agentsclimarketplace

Engineering

97,255 rows, by stacks then stars

  • Refactor

    arbiterForge/codeArbiter/core/surface/skills/refactor Skill

    154★ repo

    When you can't trust yourself with your code base, trust Arbiter.

  • Release

    arbiterForge/codeArbiter/core/surface/skills/release Skill

    154★ repo

    When you can't trust yourself with your code base, trust Arbiter.

  • Secret handling

    arbiterForge/codeArbiter/core/surface/skills/secret-handling Skill

    154★ repo

    When you can't trust yourself with your code base, trust Arbiter.

  • Security architecture

    arbiterForge/codeArbiter/core/surface/skills/security-architecture Skill

    154★ repo

    Optional, opt-in STRIDE threat pass for a sensitive feature — invoked deliberately via /threat-model, never forced on ordinary changes. Walks the change's attack surface and security boundaries (governed by {{PROJECT_DIR}}/.codearbiter/security-controls.md), surfaces threats and unmitigated gaps, and MAY dispatch security-reviewer or auth-crypto-reviewer. Not a routine gate; it can hard-STOP only on a genuinely critical unmitigated threat it surfaces.

    The same file is in 2 other repositories

  • Subagent driven development

    arbiterForge/codeArbiter/core/surface/skills/subagent-driven-development Skill

    154★ repo

    When you can't trust yourself with your code base, trust Arbiter.

  • Tdd

    arbiterForge/codeArbiter/core/surface/skills/tdd Skill

    154★ repo

    When you can't trust yourself with your code base, trust Arbiter.

  • Using git worktrees

    arbiterForge/codeArbiter/core/surface/skills/using-git-worktrees Skill

    154★ repo

    When you can't trust yourself with your code base, trust Arbiter.

  • Debug

    arbiterForge/codeArbiter/plugins/ca-codex/routines/debug Skill

    154★ repo

    Investigate-then-decide root-cause analysis for a defect whose cause is unknown (distinct from /fix, which assumes a known bug). Five gated phases: capture, hypothesize, gather, decide, hand off. Investigation only, no code changes; exits to /fix, /adr, or a no-action close.

  • Dispatching parallel agents

    arbiterForge/codeArbiter/plugins/ca-codex/routines/dispatching-parallel-agents Skill

    154★ repo

    The parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an agent per unit — subagent-driven-development, /sprint, parallel /review. It owns the dispatch/collect/funnel discipline: bound concurrency, isolate units, collect every result, dedupe overlap, and funnel through finding-triage then checkpoint-aggregator. Raw agent output is never consumed before the funnel runs; an agent that errors drops its unit without corrupting the batch.

  • Executing plans

    arbiterForge/codeArbiter/plugins/ca-codex/routines/executing-plans Skill

    154★ repo

    The checkpoint coordinator for /feature. Routed to by /feature once a writing-plans plan exists. Groups tasks into batches, delegates each batch to subagent-driven-development (fresh author agent per task, full review chain, fresh verification), then stops for a human checkpoint before the next batch. The checkpointed counterpart to /sprint's autonomous run.

  • Refactor

    arbiterForge/codeArbiter/plugins/ca-codex/routines/refactor Skill

    154★ repo

    The behavior-preserving restructure gate. Routed to by /refactor for a rename, extract, inline, move, dedup, or internal-implementation swap. Six gated phases prove behavioral parity through unmodified pre-existing tests; any diff that classifies as `feat` is not a refactor and is routed to tdd. A modified pre-existing test is rejected as evidence — it is a behavior change in disguise.

  • Release

    arbiterForge/codeArbiter/plugins/ca-codex/routines/release Skill

    154★ repo

    The single permitted path to a version tag, for any of the four independently-versioned plugins. Routed to when the user invokes /release on a non-default branch with a green suite. Takes the target plugin as its one argument (default ca), derives the SemVer bump from Conventional-Commits history since that plugin's last tag, rolls the commits into that plugin's CHANGELOG, writes an annotated tag in that plugin's namespace, and on authorization publishes it as a GitHub Release with the changelog section as its notes. A release commit, if needed, routes through commit-gate; the tag and Release are never published without explicit authorization.

  • Secret handling

    arbiterForge/codeArbiter/plugins/ca-codex/routines/secret-handling Skill

    154★ repo

    The secret-source gate. Routed to when changed code reads, writes, or passes a secret — API key, token, password, connection string, signing key, certificate, or any value that grants access. Validates that every secret comes from the approved store and never lands in source, log, test fixture, error response, image, or LLM prompt. The auth-crypto-reviewer agent is dispatched as the reviewer.

