patching AI Agent Skills

Browse 87 skills related to patching

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

pyvene-interventions

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

Causal InterventionpyveneActivation Patching+2

transformer-lens-interpretability

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Mechanistic InterpretabilityTransformerLensActivation Patching+1

fuzzing-obstacles

Techniques for patching code to overcome fuzzing obstacles. Use when checksums, global state, or other barriers block fuzzer progress.

1k-patching-native-modules

Patches native modules (expo-image, react-native, etc.) to fix native crashes or bugs.

obra/superpowers@dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

k8s-operations

kubectl operations for applying, patching, deleting, and executing commands on Kubernetes resources. Use when modifying resources, running commands in pods, or managing resource lifecycle.

dispatching-parallel-agents

Corvo007 Miosub Dispatching Parallel Agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

asyncredux-nonreentrant-mixin

Add the NonReentrant mixin to prevent an action from dispatching while already in progress. Covers preventing duplicate form submissions, avoiding race conditions, and protecting long-running operations.

asyncredux-navigation

Handle navigation through actions using NavigateAction. Covers setting up the navigator key, dispatching NavigateAction for push/pop/replace, and testing navigation in isolation.

asyncredux-abort-dispatch

Stops an AsyncRedux (Flutter) action from dispatching. Use only when the user mentions abortDispatch(), or explicitly asks to abort or prevent dispatch under certain conditions.

asyncredux-streams-timers

Manage Streams and Timers with AsyncRedux. Covers creating actions to start/stop streams, storing stream subscriptions in store props, dispatching actions from stream callbacks, and proper cleanup with disposeProps().

ring:dispatching-parallel-agents

Concurrent investigation pattern - dispatches multiple AI agents to investigate and fix independent problems simultaneously.

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

ansible-automation

Infrastructure automation and configuration management using Ansible playbooks, roles, and inventory. Use for deploying applications, patching, and managing servers.

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Dispatching Parallel Agents

Use multiple Claude agents to investigate and fix independent problems concurrently

fix-code-vulnerability

Guidance for identifying and fixing security vulnerabilities in code. This skill should be used when tasks involve fixing CWE-classified vulnerabilities, addressing security flaws, patching injection vulnerabilities, or responding to security-related test failures.

dispatching-parallel-agents

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple agents to investigate and fix independent problems concurrently

dispatching-parallel-agents

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

dispatching-parallel-agents

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

ascent-task-coordinator

Multi-agent coordination pattern for Claude Code acting as Project Manager. Use when orchestrating background agents for feature implementation, when Claude Code should delegate rather than implement, or when running parallel investigation/implementation tasks. Provides task-list.json structure, progress tracking format, and agent role definitions. Keeps Claude Code in "coordinator mode" - dispatching work to specialized agents rather than writing code directly.

multi-agent-vcs

This skill should be used when dispatching subagents for parallel development, coordinating multi-branch implementations, or when "parallel agents", "orchestrator commits", "subagent filesystem only", "multi-agent git", or "prevent stack corruption" are mentioned. Prevents stack corruption through orchestrator-only git policy.

generate-signature-for-patch

Generate and validate unique byte signatures for instructions that need to be runtime-patched using IDA Pro MCP. Use this skill when you need a signature to locate a specific instruction for patching (e.g., force/skip a branch, NOP a call, change an immediate operand). Triggers: patch signature, signature for patch, patch instruction signature, nop signature, jump patch signature, skip branch signature, force branch signature

vvvv-patching

Explains vvvv gamma visual programming patterns — dataflow, node connections, regions (ForEach/If/Switch/Repeat/Accumulator), channels for reactive data flow, event handling (Bang/Toggle/FrameDelay/Changed), patch organization, and common anti-patterns (circular dependencies, polling vs reacting, ignoring Nil). Use when the user asks about patching best practices, dataflow patterns, event handling, or how to structure visual programs.

dispatching-parallel-agents

Concurrent investigation of independent failures. Use when multiple unrelated issues need parallel resolution.

parallel-agentsfan-outdiagnosis+2

dispatching-parallel-agents

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

dependency-vulnerability-triage

patricio0312rev

Turns npm audit/Snyk results into prioritized patch plans with severity assessment, safe upgrade paths, breaking change analysis, and rollback strategies. Use for "dependency security", "vulnerability patching", "npm audit", or "security updates".

dispatching-parallel-agents

Dispatches one subagent per independent domain to parallelize investigation/fixes. Use when you have 2+ unrelated failures (e.g., separate failing test files, subsystems, bugs) with no shared state or ordering dependencies.

