alexmskills
01Plugin Claude Code
A curated marketplace of reusable, self-improving Claude Code skills and agents. Each skill is an independently versioned plugin.
A curated Claude Code plugin marketplace of reusable, self-improving skills and agents — each an independently versioned plugin.
Plugin Claude Code
A curated marketplace of reusable, self-improving Claude Code skills and agents. Each skill is an independently versioned plugin.
Plugin Claude Code
Assemble a task-specific panel of role-specialized agents and run a generate-critique-refine loop until the work converges on a strong result.
Plugin Claude Code
A self-evolving delivery crew: it composes a task-fit roster of role subagents (each on its own model tier) and runs them as a gated relay to deliver a target, with editable rosters and a per-repo learning loop. architect → dev → qa → deployer is just one example lineup.
Plugin Claude Code
Turn CLAUDE.md into a living Decisions & Learnings log that stays bounded: a format contract enforced at write time by a PreToolUse lint, four downward pressures (strike-through, merge, graduation, quarterly archive), staleness detection against the tree, and a tree-grounded coverage check for the essentials a file…
Plugin Claude Code
Drive a GitHub issue from branch to pull request with a language and build-tool agnostic workflow.
Plugin Claude Code
Automatically captures learnings to per-project memory whenever a task takes more than one fix cycle to resolve.
Plugin Claude Code
Format, static-analysis, coverage, and pre-commit skills for Maven/Java projects. codestyle (spring-javaformat + Checkstyle), pmd (ruleset, plugin wiring, report triage by priority, CPD, and suppression at the right scope), jacoco (coverage gate + gap analysis), and precommit (all of it before a commit).
Plugin Claude Code
Keep agent-written memory files from rotting: re-verifies pinned facts against the tree (version pins, sequence facts, vanished paths) and flags what has become wrong, checks MEMORY.md index drift both ways, and enforces the memory format contract at write time. Flags, never deletes — supersession is strike-through…
Plugin Claude Code
Drop ideas on a canvas, connect them, and compile the map into an organized Markdown prompt. Offline and dependency-free: a self-contained page for capture, a deterministic compiler for the map -> prompt step, and JSON Canvas (.canvas) as the save format so a map can be reworked later or opened in Obsidian. A ✦…
Plugin Claude Code
One visible channel for every long-running process — local sweeps, backgrounded commands, and work handed to external systems. The server that serves the live progress page IS the tracker: a tiny stdlib Python daemon holds live jobs in memory (auto-spawned by the first producer, single writer, no store locking)…
Plugin Claude Code
Analyzes each prompt you submit against a tiered ruleset of prompting best practices; nudges you toward better prompts (definition-of-done, scoped references, guardrails, verification steps) and quietly graduates rules you consistently follow.
Plugin Claude Code
A self-evolving 'discover' crew: it composes a task-fit team of coverage roles for an information space, fans them out in parallel, dedups, and adversarially verifies their findings into one trustworthy, cited result. The discover counterpart to dev-crew (deliver) and brainstorm-panel (decide).
Plugin Claude Code
Specialist review subagents for Java/Maven projects — code review, test running, and dependency/CVE auditing on lighter model tiers. No-write by construction: Write and Edit are withheld, so they read, build, and report without touching the working tree.
Plugin Claude Code
A per-repo repository of evolving roles (.claude/roles/) usable four ways: solo via /roles:as or per-persona skills, as dev-crew roles, as brainstorm-panel seats, and as research-sweep coverage roles. Ships seed personas, a reactive init + graduation-audit SessionStart hook, the shared-core convention, and the /roles.