  • Security architecture

    arbiterForge/codeArbiter/plugins/ca-codex/routines/security-architecture Skill

    154★ repo

    Optional, opt-in STRIDE threat pass for a sensitive feature — invoked deliberately via /threat-model, never forced on ordinary changes. Walks the change's attack surface and security boundaries (governed by <project-root>/.codearbiter/security-controls.md), surfaces threats and unmitigated gaps, and MAY dispatch security-reviewer or auth-crypto-reviewer. Not a routine gate; it can hard-STOP only on a genuinely critical unmitigated threat it surfaces.

  • Subagent driven development

    arbiterForge/codeArbiter/plugins/ca-codex/routines/subagent-driven-development Skill

    154★ repo

    The implementation engine. Routed to by /sprint (full plan, autonomous) and by executing-plans (scoped batch, checkpoint-gated). One fresh subagent per task — test-first via tdd — followed by spec-compliance review, quality review, and fresh-run verification. No single context accumulates drift, and nothing is accepted on a subagent's word.

  • Tdd

    arbiterForge/codeArbiter/plugins/ca-codex/routines/tdd Skill

    154★ repo

    The test-first gate. Routed to by /feature (after the spec is approved), /fix, and /refactor before any implementation code is written. Six gated phases — obligation scan, red, green, obligation verify, coverage, lint. No feature code exists before Phase 1 clears; nothing reaches commit-gate until all six are green.

  • Using git worktrees

    arbiterForge/codeArbiter/plugins/ca-codex/routines/using-git-worktrees Skill

    154★ repo

    OPTIONAL per-task isolation for autonomous parallel work. Routed to only on explicit opt-in by subagent-driven-development or dispatching-parallel-agents, so parallel units mutate files without colliding. Stands up one worktree per unit, works it in isolation, then integrates each unit back onto the caller's working branch for the caller's single commit-gate + finishing-a-development-branch exit. Never on the default path; it does not bypass a gate or finish per unit.

  • Ca debug

    arbiterForge/codeArbiter/plugins/ca-codex/skills/ca-debug Skill

    154★ repo

    Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to $ca-fix, $ca-adr, or a no-action close.

    The same file is in 2 other repositories

  • Ca fix

    arbiterForge/codeArbiter/plugins/ca-codex/skills/ca-fix Skill

    154★ repo

    Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

  • Ca init

    arbiterForge/codeArbiter/plugins/ca-codex/skills/ca-init Skill

    154★ repo

    Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

  • Ca refactor

    arbiterForge/codeArbiter/plugins/ca-codex/skills/ca-refactor Skill

    154★ repo

    Restructure code with behavioral parity proven through unmodified pre-existing tests, then refactor. No behavior change.

  • Ca release

    arbiterForge/codeArbiter/plugins/ca-codex/skills/ca-release Skill

    154★ repo

    Cut a release the only sanctioned way — SemVer bump from the commit log, a CHANGELOG section, an annotated tag. The only path to a version tag.

  • Ca threat model

    arbiterForge/codeArbiter/plugins/ca-codex/skills/ca-threat-model Skill

    154★ repo

    Opt-in lightweight STRIDE pass for a sensitive feature before implementation. Not a routine gate — invoke it when a change warrants security thought.

  • Debug

    arbiterForge/codeArbiter/plugins/ca-pi/routines/debug Skill

    154★ repo

    Investigate-then-decide root-cause analysis for a defect whose cause is unknown (distinct from /fix, which assumes a known bug). Five gated phases: capture, hypothesize, gather, decide, hand off. Investigation only, no code changes; exits to /fix, /adr, or a no-action close.

  • Dispatching parallel agents

    arbiterForge/codeArbiter/plugins/ca-pi/routines/dispatching-parallel-agents Skill

    154★ repo

    The parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an agent per unit — subagent-driven-development, /sprint, parallel /review. It owns the dispatch/collect/funnel discipline: bound concurrency, isolate units, collect every result, dedupe overlap, and funnel through finding-triage then checkpoint-aggregator. Raw agent output is never consumed before the funnel runs; an agent that errors drops its unit without corrupting the batch.

  • Executing plans

    arbiterForge/codeArbiter/plugins/ca-pi/routines/executing-plans Skill

    154★ repo

    The checkpoint coordinator for /feature. Routed to by /feature once a writing-plans plan exists. Groups tasks into batches, delegates each batch to subagent-driven-development (fresh author agent per task, full review chain, fresh verification), then stops for a human checkpoint before the next batch. The checkpointed counterpart to /sprint's autonomous run.

