execution
claudeDrive dependency-aware issue plans through coordinated implementation, independent review, convergent goals, and safe human-operation runbooks.
4 skills · 3 agents
Install and operate Kestrel across autonomous assignment, observation, recovery, local integration, and managed-worktree cleanup.
Plugin kestrel from marketplace greg-asher-skills in greg-asher/agent-skills. Commands read from the repo's manifest — 1 month ago.
assignAssign a bounded repository task to Kestrel for autonomous implementation and validation in a managed worktree. Use when the user explicitly invokes /kestrel:assign with an issue, task, or implementation outcome they want Kestrel to complete.
cleanupSafely remove a completed or explicitly discarded Kestrel managed worktree while retaining durable evidence by default. Use only when the user explicitly invokes /kestrel:cleanup for an identified or recent run.
integrateVerify and integrate a completed isolated Kestrel result into the current local branch while preserving unrelated changes. Use only when the user explicitly invokes /kestrel:integrate for a completed run.
recoverDiagnose and safely continue a failed, waiting, or interrupted Kestrel run without duplicating live work. Use only when the user explicitly invokes /kestrel:recover and names or implies a Kestrel run needing recovery.
runAutonomously deliver one bounded repository task through Kestrel assignment, monitoring, local integration, validation, and safe managed-worktree cleanup. Use only when the user explicitly invokes /kestrel:run and wants an end-to-end local result.
setupInstall, configure, upgrade, verify, or repair the Kestrel CLI and Local Core. Use only when the user explicitly invokes /kestrel:setup or explicitly approves setup after another Kestrel skill reports that Kestrel is unavailable or incompatible.
statusInspect and explain an active, recent, or identified Kestrel lifecycle run from durable state and runtime evidence. Use only when the user explicitly invokes /kestrel:status to check installation readiness, progress, waiting work, failure, integration, or cleanup state.
Drive dependency-aware issue plans through coordinated implementation, independent review, convergent goals, and safe human-operation runbooks.
4 skills · 3 agents
Ground agent execution in workspace evidence and build durable human understanding through mapping, blast-radius analysis, narration, adaptive trivia, and goal-aware teaching.
5 skills
Artifact-aware conversational product discovery plus deep investigation of software, documents, designs, data, and mixed source folders.
2 skills · 1 agent
Audit and safely reclaim developer disk, diagnose RAM pressure, and protect active coding-agent and repository work.
3 skills
Adaptive solution design for greenfield applications and code-aware changes to existing systems.
2 skills
Convergent product planning that turns settled discovery and design into canonical Product Briefs and agent-ready implementation issues.
2 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.