headers - Try: curl with full browser headers including sec-fetch-site, sec-fetch-mode etc. - Check if there's embedded JSON in the initial HTML response (like __RELAY_STORE__) For both, I need the working endpoint, request format, and response structure.100%subagents
Audit network exposure and authentication for the user's local services. Check: 1. **Listening ports** - run `lsof -i -P -n | grep LISTEN` to see what's listening and on what interfaces 2. **Firewall status** - check macOS firewall: `defaults read /Library/Preferences/com.apple.alf globalstate` or `/usr/libexec/ApplicationFirewall/socketfilterfw --getglobalstate` 3. **Tailscale status** - run `tailscale status` to check network isolation 4. **Service authentication**: - Check Windmill docker-compose.yml for auth config - Check Dashboard for auth/authentication mechanisms - Check if any services have rate limiting disabled for localhost - Check LibreChat auth config 5. **Docker port exposure** - check all running Docker containers and their port mappings: `docker ps --format "{{.Names}}\t{{.Ports}}"` 6. **SSH config** - check `~/.ssh/sshd_config` or system sshd_config for what address SSH listens on Report: - Services accessible from LAN (not just Tailscale) - Services with no authentication - Any rate limiting gaps DO NOT modify any files. Research only.100%subagents
Explore the claudeAutomation project to understand what existing infrastructure could support a desktop agent system. Look for: 1. **Skills system** - how are skills currently structured in ~/.claude/skills/ or continuous-claude? 2. **LLM Router** - how does llm-router/ work for routing to different models? 3. **Browser automation** - any existing browser scripts or patterns in docs/ 4. **MCP servers** - what MCP integrations exist? 5. **Dashboard** - how does the dashboard work for task execution? 6. **Maintenance agent** - how does the maintenance agent orchestrate tasks? 7. **Any existing automation scripts** in scripts/ that do file manipulation, image processing, etc. Focus on: what building blocks already exist that could be reused for a local desktop agent. Search in: - /Users/chris/projects/claudeAutomation/ - /Users/chris/.claude/ - /Users/chris/projects/claudeAutomation/docs/ - /Users/chris/projects/claudeAutomation/llm-router/ - /Users/chris/projects/claudeAutomation/dashboard/100%subagents
Audit all service configurations in ~/projects/claudeAutomation/ and ~/tools/ for port binding security. Check: 1. Docker compose files - are ports mapped to 0.0.0.0 or 127.0.0.1? 2. Any Python/Node servers - what address do they bind to? 3. Dashboard, MCP Permission, Infra Daemon configs Search for: - `docker-compose.yml` or `compose.yaml` files in ~/tools/windmill/, ~/tools/librechat/, ~/tools/continuous-claude/ - Port binding patterns: `0.0.0.0`, `bind`, `host`, `listen` in config files - Python server configs with `host=` parameters - Any `gateway.bind`, `server.host` type configs For each service found, report: - Service name - Port - Bind address (0.0.0.0 vs 127.0.0.1 vs other) - Whether it's behind Tailscale or exposed to LAN DO NOT modify any files. Research only.100%subagents
I need to understand the current infrastructure for a "maintenance window" feature. Explore these areas in /Users/chris/projects/claudeAutomation/: 1. **infra-daemon/** — What does it currently do? What's in daemon.py, config.yaml, jobs/? What scheduling exists? 2. **LaunchAgents** — What launchd services exist at /Users/chris/Library/LaunchAgents/com.claude.* ? 3. **Session detection** — How could we detect if Claude Code is currently active? Check ~/.claude/ for session files, heartbeat mechanisms, or running processes. 4. **Existing automation** — Any scripts in scripts/ that do maintenance/health checks? 5. **Windmill** — Any existing scheduled tasks at ~/tools/windmill/? Report a summary of what exists and what hooks are available for autonomous maintenance.100%subagents
Research Cline (VS Code AI coding agent extension) session/chat history file format. I need: 1. Where Cline stores its session history files (likely in VS Code's extension storage) 2. File format (JSON, JSONL, SQLite, other?) 3. How user messages are distinguished from AI responses 4. Any metadata (timestamps, model, task IDs) Search strategies: - Check common VS Code extension storage paths: ~/.vscode/extensions/, ~/Library/Application Support/Code/ - Look for cline-related directories or files - Search for "cline vscode session history" or "cline chat log format" - Cline was previously called "Claude Dev" - check both names - The extension stores task history locally Return: file location, format details, parsing strategy, and any example content you can find.100%subagents

Category Effectiveness

Short Prompt Alerts

"怎么彻底删除当前的session" — only 16 chars
"我们的容量是2TB,刚刚的复制粘贴是网上的信息" — only 23 chars

Specificity Tips

No tips.

Tips

Insights