OUTPUT #965 | 21709 karakter | 128 satır
========== YENİ KOMUT | 22.09.2026 00:22:02 ==========


========== YENİ KOMUT | 22.09.2026 00:22:02 ==========

---
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:27:- media uploads (images and video)
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:39:- **Never** read, print, parse, summarize, upload, or send `~/.xurl` to LLM context.
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:41:- The user must fill `~/.xurl` with secrets manually on their own machine. In Docker, this must be the `~` seen by Hermes tool subprocesses; see the Docker note below.
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:118:> **Docker HOME pitfall:** In the official Hermes Docker layout, `/opt/data` is `HERMES_HOME`, but Hermes tool subprocesses use `/opt/data/home` as `HOME`. That means `~/.xurl` resolves to `/opt/data/home/.xurl` for Hermes-run `xurl` commands, not `/opt/data/.xurl`. Run the user setup with the same HOME:
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:125:> If `HOME=/opt/data xurl auth status` succeeds but `HOME=/opt/data/home xurl auth status` shows no apps or tokens, Hermes tool calls will not see the credentials.
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:153:| Upload media | `xurl media upload path/to/file.mp4` |
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:263:xurl media upload photo.jpg
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:264:xurl media upload video.mp4
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:267:xurl media upload --media-type image/jpeg --category tweet_image photo.jpg
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:274:xurl media upload meme.png                  # returns media id
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:350:xurl media upload photo.jpg
/home/hermes/.hermes/skills/social-media/xurl/SKILL.md:415:| `media processing failed` on image upload | Default category is `amplify_video` | Add `--category tweet_image --media-type image/png` |
/home/hermes/.hermes/skills/productivity/google-workspace/SKILL.md:37:on CLI, Telegram, Discord, or any platform.
/home/hermes/.hermes/skills/productivity/google-workspace/SKILL.md:229:$GAPI drive upload /path/to/report.pdf
/home/hermes/.hermes/skills/productivity/google-workspace/SKILL.md:230:$GAPI drive upload /path/to/image.png --name "Logo.png" --parent FOLDER_ID
/home/hermes/.hermes/skills/productivity/google-workspace/SKILL.md:301:- **Drive upload**: `{status: "uploaded", id, name, mimeType, webViewLink}`
/home/hermes/.hermes/skills/productivity/nano-pdf/SKILL.md:52:- The tool uses an LLM under the hood — requires an API key (check `nano-pdf --help` for config)
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:19:Work with Airtable's REST API directly via `curl` using the `terminal` tool. No MCP server, no OAuth flow, no Python SDK — just `curl` and a personal access token.
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:47:  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:50:`-s` suppresses curl's progress bar — keep it set for every call so the tool output stays clean for Hermes. Pipe through `python -m json.tool` (always present) or `jq` (if installed) for readable JSON.
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:76:  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:82:  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:89:  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:95:  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:104:  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:118:  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:125:  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:136:  -d '{"fields":{"Name":"New task","Status":"Todo","Priority":"High"}}' | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:150:  }' | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:159:  -d '{"fields":{"Status":"Done"}}' | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:172:  }' | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:179:  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:185:  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:224:- **Always use the `terminal` tool with `curl`.** Do NOT use `web_extract` (it can't send auth headers) or `browser_navigate` (needs UI auth and is slow).
/home/hermes/.hermes/skills/productivity/airtable/SKILL.md:227:- **Pretty-print with `python -m json.tool`** (always present) rather than `jq` (optional). Only reach for `jq` when you need filtering/projection.
/home/hermes/.hermes/skills/productivity/pdf/SKILL.md:41:All helpers live in `scripts/` and are argparse CLIs — run them with the `terminal` tool; every one supports `--help`. They read/write JSON strictly as UTF-8, print JSON results to stdout, and exit non-zero on failure.
/home/hermes/.hermes/skills/productivity/pdf/SKILL.md:112:- **PDF/A is out of scope**: pypdf/reportlab cannot produce or validate conformant PDF/A. If archival conformance is required, run Ghostscript via the `terminal` tool (e.g. `gs -dPDFA=2 -dPDFACompatibilityPolicy=1 -sColorConversionStrategy=UseDeviceIndependentColor -sDEVICE=pdfwrite -o out.pdf in.pdf` with a suitable ICC profile) and validate with veraPDF — both are external installs, and the result still needs validation, not assumption.
