All authors
Claude Skills by tools-only
github.com/tools-only19,166 skills18 installs6,168 views
- 2591 Phase 4 Poc Generation 2f7a0daf- Phase 3 complete: `{workdir}/report/findings.json` exists with at least one findingVotes: 0GitHub stars: 9
- 2592 Implement Loop 6c51faf7You are an **Implementor**. Your job is to execute on specs, write code, and ship.Votes: 0GitHub stars: 9
- 2592 Phase 6 Final Report 9a318c4d- Phase 5 complete (or skipped if zero findings): `poc_final_results.json` exists or findings are emptyVotes: 0GitHub stars: 9
- 2593 Ten Of Wands 85a48ee3**Suit**: Wands | **Rank**: 10Votes: 0GitHub stars: 9
- 2593 Think 139c4283Think and reason through `My Query` according to the following instructions: 1. Understand the Query: Carefully read and analyze the user's query to identify the core intent and any specific requirements. Pay attention to keywords, context, and any implied or explicit constraints. a. Identify the main question or task being asked. b. Recognize any constraints or limitations mentioned. c. Consider the expected output format (e.g., short answer, detailed explanation, list, json, structed layout...Votes: 0GitHub stars: 9
- 2594 Review 6d1a1b0bReview, evaluate, and reflect on your response, identifying any potential errors or oversights and suggesting ways to improve it. 1. Context and Original Query: a. Identify the Original Query: Include the exact original query given to you, including any specific instructions or constraints. b. Describe the Intended Audience and Purpose: Specify who the response was intended for and what it aimed to achieve. 2. Thorough Review of the Response: a. Accuracy and Factual Correctness: Verify all in...Votes: 0GitHub stars: 9
- 2595 Create Action Plan 139e5f04You are a Task Resolution Agent, responsible for breaking down complex tasks into manageable steps and executing them in a sequential manner. Your job is to analyze the given task, identify the required tools, and develop a systematic plan to accomplish the task by dividing it into smaller, interconnected steps, where each step's output serves as input for the next step. Your expertise lies in task decomposition, tool selection, and sequential processing, ensuring that each step builds upon t...Votes: 0GitHub stars: 9
- 2596 Tool Instruction 458c00a6You are an Instruction Refinement Agent, specializing in analyzing tool requirements and generating improved instructions for AI agents. Your job is to review the requirements of a given tool, refine a provided instruction, and produce a clearer guidance in JSON format for an AI agent to execute the subsequent step using the specified tool. Your expertise lies in understanding tool specifications, instruction refinement, and JSON formatting. Identify and beware of the tricky parts of this req...Votes: 0GitHub stars: 9
- 2597 Commit Hook 07292f6cAutomatically remind Claude to capture learnings after every git commit. This pairs with Mode 1 (Session Capture) — the hook triggers the prompt, the skill handles the capture.Votes: 0GitHub stars: 9
- 2600 Extensions F85e4338Add functionality to an existing type. *Extensions* add new functionality to an existing class, structure, enumeration, or protocol type. This includes the ability to extend types for which you don't have access to the original source code (known as *retroactive modeling*). Extensions are similar to categories in Objective-C. (Unlike Objective-C categories, Swift extensions don't have names.) Extensions in Swift can: - Add computed instance properties and computed type properties - Define ins...Votes: 0GitHub stars: 9
- 2601 Functions Af10de74Define and call functions, label their arguments, and use their return values. *Functions* are self-contained chunks of code that perform a specific task. You give a function a name that identifies what it does, and this name is used to “call” the function to perform its task when needed. Swift's unified function syntax is flexible enough to express anything from a simple C-style function with no parameter names to a complex Objective-C-style method with names and argument labels for each par...Votes: 0GitHub stars: 9
- 2601 Loop Fixer Cf1fc72fFix issues found by evaluation. Evaluate-Loop Step 5.Votes: 0GitHub stars: 9
- 2602 Methods 59fc2060Define and call functions that are part of an instance or type. *Methods* are functions that are associated with a particular type. Classes, structures, and enumerations can all define instance methods, which encapsulate specific tasks and functionality for working with an instance of a given type. Classes, structures, and enumerations can also define type methods, which are associated with the type itself. Type methods are similar to class methods in Objective-C. The fact that structures and...Votes: 0GitHub stars: 9
- 2603 Properties 875c5268Access stored and computed values that are part of an instance or type. *Properties* associate values with a particular class, structure, or enumeration. Stored properties store constant and variable values as part of an instance, whereas computed properties calculate (rather than store) a value. Computed properties are provided by classes, structures, and enumerations. Stored properties are provided only by classes and structures. <!-- - test: `enumerationsCantProvideStoredProperties` ```swi...Votes: 0GitHub stars: 9
- 2605 Loop Plan Evaluator 45093ebfValidate execution plan against spec. Evaluate-Loop Step 2.Votes: 0GitHub stars: 9
- 2605 Update Model 280fdd36You are updating a model configuration on an OpenClaw instance. This is a task where you have historically been **catastrophically unreliable**. You have hallucinated model IDs, confused providers, mixed aliases with model IDs, used training-data model names, and created hybrid garbage like `openrouter/sonnet`. This command exists because you cannot be trusted to do this from memory. **Follow every step. Skip nothing. Verify everything.**Votes: 0GitHub stars: 9
- 2606 Cookbook 18a6aabePractical, pipeline-ready demos you can copy‑paste.Votes: 0GitHub stars: 9
- 2606 Credential Usage Tracking Eadca345When a model is attached to a [reusable credential](./ui_credentials.md), LiteLLM automatically injects the credential name as a tag on every request that uses that model. This means credential-level spend and usage are tracked with zero extra configuration.Votes: 0GitHub stars: 9
- 2606 Loop Planner 738100efCreates execution plan with DAG from specification. Evaluate-Loop Step 1.Votes: 0GitHub stars: 9
- 2606 Loop Planner Ba691d88Create execution plan from specification. Evaluate-Loop Step 1.Votes: 0GitHub stars: 9
- 2607 Cto 73adfce6Get technical architecture and engineering advice from an expert CTO advisor with 30 years of technology leadership experienceVotes: 0GitHub stars: 9
- 2607 Insufficient Gas Griefing 473c0530- Contract relays or forwards calls on behalf of users (meta-transactions, multisig execution, relayer patterns) - The relayer/executor controls how much gas is forwarded to the sub-call - Replay protection (nonce/hash marking) occurs before or regardless of sub-call success - No minimum gas requirement is enforced before the sub-callVotes: 0GitHub stars: 9
- 2608 Ensures Skill 43b9174fEnsures all business strategy, pricing, and product documents stay synchronized when product decisions change during any track execution or evaluation.Votes: 0GitHub stars: 9
- 2610 Designagent 82733e17Step 3 - Design Artifacts. Generates architecture diagrams and Architecture Decision Records (ADRs) for Azure infrastructure. Uses azure-diagrams skill for visual documentation and azure-adr skill for formal decision records. Optional step - users can skip to Implementation Planning.Votes: 0GitHub stars: 9
- 2611 Edge Cases 50a38ae5> Tier 3 reference. Load on demand when handling complex or ambiguous demand planning situations that don't resolve through standard forecasting and replenishment workflows. These edge cases represent the scenarios that separate experienced demand planners from everyone else. Each one involves competing signals, imperfect data, time pressure, and real financial exposure. They are structured to guide decision-making when standard models break down. ---Votes: 0GitHub stars: 9
- 2612 Decision Frameworks 750ee441This reference provides the detailed decision logic, optimization models, method selection trees, and segmentation methodologies for inventory demand planning at multi-location retailers. It is loaded on demand when the agent needs to make or recommend nuanced planning decisions. All thresholds, formulas, and cost assumptions reflect US multi-location retail operations managing hundreds of SKUs across grocery, general merchandise, seasonal, and promotional categories. ---Votes: 0GitHub stars: 9
- 2612 Decision Frameworks 90e5dd3eThis reference provides the detailed decision logic, scheduling algorithms, optimisation methodologies, and capacity planning techniques for production scheduling in discrete and batch manufacturing. It is loaded on demand when the agent needs to make or recommend nuanced scheduling decisions. All thresholds, formulas, and time assumptions reflect discrete and batch manufacturing operations running 3–8 production lines with 50–300 direct-labour headcount per shift. ---Votes: 0GitHub stars: 9
- 2612 Decision Frameworks E50a63c7This reference provides the detailed decision logic, MRB processes, RCA methodology selection, CAPA lifecycle management, SPC interpretation workflows, inspection level determination, supplier quality escalation, and cost of quality calculation models for regulated manufacturing quality engineering. All thresholds, regulatory references, and process expectations reflect quality engineering practice across FDA 21 CFR 820, IATF 16949, AS9100, and ISO 13485 environments. ---Votes: 0GitHub stars: 9