  • Refactor

    arbiterForge/codeArbiter/plugins/ca-pi/routines/refactor Skill

    154★ repo

    The behavior-preserving restructure gate. Routed to by /refactor for a rename, extract, inline, move, dedup, or internal-implementation swap. Six gated phases prove behavioral parity through unmodified pre-existing tests; any diff that classifies as `feat` is not a refactor and is routed to tdd. A modified pre-existing test is rejected as evidence — it is a behavior change in disguise.

  • Release

    arbiterForge/codeArbiter/plugins/ca-pi/routines/release Skill

    154★ repo

    The single permitted path to a version tag, for any target declared in the project's .codearbiter/release-targets.md. Routed to when the user invokes /release on a non-default branch with a green suite. Takes the declared target as its one argument, derives the SemVer bump from Conventional-Commits history since that target's last tag, rolls the commits into that target's CHANGELOG, writes an annotated tag in that target's namespace, and on authorization publishes it as a GitHub Release with the changelog section as its notes. A release commit, if needed, routes through commit-gate; the tag and Release are never published without explicit authorization.

  • Secret handling

    arbiterForge/codeArbiter/plugins/ca-pi/routines/secret-handling Skill

    154★ repo

    The secret-source gate. Routed to when changed code reads, writes, or passes a secret — API key, token, password, connection string, signing key, certificate, or any value that grants access. Validates that every secret comes from the approved store and never lands in source, log, test fixture, error response, image, or LLM prompt. The auth-crypto-reviewer agent is dispatched as the reviewer.

  • Security architecture

    arbiterForge/codeArbiter/plugins/ca-pi/routines/security-architecture Skill

    154★ repo

    Optional, opt-in STRIDE threat pass for a sensitive feature — invoked deliberately via /threat-model, never forced on ordinary changes. Walks the change's attack surface and security boundaries (governed by <project-root>/.codearbiter/security-controls.md), surfaces threats and unmitigated gaps, and MAY dispatch security-reviewer or auth-crypto-reviewer. Not a routine gate; it can hard-STOP only on a genuinely critical unmitigated threat it surfaces.

  • Subagent driven development

    arbiterForge/codeArbiter/plugins/ca-pi/routines/subagent-driven-development Skill

    154★ repo

    The implementation engine. Routed to by /sprint (full plan, autonomous) and by executing-plans (scoped batch, checkpoint-gated). One fresh subagent per task — test-first via tdd — followed by spec-compliance review, quality review, and fresh-run verification. No single context accumulates drift, and nothing is accepted on a subagent's word.

  • Tdd

    arbiterForge/codeArbiter/plugins/ca-pi/routines/tdd Skill

    154★ repo

    The test-first gate. Routed to by /feature (after the spec is approved), /fix, and /refactor before any implementation code is written. Six gated phases — obligation scan, red, green, obligation verify, coverage, lint. No feature code exists before Phase 1 clears; nothing reaches commit-gate until all six are green.

  • Using git worktrees

    arbiterForge/codeArbiter/plugins/ca-pi/routines/using-git-worktrees Skill

    154★ repo

    OPTIONAL per-task isolation for autonomous parallel work. Routed to only on explicit opt-in by subagent-driven-development or dispatching-parallel-agents, so parallel units mutate files without colliding. Stands up one worktree per unit, works it in isolation, then integrates each unit back onto the caller's working branch for the caller's single commit-gate + finishing-a-development-branch exit. Never on the default path; it does not bypass a gate or finish per unit.

  • Ca debug

    arbiterForge/codeArbiter/plugins/ca-pi/skills/ca-debug Skill

    154★ repo

    Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to /ca-fix, /ca-adr, or a no-action close.

  • Ca doctor

    arbiterForge/codeArbiter/plugins/ca-pi/skills/ca-doctor Skill

    154★ repo

    Verify the active host install, package, command ownership, enforcement, wrapper self-test, and active-dispatch coverage gap. Read-only.

  • Ca fix

    arbiterForge/codeArbiter/plugins/ca-pi/skills/ca-fix Skill

    154★ repo

    Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

  • Ca init

    arbiterForge/codeArbiter/plugins/ca-pi/skills/ca-init Skill

    154★ repo

    Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

  • Ca refactor

    arbiterForge/codeArbiter/plugins/ca-pi/skills/ca-refactor Skill

    154★ repo

    Restructure code with behavioral parity proven through unmodified pre-existing tests, then refactor. No behavior change.

  • Ca release

    arbiterForge/codeArbiter/plugins/ca-pi/skills/ca-release Skill

    154★ repo

    Cut a release the only sanctioned way — SemVer bump from the commit log, a CHANGELOG section, an annotated tag. The only path to a version tag.

