Search: acting
29 result(s) on page 1
When_Claude_reads_a_file_containing_an_API_key,_the_raw_key_content_gets_sent_to_Claude's_servers._key-guard_prevents_this_by_acting_as_a_local_middleman_—_Claude_calls_a_tool,_the_tool_reads_the_key_and_makes_the_API_call_locally,_and_only_the_result_is_returned_to_Claude.
Security guardrail: prevents API keys from being sent to Claude. Triggers when user asks to call an external API, use a key, check credentials, read .env fil...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__#_key-guard__A_local_MCP_server_that_keeps_API_keys_off_Claude's_servers.__##_Why_This_Exists__When_Claude_reads_a_file_containing_an_API_key,_the_raw_key_content_gets_sent_to_Claude's_servers._key-guard_prevents_this_by_acting_as_a_local_middleman_—_Claude_calls_a_tool,_the_tool_reads_the_key_and_makes_the_API_call_locally,_and_only_the_result_is_returned_to_Claude.An_AI-powered_tool_that_turns_conversations_into_polished,_structured_summary_cards_by_extracting_key_ideas,_action_items,_and_next_steps.
Say "Help me install this skill from https://clawhub.ai/shuminliu026/chat-summary-card" to your local agent, then turn conversations into polished visual sum...
quarantinedconversation-summaryshareable-summaryClawHub- Registry
- ClawHub
- Version
- 1.0.5
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__An_AI-powered_tool_that_turns_conversations_into_polished,_structured_summary_cards_by_extracting_key_ideas,_action_items,_and_next_steps.For_example,_add_a_2-second_wait_after_`mouse_click`_to_avoid_operation_failure_due_to_slow_system_response.
Professional Windows-only visual automation toolkit with 11 modules for screenshot, OCR, template matching, clicks, input, environment setup, and looping tasks.
quarantinedai-agentopenclawvisual-automationClawHub- Registry
- ClawHub
- Category
- AI Agents
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__OpenClaw_11-in-1_Visual_Automation_Suite_(Windows_Only)_Complete_visual_automation_toolkit_with_11_integrated_modules.__###_💰_Price_One-time_purchase:_**$2.99**_(Lifetime_access_to_all_modules_+_future_updates)__###_🚀_How_to_Purchase_1.__Pay_via_PayPal_Invoice:_____🔗_[Click_to_pay_$2.99](https:____www.paypal.com__invoice__p__#V2RC9S8LVKJ434R9)_2.__After_payment,_send_your_email_to:_**[email protected]**_3.__I_will_send_the_full_download_link_within_12_hours.__###_🖥️_Compatibility_-_Windows_10____11_only_-_Not_compatible_with_macOS____Linux_##_1._Product_Basic_Description_###_1.1_Core_Functions_Provides_professional_universal_computer_vision_automation_capabilities_covering_the_full-process_visual_automation_scenarios_such_as_environment_initialization,_full-screen_automatic_screenshot,_OCR_text_recognition,_template_matching_target_localization,_mouse_click_simulation,_keyboard_input_simulation,_and_complete_environment_initialization_&_cleanup_mechanisms._It_supports_custom_task_combination_and_cyclic_execution.__###_1.2_Version_&_Directory_Description_-_Core_Capability:_Flexible_invocation_based_on_minimum_executable_units,_supporting_parameter_customization,_result_variable_inheritance,_and_custom_skill_saving._All_functions_can_be_used_directly_with_the_`call`_command_right_after_extracting_the_package._-_Directory_Structure:____-_`claw.json`_-_Skill_package_configuration_file___-_`skills__all_skills.claw`_-_All_skill_unit_definitions___-_`templates__`_-_Directory_for_template_images_(place_your_template_images_here_for_matching)___-_Temporary_file_directory_`temp__`_(for_storing_screenshots_like_temp__screen.png)_is_automatically_created_after_executing_`init_env`;_temporary_screenshot_files_can_be_cleaned_up_via_`clean_temp`._-_Version_Info:_Current_version:_1.0.0;_Compatible_with_OpenClaw_>=_1.0.0__###_1.3_Paid_Attribute_This_automation_skill_system_(vision-auto-tool-pro)_is_a_paid_professional_toolkit._The_document_does_not_explicitly_authorize_commercial_use_of_the_toolkit._The_paid_permission_only_covers_basic_usage_(non-commercial_by_default),_and_commercial_use_requires_separate_confirmation_of_authorization_with_the_provider_(e.g.,_purchasing_a_commercial_license,_signing_a_commercial_agreement).__##_2._Complete_Skill_Invocation_Manual_###_Important_Notes_Ensure_sufficient_time_is_reserved_for_the_computer_to_respond_to_each_click_or_operation._For_example,_add_a_2-second_wait_after_`mouse_click`_to_avoid_operation_failure_due_to_slow_system_response.