Adam's machine-bound coding skills for Claude Code on the owner's own machines (WSL and Windows homes): Claude Code settings sync, session and memory management, and elevation from WSL.
Plugin adam-coding-local from marketplace adam-agentskills in Adam-S-Daniel/adam-agentskills. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
launch-top-level-claude-sessionLaunch a new top-level interactive Claude Code session in a new Windows Terminal tab, on Windows or in WSL, in a chosen folder, optionally remote-controllable and seeded with a prompt or handoff file. Use whenever the user asks to start, open, launch or spawn a new or separate Claude Code session, o
migrate-claude-memoryInventory and clean up Claude Code auto-memory stores under ~/.claude/projects/*/memory/ on this machine: decoded paths, counts, sizes, freshness, orphaned stores for review, never deleting ambiguous ones. Trigger on "clean up claude memory", "orphaned memory", "inventory memory stores". Local-only;
sync-cc-settings-between-wsl-and-windowsSync Claude Code settings.json between the Windows and WSL homes, merging per property and keeping OS-bound keys per file. Use for "sync Claude Code settings", "merge my settings.json", or keeping WSL and Windows settings in sync, not for editing one file. Windows-only (PowerShell 7+ and the WSL UNC
tool-powershellUse when a PowerShell tool call fails with a bare "Exit code 1", fails the same way twice, or is refused as blocked or protected. Covers getting the real error, the two-strikes stop rule, reporting a policy block instead of routing around it, and previewing deletions. For "Access is denied" from pow
windows-elevation-from-wslHandle "Access is denied" from powershell.exe or pwsh.exe run inside WSL: scheduled-task registration, service changes, LSA rights grants such as SeBatchLogonRight, HKLM writes or any other Windows state change from WSL. Use it before attempting such a write from WSL and the moment one is denied. A
"${CLAUDE_PLUGIN_ROOT}"/hooks/clone-sync/on-merge.sh
"${CLAUDE_PLUGIN_ROOT}"/hooks/clone-sync/on-session-start.sh
The cms-platform site machinery's own skills, federated from that repo rather than mirrored here: Decap /admin config rendering, AWS bootstrap and PR preview environments, Playwright e2e, CI watcher loops, stuck-PR triage, and the platform release/consumer-bump flow.
13 skills
Adam's coding skills for Claude Code terminals and Claude Code cloud sessions: GitHub Actions debugging and hardening, settings-as-code, bash CI reliability review, skill provenance, disarming inherited reach, and filing vendor release-impact issues.
9 skills
Adam's non-coding skills that need local files or a signed-in browser, for the Claude Desktop app's local Cowork: PDF OCR, audit, renaming and comparison, and Fastmail email and sending-identity workflows.
7 skills
Adam's skills for any Claude surface, coding or not: the claude.ai web and iOS apps, Claude in Chrome, the Claude Desktop app, and Claude Code. Writing ADRs and resolving task ambiguity. It also installs the fleet guidance into Claude Code's user memory at session start, and in Claude Code blocks a GitHub write that lacks the agent marker.
2 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
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
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
Expose the plugin-safe Claude Code subset of Agentic Awesome Skills through a single marketplace entry.
200 skills
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
12 skills · 11 agents · hooks
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.