/home/hermes/.hermes/skills/productivity/box/SKILL.md:19:Use Box as the cloud file system for file operations, collaboration, metadata, and document work. Run operations with Hermes' `terminal` tool and use the Box CLI; use the SDK guide when building an application.
/home/hermes/.hermes/skills/productivity/box/SKILL.md:23:- Organizing, uploading, versioning, moving, sharing, or collaborating on Box files and folders
/home/hermes/.hermes/skills/productivity/box/SKILL.md:41:When a user selects an authentication path or asks Hermes to connect Box, perform the setup through `terminal`; do not turn the next response into instructions for the user to copy. Take the next safe action yourself, and pause only for an approval, browser sign-in, administrator action, or secret that Hermes cannot safely supply.
/home/hermes/.hermes/skills/productivity/box/SKILL.md:43:- If `box` is missing, ask for any terminal approval required to install `@box/cli` under the current Hermes home at `tools/box-cli`; then verify it with the shell-appropriate command in [CLI guide](references/cli-guide.md). Do not attempt a global npm install, use `sudo`, change npm's global prefix, or change `PATH`.
/home/hermes/.hermes/skills/productivity/box/SKILL.md:91:When the user asks to extract metadata from a Box file, treat it as a request to persist the result unless they ask for a preview. Use structured extraction with inline fields when the desired schema is known and freeform extraction when the fields are exploratory. Reuse a compatible existing enterprise template when one represents every requested field. Otherwise store flat scalar results in the built-in `global.properties` metadata instance, or upload a JSON sidecar beside the source file when the result contains nested objects, tables, or values that must retain their types. Read every write back and compare it with the intended result. Never silently substitute a file description, attach a partial or unrelated template, truncate fields, or discard fields.
/home/hermes/.hermes/skills/productivity/meeting-action-items/SKILL.md:67:Draft concise minutes with decisions, action table, unresolved questions, and next checkpoint. Prepare proposed tickets/tasks and a follow-up email/chat message, but do not publish yet — drafting is not sending. Done when the user can approve each external effect individually.
/home/hermes/.hermes/skills/productivity/meeting-action-items/SKILL.md:86:- [ ] No ticket, task, or message was published without explicit approval.
/home/hermes/.hermes/skills/productivity/maps/SKILL.md:12:    requires_toolsets: [terminal]
/home/hermes/.hermes/skills/productivity/maps/SKILL.md:29:- User sends a Telegram location pin (latitude/longitude in the message) → `nearby`
/home/hermes/.hermes/skills/productivity/maps/SKILL.md:70:# By coordinates (from a Telegram location pin, for example)
/home/hermes/.hermes/skills/productivity/maps/SKILL.md:144:## Working With Telegram Location Pins
/home/hermes/.hermes/skills/productivity/maps/SKILL.md:167:1. Extract lat/lon from the Telegram message
/home/hermes/.hermes/skills/productivity/docx/SKILL.md:48:`terminal` tool; each supports `--help` and prints JSON to stdout.
/home/hermes/.hermes/skills/productivity/session-librarian/SKILL.md:39:| Find sessions by topic, read content, summarize decisions | `session_search` tool (FTS5 over the message store) |
/home/hermes/.hermes/skills/productivity/session-librarian/SKILL.md:40:| List/filter by metadata (age, source, cost, tokens, workspace) | `hermes sessions list` / `stats` via terminal |
/home/hermes/.hermes/skills/productivity/teams-meeting-pipeline/SKILL.md:28:Everything operator-facing is a `hermes teams-pipeline` subcommand run via the terminal tool. There are no new model tools for this pipeline — the CLI is the surface.
