๐
Plugins
Loading...
Showing 30 of 22881 results
Core infrastructure: persistent agent identity, session lifecycle hooks, operational memory, and meta skills. Customizable agent name and memory path.
The Index-driven dev pipeline: Inspector Lestrade (triage), Dr. Watson (dev work), and Sherlock Holmes (code review) as subagents. Interactive or unattended dispatch.
Generate a prioritized morning workday report with GitHub PRs and Jira issues grouped by priority
An autonomous dev loop (/orchestrate fans out parallel issue-solving in isolated git worktrees, then per-issue my-review reviews each built slice and surfaces its findings), a single-task plan-build-review chain (/pipeline: models routed by complexity tier), plus a context watchdog that drives early /clear and /handoff as the window fills and auto-resumes the in-flight plan.
Day-to-day control: enforces the layer (hooks/routing) and produces trend reports. Depends on the other two.
Build multi-step email sequences that respond to customer actions automatically.
Scaffold complete Athena workflow packages with workflow definitions, plugin pins, marketplace registration, and validation gates
Workflow-builder skill: design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool (CLAUDE_CODE_WORKFLOWS=1, /workflows). Every session opens with an intake question set; when the user is vague, a stdlib recommendation engine infers and proposes a topology with rationale instead of stalling. Ships 3 stdlib Python tools (intake recommendation engine, .js validator enforcing pure-literal-meta / no-non-determinism / guarded-loop / parallel-thunk rules, topology scaffolder), 3 references citing 7-8 authoritative sources each (API surface, orchestration patterns, decision + intake guide), templates + a runnable example, cs-workflow-architect persona agent + /cs:workflow-build slash command. Use when building, scaffolding, or running a custom Claude Code workflow or orchestrating sub-agents (fan-out, pipeline, loop, judge-panel).
PROGRESS.md ๆฐธ็ถๅใใใฏ + ใซใผใๅฎ่กใฏใผใฏใใญใผ skill ็พค (implement-issue / run-epic / create-issue)ใ
from Lordjiggy/claude-code-marketplace
Orchestration Temporal (TypeScript) โ workflows skill_eval, source_watch, usage_observer + activities.
Git worktreeใจWezTermใๆดป็จใใไธฆๅ้็บใฏใผใฏใใญใผๆฏๆดใใผใซ
Visualize, instrument, budget, replay, and estimate Claude Code Workflow runs (workflow-lens CLI + Control Tower dashboard).
PreToolUse hooks that keep sub-model choices deliberate โ denies high-fan-out Workflow scripts with no per-agent model: override, asks before all-Opus built-in named workflows (e.g. deep-research), and denies ad-hoc Agent dispatches that omit model unless the agent type pins one in frontmatter.
Personal productivity rule for KMRH47: when work repeats or performance work needs before/after evidence, convert it into deterministic workflow nodes, measurement ledgers, explicit inputs, outputs, reports, and composable orchestrators instead of burning human memory and agent tokens.
ใจใผใธใงใณใ้ไพๅญใฎไฝๆฅญ้็จในใญใซ็พค๏ผexternal-writes / test-targeted๏ผใ
Skill-level observability for agentic workflows
Comprehensive development workflow system for codebase research, implementation planning, and stacked PR management through specialized AI agents