Symfony

Comprehensive skill for all Symfony framework components. Covers HTTP handling, dependency injection, forms, validation, caching, messaging, console commands, event dispatching, workflows, serialization, testing, filesystem operations, configuration, and utility components. Use when working with any Symfony component.

symfony-messenger

Handle synchronous and asynchronous message dispatching and queuing. Implement message buses, handlers, transports (AMQP, Doctrine, Redis, Beanstalkd), middleware, envelopes, and stamps for building event-driven architectures.

symfony-messenger

Handle synchronous and asynchronous message dispatching and queuing. Implement message buses, handlers, transports (AMQP, Doctrine, Redis, Beanstalkd), middleware, envelopes, and stamps for building event-driven architectures.

aws-rds

Manage Amazon RDS for fully managed relational databases. Provision MySQL, PostgreSQL, and Aurora instances with automated backups and patching. Configure read replicas for scaling, snapshots for recovery, and Aurora Serverless for variable workloads.

git

Execution-layer skill for git inspection and safe patching

diff-apply

Apply generated .diff or .patch files to the ace_engine repository (TypeScript/C++ hybrid codebase) with intelligent conflict resolution. Use this when applying patches to ace_engine code to resolve merge conflicts while preserving original logic, or to validate changes by compiling after patching. The target repository path is ROOT/code/foundation/arkui/ace_engine in a repo-manifest project.

attribution-patching

Gradient-based approximation to activation patching for scalable circuit analysis. Use when activation patching is too slow or when analyzing many components simultaneously.

type-ignore:fix

Fixes type ignores in a file, directory, or codebase by discovering ignores and dispatching parallel fixer agents. Use when cleaning up type ignores across multiple files, eliminating ignores before a release, or batch-fixing type errors.

activation-patching

Causal intervention via activation patching to identify important model components. Use when determining which layers, heads, or positions are causally responsible for model behavior.

ccpm-debugging

Systematic debugging with defense-in-depth approach (symptoms → immediate cause → root cause → systemic issues → prevention). Auto-activates when user mentions "error", "failing", "broken", "debug", "bug", "issue" or when /ccpm:verify runs. Uses Observe → Hypothesize → Test → Confirm → Fix → Verify → Document workflow. Updates Linear with findings and automatically logs blockers that require external fixes. Traces root causes instead of patching symptoms. Integrates with ccpm-code-review to verify fixes pass all gates before marking complete. Suggests binary search for intermittent issues and five-whys analysis for complex problems.

GPUI Patterns

Common GPUI patterns including component composition, state management strategies, event handling, and action dispatching. Use when user needs guidance on GPUI patterns, component design, or state management approaches.

cw-plan

Transform a specification into a task graph with dependencies. Use after cw-spec to break a spec into executable tasks with proper sequencing before dispatching with cw-dispatch.

dispatching-parallel-agents

agent-skills-hub

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

dispatching-parallel-agents

Sentry01 Copilot Cli Harness Dispatching Parallel Agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

dispatching-parallel-agents

Use when facing 2+ independent experiments or tasks that can be worked on without shared state or sequential dependencies

Dispatching Parallel Agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

None

Vulnerability remediation SLAs define mandatory timeframes for patching or mitigating identified vulnerabilities based on severity, asset criticality, and exploit availability. Effective SLA programs

vulnerability-managementcvesla+3

Join Clawiskill today. The decentralized skill network for AI Agents.

Explore Network