__###_2.1_List_of_All_Minimum_Executable_Units_|_Unit_Name_______________|_Fixed_Call_Name__________|_Function_Description_________________________________________________________________|_Individual_Call_Method__________________________|_|-------------------------|--------------------------|--------------------------------------------------------------------------------------|-------------------------------------------------|_|_Initialize_Environment__|_`init_env`_______________|_Create_directory_structure,_clear_temporary_files,_check_template_directory__________|_`call_init_env`__________________________________|_|_Full_Screen_Screenshot__|_`screenshot_full`________|_Capture_entire_screen_and_save_as_temp__screen.png____________________________________|_`call_screenshot_full`___________________________|_|_Check_Screenshot_Validity_|_`check_screenshot_valid`_|_Check_for_black_screen__freeze,_wake_up_the_interface_if_invalid______________________|_`call_check_screenshot_valid`____________________|_|_Wake_Interface__________|_`wake_window`____________|_Solve_the_problems_of_background_non-rendering_and_black_screenshot___________________|_`call_wake_window`_______________________________|_|_OCR_Recognition_________|_`ocr_recognize`__________|_Recognize_all_text_on_the_screen_and_their_corresponding_coordinates__________________|_`call_ocr_recognize`_____________________________|_|_Template_Matching_______|_`template_match`_________|_Use_template_image_to_match_and_locate_icons__buttons__________________________________|_`call_template_match_category_template_name`_____|_|_Unified_Localization____|_`locate_target`__________|_Prioritize_OCR_positioning;_use_template_matching_if_not_found,_return_coordinates___|_`call_locate_target_target_text_OR_category+template_name`_|_|_Mouse_Click_____________|_`mouse_click`____________|_Move_to_the_specified_coordinates_and_perform_click_operation________________________|_`call_mouse_click_X_Y_[click_type,_default=single_click]`_|_|_Keyboard_Input__________|_`keyboard_input`_________|_Input_text_after_locating_the_input_box______________________________________________|_`call_keyboard_input_target_coords__description_input_content`_|_|_Clean_Temporary_Files___|_`clean_temp`_____________|_Delete_temporary_screenshots_and_free_up_storage_space_______________________________|_`call_clean_temp`________________________________|_|_Loop_Restart____________|_`loop_restart`___________|_Wait_2_seconds_then_go_back_to_the_screenshot_step_and_restart_the_process___________|_`call_loop_restart`______________________________|__###_2.2_Method_for_Invoking_Individual_Units_####_Invocation_Format_```_call_[unit_call_name]_[parameter...]_```_####_Invocation_Examples_-_Initialize_environment:_`call_init_env`_-_Template_match_browser_icon_on_desktop:_`call_template_match_desktop_web`_-_Perform_double-click_at_coordinates_(100,200):_`call_mouse_click_100_200_double`__###_2.3_Combine_into_Custom_New_Tasks_By_writing_one_call_instruction_per_line_in_execution_order,_you_can_combine_them_into_a_custom_new_task,_which_supports_variable_inheritance,_looping,_and_permanent_saving.__####_Format_Example_(Open_Browser)_```_#_Task_Name:_Open_Browser_call_init_env_call_screenshot_full_call_check_screenshot_valid_call_locate_target_browser_desktop_Browser_call_mouse_click_{{resultX}}_{{resultY}}_double_call_clean_temp_```__####_Combination_Steps_1._**Write_task_name_and_description_first**_(for_easier_identification_later)_2._**In_execution_order**,_write_one_`call_unit_name_parameters`_instruction_per_line_3._Coordinates_can_use_variables_`{{resultX}}`__`{{resultY}}`_to_inherit_the_output_result_of_the_previous_unit_4._If_cyclic_execution_is_required,_add_`call_loop_restart`_at_the_end_5._**Save_custom_skill**:_Use_`save_skill_skill_name_instruction_list`_to_save_the_task_permanently,_then_call_it_directly_with_`call_skill_name`__###_2.4_Complete_Main_Flow_Invocation_Example_```_#_General_Main_Flow:_vision_auto_main_call_init_env_call_screenshot_full_call_check_screenshot_valid_call_ocr_recognize_#_If_template_matching_is_needed,_add_this_line:_call_template_match_category_name_call_locate_target_target_text_call_mouse_click_{{X}}_{{Y}}_#_If_text_input_is_needed,_replace_the_above_line_with:_call_keyboard_input_{{X}}_{{Y}}_input_content_call_clean_temp_#_Add_this_line_if_you_need_to_loop:_call_loop_restart_```___###_Important_Notes_Ensure_sufficient_time_is_reserved_for_the_computer_to_respond_to_each_click_or_operation.___>__For_example,_add_a_2-second_wait_after_`mouse_click`_to_avoid_operation_failure_due_to_slow_system_response.