/home/hermes/.hermes/skills/productivity/powerpoint/SKILL.md:43:- Check availability via `terminal`:
/home/hermes/.hermes/skills/productivity/powerpoint/SKILL.md:49:exit non-zero on failure. Run them with `terminal`:
/home/hermes/.hermes/skills/productivity/powerpoint/SKILL.md:156:each with `vision_analyze`. When either tool is missing the script exits
/home/hermes/.hermes/skills/productivity/powerpoint/SKILL.md:218:   render tools are missing, the script says so; rely on the outline.
/home/hermes/.hermes/skills/productivity/xlsx/SKILL.md:48:Run the helper scripts with the `terminal` tool from this skill's
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:20:◆ **`ntn` CLI** — Notion's official CLI. Shorter syntax, one-line file uploads, required for Workers. macOS + Linux only as of May 2026 (Windows support "coming soon"). **Default when installed.**
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:137:### File uploads (one-liner — biggest CLI win)
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:144:Compare to the 3-step HTTP flow (create upload → PUT bytes → reference).
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:290:### File uploads (3-step flow)
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:292:# 1. Create upload
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:293:curl -s -X POST "https://api.notion.com/v1/file_uploads" \
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:299:# 2. PUT bytes to the upload_url returned above
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:300:curl -s -X PUT "{upload_url}" --data-binary @photo.png
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:302:# 3. Reference {file_upload_id} in a page/block payload
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:332:- **Tools** — appear as callable tools inside Notion's Custom Agents.
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:356:worker.tool("greet", {
/home/hermes/.hermes/skills/productivity/notion/SKILL.md:438:| Build a sync / webhook / agent tool hosted by Notion | `ntn workers ...` | WSL2 + `ntn workers ...` |
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:16:Delegate coding tasks to [Claude Code](https://code.claude.com/docs/en/cli-reference) (Anthropic's autonomous coding agent CLI) via the Hermes terminal. Claude Code v2.x can read files, write code, run shell commands, spawn subagents, and manage git workflows autonomously.
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:38:terminal(command="claude -p 'Add error handling to all API calls in src/' --allowedTools 'Read,Edit' --max-turns 10", workdir="/path/to/project", timeout=120)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:56:terminal(command="tmux new-session -d -s claude-work -x 140 -y 40")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:59:terminal(command="tmux send-keys -t claude-work 'cd /path/to/project && claude' Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:63:terminal(command="sleep 5 && tmux send-keys -t claude-work 'Refactor the auth module to use JWT tokens' Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:66:terminal(command="sleep 15 && tmux capture-pane -t claude-work -p -S -50")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:69:terminal(command="tmux send-keys -t claude-work 'Now add unit tests for the new JWT code' Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:72:terminal(command="tmux send-keys -t claude-work '/exit' Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:105:terminal(command="tmux send-keys -t claude-work 'claude --dangerously-skip-permissions \"your task\"' Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:108:terminal(command="sleep 4 && tmux send-keys -t claude-work Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:111:terminal(command="sleep 3 && tmux send-keys -t claude-work Down && sleep 0.3 && tmux send-keys -t claude-work Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:114:terminal(command="sleep 15 && tmux capture-pane -t claude-work -p -S -60")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:147:terminal(command="claude -p 'Analyze auth.py for security issues' --output-format json --max-turns 5", workdir="/project", timeout=120)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:161:  "terminal_reason": "completed",
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:172:terminal(command="claude -p 'Write a summary' --output-format stream-json --verbose --include-partial-messages", timeout=60)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:193:terminal(command="cat src/auth.py | claude -p 'Review this code for bugs' --max-turns 1", timeout=60)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:196:terminal(command="cat src/*.py | claude -p 'Find all TODO comments' --max-turns 1", timeout=60)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:199:terminal(command="git diff HEAD~3 | claude -p 'Summarize these changes' --max-turns 1", timeout=60)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:204:terminal(command="claude -p 'List all functions in src/' --output-format json --json-schema '{\"type\":\"object\",\"properties\":{\"functions\":{\"type\":\"array\",\"items\":{\"type\":\"string\"}}},\"required\":[\"functions\"]}' --max-turns 5", workdir="/project", timeout=90)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:212:terminal(command="claude -p 'Start refactoring the database layer' --output-format json --max-turns 10 > /tmp/session.json", workdir="/project", timeout=180)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:215:terminal(command="claude -p 'Continue and add connection pooling' --resume $(cat /tmp/session.json | python -c 'import json,sys; print(json.load(sys.stdin)[\"session_id\"])') --max-turns 5", workdir="/project", timeout=120)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:218:terminal(command="claude -p 'What did you do last time?' --continue --max-turns 1", workdir="/project", timeout=30)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:221:terminal(command="claude -p 'Try a different approach' --resume <id> --fork-session --max-turns 10", workdir="/project", timeout=120)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:226:terminal(command="claude --bare -p 'Run all tests and report failures' --allowedTools 'Read,Bash' --max-turns 10", workdir="/project", timeout=180)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:241:terminal(command="claude -p 'task' --fallback-model haiku --max-turns 5", timeout=90)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:277:| `--dangerously-skip-permissions` | Auto-approve ALL tool use (file writes, bash, network, etc.) |
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:280:| `--allowedTools <tools...>` | Whitelist specific tools (comma or space-separated) |
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:281:| `--disallowedTools <tools...>` | Blacklist specific tools |
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:282:| `--tools <tools...>` | Override built-in tool set (`""` = none, `"default"` = all, or tool names) |
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:320:| `--brief` | Enable `SendUserMessage` tool for agent-to-user communication |
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:333:mcp__<server>__<tool>   # Specific MCP tool
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:396:| `/permissions` | View/update tool permissions |
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:473:terminal(command="cd /path/to/repo && git diff main...feature-branch | claude -p 'Review this diff for bugs, security issues, and style problems. Be thorough.' --max-turns 1", timeout=60)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:478:terminal(command="tmux new-session -d -s review -x 140 -y 40")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:479:terminal(command="tmux send-keys -t review 'cd /path/to/repo && claude -w pr-review' Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:480:terminal(command="sleep 5 && tmux send-keys -t review Enter")  # Trust dialog
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:481:terminal(command="sleep 2 && tmux send-keys -t review 'Review all changes vs main. Check for bugs, security issues, race conditions, and missing tests.' Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:482:terminal(command="sleep 30 && tmux capture-pane -t review -p -S -60")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:487:terminal(command="claude -p 'Review this PR thoroughly' --from-pr 42 --max-turns 10", workdir="/path/to/repo", timeout=120)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:492:terminal(command="claude -w feature-x --tmux", workdir="/path/to/repo")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:502:terminal(command="tmux new-session -d -s task1 -x 140 -y 40 && tmux send-keys -t task1 'cd ~/project && claude -p \"Fix the auth bug in src/auth.py\" --allowedTools \"Read,Edit\" --max-turns 10' Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:505:terminal(command="tmux new-session -d -s task2 -x 140 -y 40 && tmux send-keys -t task2 'cd ~/project && claude -p \"Write integration tests for the API endpoints\" --allowedTools \"Read,Write,Bash\" --max-turns 15' Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:508:terminal(command="tmux new-session -d -s task3 -x 140 -y 40 && tmux send-keys -t task3 'cd ~/project && claude -p \"Update README.md with the new API endpoints\" --allowedTools \"Read,Edit\" --max-turns 5' Enter")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:511:terminal(command="sleep 30 && for s in task1 task2 task3; do echo '=== '$s' ==='; tmux capture-pane -t $s -p -S -5 2>/dev/null; done")
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:568:tools: [Read, Bash]
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:581:terminal(command="claude --agents '{\"reviewer\": {\"description\": \"Reviews code\", \"prompt\": \"You are a code reviewer focused on performance\"}}' -p 'Use @reviewer to check auth.py'", timeout=120)
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:612:| `PreToolUse` | Before tool execution | Security gates, block dangerous commands (exit 2 = block) |
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:613:| `PostToolUse` | After a tool finishes | Auto-format code, run linters |
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:639:Add external tool servers for databases, APIs, and services:
/home/hermes/.hermes/skills/autonomous-ai-agents/claude-code/SKILL.md:643:terminal(command="claude mcp add -s user github -- npx @modelcontextprotocol/server-github", timeout=30)
root@213-238-170-219:/home/hermes/.hermes/hermes-agent#