Development plugins

Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.

3 commands · hooks

A structured validation workflow for software development tasks, plus QA test automation and JIRA integration. Validates requirement completeness, runs manual test cases on web (playwright-cli) or Android (adb) via the automation-expert agent, and retrieves/posts results to JIRA tickets.

3 skills · 1 agent

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.

3 commands · hooks

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.

3 commands · hooks

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.

3 commands · hooks

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.

3 commands · hooks

Auto-triggered Skills for querying R package documentation via WebFetch. Covers CRAN, tidyverse, Shiny, and general R packages.

4 skills

Folder-level OCR pipeline orchestrator wrapping macdoc — PDF→PNG split, parallel OCR with SSH-tunnel health check + auto-retry, per-page md merge, idempotent resume from interruption. Wraps the boilerplate every 'OCR a folder of PDFs' task otherwise re-derives.

1 skill · 3 commands

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

Injects real-time, up-to-date library documentation into Claude's context for accurate code generation

4 skills

Patterns for AI-powered apps: retrieval evaluation, grounded generation with citations, SSE streaming UI, and the OpenAI API.

4 skills

Guided 7-phase feature development workflow with specialised agents for exploration, architecture, and review

1 command · 3 agents

Ascend C Kernel 直调算子开发 Team。含完整工作流（设计→实现→审查→性能验收）、3 个专业 Agent 和工程模板。

3 agents · hooks

PyPTO 算子端到端开发 Team。含 3 个 Subagent（analyst/developer/perf-tuner），7 阶段状态机编排，支持断点续跑和失败恢复。

3 agents · hooks

NPU 模型推理端到端优化 Team。含 workflow、分析/实施/验证 Subagent，覆盖并行、KVCache/FA、融合算子、图模式、多流、预取和 SuperKernel。

3 agents · hooks

Three native skills that run the Diolog Tasks issue pipeline — triage, plan, and worker — entirely inside your interactive Claude Code session (no Agent SDK, so usage draws from your standard interactive allowance, not the separate Agent SDK credit). Formerly linear-issue-pipeline; now targets the diolog-tasks MCP (mcp.diolog.com.au). tasks-triage runs a technical + Specification Sentinel product review and posts a non-technical readiness comment; tasks-plan classifies a tier, investigates the codebase, writes docs/plans/{id}.md and comments the repo-relative path (no file upload); tasks-worker implements a planned issue in an isolated worktree via dynamic ultracode workflows (understand → implement → rebase → acceptance review → resolve), with no remote PR. The plan and worker fan out parallel subagents via the Workflow tool to speed up large investigations. Recalibrated for current-model behaviour (Anthropic's Claude Opus 5 prompting guidance), ported from the generalized twin: tasks-worker's per-phase gate is explicitly a conformance check (evidence-shaped — the clause, the file:line, the gate you ran) rather than a second correctness review stacked on a phase that already reviewed itself; adversarial finding-verification is aimed at Criticals, structural fixes, and locked-decision reversals rather than blanket 1:1, and no reviewer is briefed to be conservative; the completion comment keeps to tables/counts/drops/gates rather than narrating the phases; and tasks-triage/tasks-plan gain the effort dial plus length budgets. All three point at the twin's new pipeline-wide canonical feature-spec-pipeline/skills/work/references/model-and-effort.md. v2.4.0 (from the WEB-4905 110-ticket audit): a fourth skill, tasks-verify — an independent fresh-session acceptance verifier that re-derives requirements from the ticket and closes them on typed behavioural evidence (browser measurements, exercised requests, stored-row counts) before a ticket is treated as done; evidence-typ

4 skills

Four native skills that run an issue-tracker-free, markdown-doc feature pipeline — /triage, /plan, /work, /gap-fix — entirely inside your interactive Claude Code session. /triage turns a feature idea (inline text or a notes file) into a versioned spec at docs/specs/spec-DIO-0001.md (id allocated from docs/feature-specs/LEDGER.md), running a codebase grounding pass plus a Specification Sentinel product/UX/compliance review and appending a non-technical readiness section. /plan classifies a tier, investigates the codebase, writes docs/plans/plan-DIO-0001.md and links it from the spec. /work implements the plan in an isolated worktree via dynamic ultracode workflows (understand → implement → rebase → acceptance review → resolve), appends a progress section to the spec, and leaves the branch local — no remote PR. /gap-fix runs after /work as the remediation step: it re-enters the work branch, ALWAYS re-audits the delivered code against the original spec (merging in any human/QA gaps you provide), and implements the fixes in code (file-disjoint fan-out + typecheck gates), looping audit→fix until only optional Low items remain, then commits locally and appends a gap-fix progress note — no remote PR. The plan, work, and gap-fix skills fan out parallel subagents via the Workflow tool (in small batches to avoid throttling). A doc-driven sibling of diolog-tasks-pipeline that needs no Diolog Tasks MCP. Recalibrated for current-model behaviour (Anthropic's Claude Opus 5 prompting guidance) with a new pipeline-wide canonical reference, skills/work/references/model-and-effort.md: the model × effort lane calibration (per-lane effort levels, `low` as the level built for subagents, effort-before-model because REVIEWER ≥ WRITER is about capability class not spend, `xhigh` + 64k `max_tokens` for long-horizon runners, hold-effort-constant for the prompt cache, never hardcode a dated model id in a wire self-check); the oracle-checks-vs-re-reading-your-own-work distinction that says whic

4 skills

Public data enrichment for law enforcement agencies — ORI to contextual feature vectors via 9 federal data sources

3 skills · 1 MCP server

Constraint-driven verification skills for coding agents.

4 skills

Performance optimization workflow for Python/Django and TypeScript/Vue. Includes the /perf command with a 7-phase workflow, perf-analyzer and perf-reviewer agents, and a performance-hints skill with distilled reference material.

1 skill · 1 command · 2 agents

A Claude Code plugin whose skills guide design from a fuzzy requirement all the way to an experienceable screen, covering UX exploration, UI specification, ubiquitous language mapping, and design build.

4 skills

The Modulary toolkit: new, find, list, and add for a library of stack-agnostic capability modules.

4 skills

Generate and edit project images with OpenAI GPT Image models through a bundled local MCP server.

2 skills · 1 command · 1 MCP server

Authoring workflows for Claude Code primitives: skills, hooks, subagents and instruction files (CLAUDE.md and rules). Each follows a draft, test, review and iterate loop against the current reference docs, and delegates to its siblings when a job needs more than one primitive.

4 skills

Guided setup for your own HiveTrade bot, with a local MCP server that never handles your private key.

2 skills · 1 MCP server · hooks

Local, typed, append-only inbox CLI (cci) and Claude Code plugin for multi-agent drive coordination with bounded reads

1 skill · 2 MCP servers · hooks