Plugin Claude Code
Bundles 1 skill · 125 tokens together
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
Bundles 1 skill · 125 tokens together
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
Bundles 1 skill, 6 agents · 556 tokens together
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
Bundles 1 skill, 1 command · 210 tokens together
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
Bundles 1 skill · 69 tokens together
Drive a GitHub issue from branch to pull request with a language and build-tool agnostic workflow.
Plugin Claude Code
Bundles 1 skill · 45 tokens together
Automatically captures learnings to per-project memory whenever a task takes more than one fix cycle to resolve, and nudges toward a change of approach when the same command fails three times in a row.
Plugin Claude Code
Bundles 4 skills · 330 tokens together
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
Bundles 1 skill · 103 tokens together
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
Bundles 1 skill, 3 commands · 177 tokens together
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
Bundles 1 skill · 149 tokens together
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
Bundles 1 skill, 8 commands · 345 tokens together
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
Bundles 1 skill · 125 tokens together
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
Bundles 1 skill, 3 agents · 87 tokens together
Specialist review subagents for any stack — code review, test running, and dependency/CVE auditing on lighter model tiers. Each finds the project's own build, lint and audit commands (Maven, Gradle, npm, Python, Go, Rust, .NET, Ruby and more) instead of assuming one. No-write by construction: Write and Edit are…
Plugin Claude Code
Bundles 9 skills · 739 tokens together
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.
Plugin Claude Code
Bundles 1 skill · 128 tokens together
Read the whole screenshot, not just the bug you came for. Sweeps every capture against a checklist of UI defects, files what it finds, and grows the checklist each time a defect is reported that it should have caught.
Plugin Claude Code
Bundles 1 skill · 116 tokens together
Build a presentation-ready screenshot deck of the current product for demos, slide decks, and stakeholder walkthroughs. Discovers the aspects worth showing (entry points, routes, --help, recent CHANGELOG), proposes an editable plan, captures each aspect with the right tool per surface (the project's existing browser…
Plugin Claude Code
Bundles 1 skill · 94 tokens together
Scan a codebase for OWASP-style vulnerabilities and report findings with file:line locations and remediation guidance.
Plugin Claude Code
Bundles 1 skill · 125 tokens together
Audit SKILL.md files against published skill-authoring guidance — frontmatter validity, whether the description actually says when to trigger, body size, progressive disclosure, and broken references. Zero-dependency Python checker with three severity levels, usable as a CI gate. Self-learning: a defect it fails to…
Plugin Claude Code
Bundles 1 skill · 87 tokens together
Spring Batch 5/6 development: what the framework actually does versus what its API suggests, grounded in runnable samples. Restart versus a new JobInstance, flow and deciders, tasklet transaction boundaries, partitioning, the job repository Boot 4 does not give you, and the testing package most projects declare and…
Plugin Claude Code
Bundles 1 skill · 134 tokens together
Self-calibrating discipline for bug fixes: treat the local fault as one instance of a class — check scope for the same pattern elsewhere, name the class of mistake, propose prevention drawn from the repo's own lint/pre-commit/test tooling — and report before patching, defaulting to a local fix. First run calibrates a…
Plugin Claude Code
Bundles 1 skill · 126 tokens together
Backlog-drain loop: rank the open tickets, dispatch the genuinely startable ones in parallel (worktree-isolated, role-briefed, honest width), verify and merge each result, and re-triage on every completion until the queue is empty or everything left needs the user.
Plugin Claude Code
Bundles 1 skill · 117 tokens together
Audit and tighten a repo's CLAUDE.md and guardrails so Claude Code works faster and more accurately in it: verify CLAUDE.md against reality, tighten the verify loop, add missing static guardrails, cut permission friction.
Plugin Claude Code
Bundles 1 skill · 108 tokens together
The runtime half of multi-lane orchestration: detect a lane that has drifted from its brief, decide relay-vs-re-scope-vs-pause, read a verdict you did not run, and hold the machine's real parallelism ceiling. Carries four measured deviation shapes — the control that pins a blocker in place, the report taken as fact…
Skill Claude Code
Java 21 | Spring Boot 4.0.2 | Kubernetes Client 25.0.0 | Picocli 4.7.6.
Skill Claude Code
Code review automation for Java, TypeScript, JavaScript, Python, Go. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: