All authors
Claude Skills by tools-only
github.com/tools-only19,166 skills18 installs6,168 views
- 2498 Frama C Integration 3d5496e9Practical tips for using ACSL annotations with Frama-C verification tools.Votes: 0GitHub stars: 9
- 2498 Hashline Subsystem 921790b7The hashline edit subsystem provides cryptographically-validated file editing for agent operations. It implements a **read-side annotation + write-side validation** pattern that prevents stale edits and ensures edits are always applied to the correct line content.Votes: 0GitHub stars: 9
- 2498 Reasoning A05be33dHow to configure reasoning model settings from secondary providers.Votes: 0GitHub stars: 9
- 2498 Sdlc Layer Agent Candidates 272ca777**Source**: Full read of all 15 agents in `.claude/agents/` **Plan Context**: Layer 0 (SDLC-Agnostic), Layer 1 (Language-Specific), Layer 2 (Stack/Goal-Specific), ARL Meta-Layer **Generated**: 2026-02-23 ---Votes: 0GitHub stars: 9
- 2498 Soql Reference 4f3c7a7fQuick reference for SOQL queries used in sf-permissions.Votes: 0GitHub stars: 9
- 2498 Zerg Design E1242220Generate technical architecture and a task graph for parallel execution.Votes: 0GitHub stars: 9
- 2499 Comparison Techniques 00532933This document describes various techniques for comparing behavior between original and migrated repositories to detect differences, regressions, and semantic changes.Votes: 0GitHub stars: 9
- 2499 Contrib 40379351Contributions of benchmark results are welcome! See the [benchmark README](https://github.com/Aider-AI/aider/blob/main/benchmark/README.md) for information on running aider's code editing benchmarks. Submit results by opening a PR with edits to the [benchmark results data files](https://github.com/Aider-AI/aider/blob/main/aider/website/_data/).Votes: 0GitHub stars: 9
- 2499 Field Coverage Rules 62b0df0cThis guide documents field coverage validation rules for SOQL queries—ensuring that all fields accessed in Apex code are actually queried. This is a common source of runtime errors, especially in LLM-generated code. > **Source**: [LLM Mistakes in Apex & LWC - Salesforce Diaries](https://salesforcediaries.com/2026/01/16/llm-mistakes-in-apex-lwc-salesforce-code-generation-rules/) ---Votes: 0GitHub stars: 9
- 2499 File Upload Checklist 95e05da5> Derived from 30 real-world vulnerability cases (WooYun 2010-2016)Votes: 0GitHub stars: 9
- 2499 How To Use Abac3394Hey Claude—I just added the "claude-md-enhancer" skill. Can you help me create or improve my project's CLAUDE.md file?Votes: 0GitHub stars: 9
- 2499 Magic Keywords 518a7c2bMagic keywords provide shortcuts for model selection and task routing in the `/protocol` command.Votes: 0GitHub stars: 9
- 2499 P1 Gitlab Skill Remove Hardcoded Corporate Url 507f942c`validate_glfm.py` lines 152-153 hardcode `https://sourcery.assaabloy.net` as the default GitLab instance URL. `gitlab-ci-local-guide.md` line 51 also references this URL. This leaks a corporate internal URL into a public repository. Replace with a generic placeholder (e.g., `https://gitlab.example.com`) or make the URL a required argument with no default.Votes: 0GitHub stars: 9
- 2499 Sdlc Layer Candidates From Plugins 73a1efb9**Generated**: 2026-02-23 **Source**: Full read of all plugins under `plugins/` (CLAUDE.md, plugin.json, SKILL.md, agents, references, workflows) **Plan Context**: Layer 0 (SDLC-Agnostic), Layer 1 (Language-Specific), Layer 2 (Stack/Goal-Specific), ARL Meta-Layer ---Votes: 0GitHub stars: 9
- 2499 Zerg Document D0976676Generate documentation for a specific component, module, or command.Votes: 0GitHub stars: 9
- 250 Skill Architecture Design Be550fb4> **Version**: 3.0.2 > **Date**: 2026-02-04 > **Purpose**: Comprehensive system architecture analysis with diagrams, module relationships, and formal workflow specification > **Note (v3.0.2)**: Architecture refactored for clarity and determinism: > - SKILL.md: "WHAT & WHY" (静态契约) - ~4K tokens target > - WORKFLOW.md: "HOW & WHEN" (动态协议) - ~4K tokens target > - FSM formalization for 8-phase workflow > - 4-Gate Protocol per phase (ENTRY → THINKING → PLANNING → EXECUTING → REFLECTING → EXIT) ---Votes: 0GitHub stars: 9
- 250 Skill Architecture Design Caff0b9a> **Version**: 3.0.3 > **Date**: 2026-02-04 > **Purpose**: Comprehensive system architecture analysis with diagrams, module relationships, and formal workflow specification > **Note (v3.0.2)**: Architecture refactored for clarity and determinism: > - SKILL.md: "WHAT & WHY" (静态契约) - ~4K tokens target > - WORKFLOW.md: "HOW & WHEN" (动态协议) - ~4K tokens target > - FSM formalization for 8-phase workflow > - 4-Gate Protocol per phase (ENTRY → THINKING → PLANNING → EXECUTING → REFLECTING → EXIT) ---Votes: 0GitHub stars: 9
- 250 Skill Architecture Design E881dcaa> **Version**: 3.0.1 > **Date**: 2026-02-03 > **Purpose**: Comprehensive system architecture analysis with diagrams, module relationships, and formal workflow specification > **Note (v3.0.1)**: Architecture refactored for clarity and determinism: > - SKILL.md: "WHAT & WHY" (静态契约) - ~4K tokens target > - WORKFLOW.md: "HOW & WHEN" (动态协议) - ~4K tokens target > - FSM formalization for 8-phase workflow > - 4-Gate Protocol per phase (ENTRY → THINKING → PLANNING → EXECUTING → REFLECTING → EXIT) ---Votes: 0GitHub stars: 9
- 2500 Difference Patterns 003cae23This document catalogs common patterns of behavioral differences found when comparing original and migrated repositories, along with diagnostic approaches and remediation strategies.Votes: 0GitHub stars: 9
- 2500 Edit 92b57853Quantitative benchmark of basic LLM code editing skill.Votes: 0GitHub stars: 9
- 2500 Info Disclosure Checklist Aac2c34e> Derived from ~56 real-world vulnerability cases (WooYun 2010-2016)Votes: 0GitHub stars: 9
- 2500 P2 Configurable Token Thresholds For Pluginvalidatorpy 181209ad`plugin_validator.py` token complexity thresholds (4400 warn, 8800 error) are hardcoded constants. Allow per-project or per-plugin configuration via a config file (e.g., `.claude-plugin/validator.json` or a `[tool.plugin-validator]` section in `pyproject.toml`) so different projects can set their own limits.Votes: 0GitHub stars: 9
- 2500 Progress Hud 7ed6d284Real-time terminal UI components for displaying task progress, model usage, and token estimates.Votes: 0GitHub stars: 9
- 2500 Sdlc Layer Candidates Master 35ee3b41**Generated**: 2026-02-23 **Source**: Full read of plugins/, .claude/skills/, .claude/agents/ by 3 parallel sub-agents **Purpose**: Comprehensive review list for user to add specific items to the plan ---Votes: 0GitHub stars: 9
- 2500 Skill Php84 12f6b3dfExtension upgrade patterns for PHP 8.4. Rector rules, PHPStan configuration, and compatibility fixes.Votes: 0GitHub stars: 9
- 2500 Skill Php84 86f26dcfPHP 8.4 security considerations for TYPO3. New security features and potential vulnerabilities.Votes: 0GitHub stars: 9
- 2500 Skill Php84 C4b59d2dPHP 8.4 patterns for TYPO3 SEO services. Modern code patterns for meta tag handling and sitemap generation.Votes: 0GitHub stars: 9
- 2500 Skill Php84 F23bec31PHP 8.4 coding standards for TYPO3 extension conformance. Property hooks, visibility, and modern patterns.Votes: 0GitHub stars: 9
- 2500 Zerg Logs 74d90f7eStream, filter, and aggregate worker logs for debugging and monitoring.Votes: 0GitHub stars: 9
- 2501 01 Framework Validation Strategy 183331a6**Version:** 1.0 **Date:** 2025-12-29 **Owner:** @agent-qaVotes: 0GitHub stars: 9
- 2501 Exit Codes 0f6c6de3Exit codes are the primary communication mechanism between test scripts and git bisect. Understanding and using the correct exit codes is critical for successful automated bisection.Votes: 0GitHub stars: 9
- 2501 Notes Aebac3fcAll pricing information is the cost to run the benchmark at the time it was run. Providers change their pricing and sometimes introduce entirely novel pricing structures. Pricing is provided on a *best efforts* basis, and may not always be current or fully accurate.Votes: 0GitHub stars: 9
- 2501 P2 Conventional Commits Fix Changelog References To Nonexistent 72f73f16CHANGELOG references files that do not exist in the repository. Additionally, related skills referenced in the plugin do not exist. All dead references need to be either created or removed.Votes: 0GitHub stars: 9
- 2501 Path Traversal Checklist E420e992> Derived from ~30 real-world vulnerability cases (WooYun 2010-2016)Votes: 0GitHub stars: 9
- 2501 Sdlc Layer Candidates F780a1e8**Generated**: 2026-02-23 **Source**: Full read of all skills under `.claude/skills/` and their `references/` subdirectories **Plan Context**: Layer 0 (SDLC-Agnostic), Layer 1 (Language-Specific), Layer 2 (Stack/Goal-Specific), ARL Meta-Layer ---Votes: 0GitHub stars: 9
- 2501 Skill Content Blocks E5f5b2f4Contributing to Content Blocks extension. Patch workflow, testing, and documentation for the Content Blocks project.Votes: 0GitHub stars: 9
- 2501 Skill Content Blocks Ffe4ed74Rector patterns for Content Blocks migration. Automating TCA to Content Blocks conversion and code updates.Votes: 0GitHub stars: 9
- 2501 Zerg Plan 39a9e1dbCapture complete requirements for a feature through interactive discovery.Votes: 0GitHub stars: 9
- 2502 00 Quick Reference 4ff3f348```bash mkdir -p ~/.claude && cd ~/.claude git clone https://github.com/Everyone-Needs-A-Copilot/claude-copilot.git copilotVotes: 0GitHub stars: 9
- 2502 Edit Formats 0d3c5081Aider uses various "edit formats" to let LLMs edit source files.Votes: 0GitHub stars: 9
- 2502 Git Bisect Guide 24b6e3a4Git bisect is a powerful binary search tool for finding the commit that introduced a bug or regression. It efficiently narrows down the problematic commit by testing commits in a logarithmic manner.Votes: 0GitHub stars: 9
- 2502 P2 Llamafile Fix Huggingface Model Urls Wrong Org Name Fabricat Ca91f592SourceForge mirror is confirmed legitimate (auto-mirror with disclaimer). HuggingFace URLs need two fixes: (1) org name `Mozilla` must be changed to `mozilla-ai`, (2) model repo names need verification against actual `mozilla-ai` org repos — current names appear fabricated. The `llava-v1.5-7b-llamafile` URL works only via redirect.Votes: 0GitHub stars: 9
- 2502 Rce Checklist 60e3a56a> Derived from 11 real-world vulnerability cases (WooYun 2010-2016)Votes: 0GitHub stars: 9
- 2502 Sam Definition C220f102**SAM (Stateless Agent Methodology)** is a constraint-driven development framework that compensates for LLM limitations through architectural structure rather than behavioral instructions. It treats Claude as a **stateless computation engine**—not a knowledge worker—that receives complete context and returns verified artifacts.Votes: 0GitHub stars: 9
- 2502 Tdd Tech Lead Fbd6a78bYou are a team lead. Your responsibility is to assign work to the relevant team member. You don't write code, you don't review code. You work with the team to create a plan then assign development work to the `super-tdd-developer` and review work to the `code-reviewer`. When building a plan, you seek input from the `code-reviewer` so that design and test problems can be avoided rather than caught during code review. And you seek input from the `super-tdd-developer` to ensure the plan is TDD c...Votes: 0GitHub stars: 9
- 2502 Zerg Select Tool 66eb15f1Intelligent tool routing across MCP servers, native tools, and Task agent subtypes.Votes: 0GitHub stars: 9
- 2503 01 Conductoragent 03e38d94Master orchestrator for the 7-step Azure infrastructure workflow. Coordinates specialized agents (Requirements, Architect, Design, Bicep Plan, Bicep Code, Deploy) through the complete development cycle with mandatory human approval gates. Maintains context efficiency by delegating to subagents and preserves human-in-the-loop control at critical decision points.Votes: 0GitHub stars: 9
- 2503 01 Usage Guide F94a5e9c**How to actually use Claude Copilot to build software.** This guide shows real workflows, not feature lists. After setup, this is how you work. ---Votes: 0GitHub stars: 9
- 2503 Auto Accept Architect 4d97fe45See how a new command-line option is added to automatically accept edits proposed by the architect model, with implementation. Aider also updates the project's HISTORY file.Votes: 0GitHub stars: 9
- 2503 Language Manifest Schema 57f76c28The schema for language plugin manifests that compose with the development harness. Language plugin authors create a `references/language-manifest.md` file in their plugin's skill directory to declare specialist agents, quality gates, and project detection rules. ---Votes: 0GitHub stars: 9