  • Ca threat model

    arbiterForge/codeArbiter/plugins/ca-pi/skills/ca-threat-model Skill

    154★ repo

    Opt-in lightweight STRIDE pass for a sensitive feature before implementation. Not a routine gate — invoke it when a change warrants security thought.

  • Sandbox claude inside

    arbiterForge/codeArbiter/plugins/ca-sandbox/skills/sandbox-claude-inside Skill

    154★ repo

    Run Claude Code INSIDE a ca-sandbox box (`--with-claude`). Routed to when the user wants an agent loop running against an isolated, ephemeral sandbox rather than the host. Authenticates via an env-injected CLAUDE_CODE_OAUTH_TOKEN with no host bind of ~/.claude; the image pins the CLI and disables the autoupdater; HOME is backed by a named volume so the .claude state persists across restart. Five gated phases — posture, image, token, run, teardown. The hard default is offline or Anthropic-domains-only egress, and the token volume is NEVER co-mounted with an untrusted-code run; both are enforced, not advised.

  • Debug

    arbiterForge/codeArbiter/plugins/ca/skills/debug Skill

    154★ repo

    Investigate-then-decide root-cause analysis for a defect whose cause is unknown (distinct from /fix, which assumes a known bug). Five gated phases: capture, hypothesize, gather, decide, hand off. Investigation only, no code changes; exits to /fix, /adr, or a no-action close.

  • Dispatching parallel agents

    arbiterForge/codeArbiter/plugins/ca/skills/dispatching-parallel-agents Skill

    154★ repo

    The parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an agent per unit — subagent-driven-development, /sprint, parallel /review. It owns the dispatch/collect/funnel discipline: bound concurrency, isolate units, collect every result, dedupe overlap, and funnel through finding-triage then checkpoint-aggregator. Raw agent output is never consumed before the funnel runs; an agent that errors drops its unit without corrupting the batch.

  • Executing plans

    arbiterForge/codeArbiter/plugins/ca/skills/executing-plans Skill

    154★ repo

    The checkpoint coordinator for /feature. Routed to by /feature once a writing-plans plan exists. Groups tasks into batches, delegates each batch to subagent-driven-development (fresh author agent per task, full review chain, fresh verification), then stops for a human checkpoint before the next batch. The checkpointed counterpart to /sprint's autonomous run.

  • Refactor

    arbiterForge/codeArbiter/plugins/ca/skills/refactor Skill

    154★ repo

    The behavior-preserving restructure gate. Routed to by /refactor for a rename, extract, inline, move, dedup, or internal-implementation swap. Six gated phases prove behavioral parity through unmodified pre-existing tests; any diff that classifies as `feat` is not a refactor and is routed to tdd. A modified pre-existing test is rejected as evidence — it is a behavior change in disguise.

  • Release

    arbiterForge/codeArbiter/plugins/ca/skills/release Skill

    154★ repo

    The single permitted path to a version tag, for any of the four independently-versioned plugins. Routed to when the user invokes /release on a non-default branch with a green suite. Takes the target plugin as its one argument (default ca), derives the SemVer bump from Conventional-Commits history since that plugin's last tag, rolls the commits into that plugin's CHANGELOG, writes an annotated tag in that plugin's namespace, and on authorization publishes it as a GitHub Release with the changelog section as its notes. A release commit, if needed, routes through commit-gate; the tag and Release are never published without explicit authorization.

  • Secret handling

    arbiterForge/codeArbiter/plugins/ca/skills/secret-handling Skill

    154★ repo

    The secret-source gate. Routed to when changed code reads, writes, or passes a secret — API key, token, password, connection string, signing key, certificate, or any value that grants access. Validates that every secret comes from the approved store and never lands in source, log, test fixture, error response, image, or LLM prompt. The auth-crypto-reviewer agent is dispatched as the reviewer.

  • Security architecture

    arbiterForge/codeArbiter/plugins/ca/skills/security-architecture Skill

    154★ repo

    Optional, opt-in STRIDE threat pass for a sensitive feature — invoked deliberately via /threat-model, never forced on ordinary changes. Walks the change's attack surface and security boundaries (governed by ${CLAUDE_PROJECT_DIR}/.codearbiter/security-controls.md), surfaces threats and unmitigated gaps, and MAY dispatch security-reviewer or auth-crypto-reviewer. Not a routine gate; it can hard-STOP only on a genuinely critical unmitigated threat it surfaces.