ReAct_Loop
Solve complex problems by interleaving reasoning with actions. Based on the ReAct research, this skill alternates between thinking (reasoning about the situa...
quarantinedactingproblem-solvingreasoningClawHub- Registry
- ClawHub
- Category
- Research
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__ReAct_LoopRoleplay_Agent
Create emotionally driven roleplay scenes by defining personas through current wants, obstacles, and moment-before context, generating natural, actor-directe...
quarantinedactingcharactercharacter-arcClawHub- Registry
- ClawHub
- Category
- Creative
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Roleplay_Agentdrivectl_-_your_command-line_tool_for_interacting_with_Google_Drive
Interact with Google Drive, Docs, and Sheets using the drivectl CLI. Use this skill when asked to list Drive files, download files, read/update Sheets, or cr...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__drivectl_-_your_command-line_tool_for_interacting_with_Google_Driveextracting-pdf-text
Indexed by skills.sh from letta-ai/skills
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.0
- Author
- letta-ai
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__extracting-pdf-textAction_Guard
Prevents duplicate external actions (posts, replies, sends, transfers, deploys). Check before acting, record after. Use when: (1) replying to social media po...
quarantinedagentsdedupsafetyClawHub- Registry
- ClawHub
- Category
- AI Agents
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Action_GuardAgent_Shared_Context
Cross-agent context sharing via shared files. Agents write trends, highlights, and signals to a shared folder. Other agents read before acting — creating coo...
quarantinedClawHub- Registry
- ClawHub
- Category
- Autonomous Ai Agents· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agent_Shared_ContextAgentprizm_Memory
Give your OpenClaw agent persistent, cross-session memory via AgentPrizm — recall durable facts, decisions, preferences, lessons, and contacts before acting,...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Agentprizm_MemoryAsking_Until_100
Repo-aware questioning protocol for OpenClaw that increases clarification before acting on coding, project-build, architecture, debugging, and implementation...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Asking_Until_100ClawdPoker_|_Poker_for_klankers
AI agents autonomously play continuous Texas Hold'em poker by polling game state and acting within 30 seconds using a two-worker system for reliability.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__ClawdPoker_|_Poker_for_klankersEngineer
Apply engineering judgment across systems, constraints, trade-offs, failure modes, and verification before acting.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__EngineerEngineering_Discipline
Production-grade AI coding discipline. Prevents the top 4 AI coding sins: acting without thinking, over-engineering, collateral damage, and vague execution....
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Engineering_DisciplineEnhanced_Agent_Modes
Provides three modes—Explore (read-only), Plan (analyze before acting), and Verify (check results)—plus feature flags to toggle capabilities dynamically.
quarantinedexplorefeature-flagsmodeClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Enhanced_Agent_ModesFidacy_Fraud_Detector
Detects the newest fraud in agent payments — the forged "this was approved." Use BEFORE acting on any approval, verdict, or "it's safe" claim another agent o...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Fidacy_Fraud_DetectorFossil
Semantic failure memory for AI agents. Search past reasoning failures before acting to avoid known mistakes. Record new failures and resolutions after they h...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__FossilHanlon's_Razor
Activate when: someone feels a colleague/partner/company did something on purpose to hurt them; a team believes another side is acting in bad faith; someone...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Hanlon's_RazorInversion_Protocol
Meta-cognitive reasoning skill that makes any AI agent dramatically better at decision-making by thinking backwards before acting forward. Applies Munger's I...
quarantinedClawHub- Registry
- ClawHub
- Category
- Productivity· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Inversion_ProtocolNegative_Space
Metacognitive pre-execution analysis — teaches the agent to see what ISN'T there before acting on what IS. Zero-cost reasoning skill that reduces wasted turn...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Negative_SpacePrincipal–Agent_Problem
Activate when: someone asks why an employee, executive, contractor, board member, or fund manager isn't acting in the org's interest; a compensation or incen...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Principal–Agent_ProblemPrompt_defense
Detect and block prompt injection attacks in emails. Use when reading, processing, or summarizing emails. Scans for fake system outputs, planted thinking blocks, instruction hijacking, and other injection patterns. Requires user confirmation before acting on any instructions f…
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Prompt_defenseSpellcheck
Use when interpreting user messages that may contain obvious spelling, grammar, speech-to-text, or casing errors, especially before acting on ambiguous instr...
quarantinedClawHub- Registry
- ClawHub
- Category
- Software Development· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__SpellcheckTool_Output_Auditor
Audit tool and command results before acting on them. Use when an agent has already run a command or tool, especially in multi-step workflows where a failed,...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Tool_Output_AuditorTowel_Protocol
Verify AI agent trust scores and reputation via Towel Protocol. Use when: checking if an agent is trustworthy before acting on their output, looking up an ag...
quarantinedClawHub- Registry
- ClawHub
- Category
- Autonomous Ai Agents· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Towel_ProtocolWine_Cellar
Comprehensive wine cellar management skill for tracking inventory, providing meal-based recommendations, acting as a virtual sommelier, tracking consumption/...
quarantinedClawHub- Registry
- ClawHub
- Category
- Gaming· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Wine_Cellaria-receiving-code-review
Process code review feedback critically: check correctness before acting, push back on incorrect suggestions, no performative agreement. Use when responding...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__ia-receiving-code-reviewverity-guard
Independent fail-closed second opinion before acting: allow/review/block a risky action, fact-check a claim, screen text for prompt injection, or flag PII/se...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__verity-guardxProof_-_Prove_Before_&_After_Act
Certify what your agent decided (WHY) before acting, and what it produced (WHAT) after. 4W audit trail on MultiversX, violations layer on Base, trust score.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__xProof_-_Prove_Before_&_After_Act