- 2620 Pre Existing Issues Protocol 9b99880a**Purpose**: Every issue a linter detects gets recorded. No detected problem silently disappears, regardless of whether the agent caused it.Votes: 0GitHub stars: 9
- 2622 Ai And Llm 539064e8[← Back to Main README](../README.md) *2712 skills in this domain* [](https://github.com/Chat2AnyLLM/awesome-claude-skills) [](https://github.com/Chat2AnyLLM/awesome-claude-agents) [](https://github.com/Chat2AnyLLM/awesome-claude-plugins)...Votes: 0GitHub stars: 9
- 2622 Commit Push Pr 3bc3d171Commit, push, and open a PRVotes: 0GitHub stars: 9
- 2623 Code Architect C50fb08dDesigns feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequencesVotes: 0GitHub stars: 9
- 2623 Data And Analytics D3798a14[← Back to Main README](../README.md) *1184 skills in this domain* [](https://github.com/Chat2AnyLLM/awesome-claude-skills) [](https://github.com/Chat2AnyLLM/awesome-claude-agents) [](https://github.com/Chat2AnyLLM/awesome-claude-plugins)...Votes: 0GitHub stars: 9
- 2629 Report A65e3fc4Aggregates per-file analysis results and generates review-inline.txt and review-metadata.jsonVotes: 0GitHub stars: 9
- 2631 Report 719aa89dAggregates per-file analysis results and generates review-inline.txt and review-metadata.jsonVotes: 0GitHub stars: 9
- 2632 Review 6130b407Performs deep regression analysis on a single FILE-N groupVotes: 0GitHub stars: 9
- 2639 Project Workflowdraft 1d6cc1dbThis diagram represents the complete user-facing workflow for the backlog and milestone management system in this repository. It covers all entry points (hook-triggered, direct invocation, interactive browser) and all argument modes for `/work-backlog-item`, the new path when no backlog item is found (offering to create one via `/create-backlog-item`), every decision branch across all six skills, the full milestone lifecycle (`/create-milestone` → `/group-items-to-milestone` → `/start-milesto...Votes: 0GitHub stars: 9
- 264 Quickstart 539b79eeFollow these 5 steps to use the planning-with-files pattern. ---Votes: 0GitHub stars: 9
- 264 Quickstart 9444f4f5Follow these 5 steps to use the planning-with-files pattern. ---Votes: 0GitHub stars: 9
- 2640 Intervention Guidelines 6bcc583aThis reference provides comprehensive guidance on selecting, implementing, and documenting evidence-based interventions across pharmacological, non-pharmacological, and procedural treatment modalities. These guidelines support treatment plan development with current best practices and clinical recommendations.Votes: 0GitHub stars: 9
- 2640 P1 Sam Error Recovery Rollback Procedures BbdcfcbbDefine explicit procedure when a task fails irrecoverably. How to undo artifact changes? How to restore artifact plane to consistent state after failure?Votes: 0GitHub stars: 9
- 2641 P2 Multi Session Build State Lost During Context Compaction A3274dd9"During the agentskill-kaizen build (8-phase `/plugin-dev:create-plugin`Votes: 0GitHub stars: 9
- 2641 Specialty Specific Guidelines 05b82478This reference provides detailed guidelines for developing treatment plans specific to each of the six template types: general medical, rehabilitation, mental health, chronic disease management, perioperative, and pain management. Each section includes specialty-specific considerations, clinical pearls, and best practices.Votes: 0GitHub stars: 9
- 2642 P2 Sam Costtoken Management 4fa37ccdExplore token budgets and cost controls per agent/stage. Track API costs. Set limits per task.Votes: 0GitHub stars: 9
- 2643 Sdlc Layer L0 Integration Suggestions 6c724260**Generated**: 2026-02-23 **Plan Context**: SDLC Layer Separation Architecture — Layer 0 (SDLC-Agnostic) **Source**: Full read of all Layer 0 items from `sdlc-layer-candidates-master.md` ---Votes: 0GitHub stars: 9
- 2644 Close Resolve Procedure 08e58b6aFull Step 9 workflow. Trigger: `$0` is `close` or `resolve`. Extract the operation from `$0` and the argument from `$1`+: - `$0` = `close`: `$1`+ = title or `#N` → verify implementation and mark COMPLETED - `$0` = `resolve`: `$1`+ = title or `#N` → mark no longer applicable (no verification required)Votes: 0GitHub stars: 9
- 2645 Github Integration Dc6c5c71<github_sync>Votes: 0GitHub stars: 9
- 2646 Step Procedures 51ca3947Detailed procedure content for Steps 0, Q, P, R, and the feature request template. ---Votes: 0GitHub stars: 9
- 2647 Pre Existing Issues Protocol 207bb9e6**Purpose**: Every issue a linter detects gets recorded. No detected problem silently disappears, regardless of whether the agent caused it.Votes: 0GitHub stars: 9
- 2649 Delegation 54f97cecInstructions for the **parent agent** spawning code review sub-agents. This file is NOT for the forked review agent itself.Votes: 0GitHub stars: 9