  • Subagent driven development

    arbiterForge/codeArbiter/plugins/ca/skills/subagent-driven-development Skill

    154★ repo

    The implementation engine. Routed to by /sprint (full plan, autonomous) and by executing-plans (scoped batch, checkpoint-gated). One fresh subagent per task — test-first via tdd — followed by spec-compliance review, quality review, and fresh-run verification. No single context accumulates drift, and nothing is accepted on a subagent's word.

  • Tdd

    arbiterForge/codeArbiter/plugins/ca/skills/tdd Skill

    154★ repo

    The test-first gate. Routed to by /feature (after the spec is approved), /fix, and /refactor before any implementation code is written. Six gated phases — obligation scan, red, green, obligation verify, coverage, lint. No feature code exists before Phase 1 clears; nothing reaches commit-gate until all six are green.

  • Using git worktrees

    arbiterForge/codeArbiter/plugins/ca/skills/using-git-worktrees Skill

    154★ repo

    OPTIONAL per-task isolation for autonomous parallel work. Routed to only on explicit opt-in by subagent-driven-development or dispatching-parallel-agents, so parallel units mutate files without colliding. Stands up one worktree per unit, works it in isolation, then integrates each unit back onto the caller's working branch for the caller's single commit-gate + finishing-a-development-branch exit. Never on the default path; it does not bypass a gate or finish per unit.

  • Debug

    arbiterForge/codeArbiter/site/test/fixtures/plugin-collisions/skills/debug Skill

    154★ repo

    A fixture skill named debug, colliding with the debug command/agent.

  • Alibabacloud ecs windows online troubleshooting

    aliyun/alibabacloud-ecs-troubleshoot-skills/skills/alibabacloud-ecs-windows-online-troubleshooting Skill

    148★ repo

    Use this skill whenever the user reports a problem with a Windows system, Windows Server, or Windows ECS instance, or asks to check, diagnose, inspect, or troubleshoot anything Windows-related. Covers network issues (ping, DNS, DHCP, firewall, SMB), RDP/remote desktop (connection failures, authentication, black screen, lag), storage/disk, system activation, Windows Update, performance slowdowns, user accounts/permissions, drivers, app crashes, security/certificate/TLS, scheduled tasks, or vague requests like 'check the system' or 'something is wrong.' Load this skill even if the user does not explicitly mention Windows but the context implies a Windows environment.

  • Dart test coverage

    kevmoo/dash_skills/skills/dart-test-coverage Skill

    148★ repo

    Understand and improve test coverage in a Dart package. Helps agents run coverage, interpret results, and identify missed lines.

  • Dart test fundamentals

    kevmoo/dash_skills/skills/dart-test-fundamentals Skill

    148★ repo

    Core concepts and best practices for `package:test`. Covers `test`, `group`, lifecycle methods (`setUp`, `tearDown`), and configuration (`dart_test.yaml`).

  • Ai firstify

    techwolf-ai/ai-first-toolkit/plugins/ai-firstify/skills/ai-firstify Skill

    145★ repo

    Analyze, re-engineer, or bootstrap projects to align with AI-first design principles. Use when asked to review, audit, improve, 'ai-firstify', or start a new project. Performs deep analysis across 7 dimensions, actively restructures existing projects, or guides new project setup through discovery questions. Based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp.

    The same file is in 2 other repositories

  • Analyze performance

    techwolf-ai/ai-first-toolkit/plugins/content-studio/skills/analyze-performance Skill

    145★ repo

    Analyze engagement patterns across published posts to identify what works. Use when asked to review performance, find successful patterns, or optimize future content.

  • Setup content studio

    techwolf-ai/ai-first-toolkit/plugins/content-studio/skills/setup-content-studio Skill

    145★ repo

    Set up a new content studio for a person. Copies the plugin template, adapts it to the person's voice, themes, and content types through interactive discovery. Use when asked to create a content studio for someone new.

  • Setup knowledge base

    techwolf-ai/ai-first-toolkit/plugins/knowledge-base/skills/setup-knowledge-base Skill

    145★ repo

    Interactive onboarding to create a structured knowledge base. Defines categories, scaffolds the directory structure, creates the index, and optionally imports initial content. Run this first before using /kb-answer or /kb-import.

  • Performance cycle

    techwolf-ai/ai-first-toolkit/plugins/people-management/skills/performance-cycle Skill

    145★ repo

    Evidence gathering for performance review cycles. Gathers goal completion evidence, peer feedback, development progress, scope changes, and values alignment, organised along the org's performance framework dimensions, with organizational values as the 'how' lens. Surfaces evidence gaps. Never suggests ratings, only organises evidence for the manager's judgment.