#coding-agent
70 resources · page 1 of 2
Results
- planning-with-files
Manus-style persistent file-based planning for AI coding agents: keeps task_plan.md, findings.md, and progress.md on disk so work survives context loss…
- planning-with-files-ar
The publisher’s description is only a heading. Open the skill to read what it does.
- planning-with-files-de
Manus-artiges Dateiplanungssystem zur Organisation und Verfolgung des Fortschritts komplexer Aufgaben.
- planning-with-files-es
Sistema de planificación basado en archivos estilo Manus para organizar y rastrear el progreso de tareas complejas.
- workflow-authoring
Guidance for writing, editing, reviewing, and debugging JavaScript workflow code for pi-dynamic-workflows.
- codex-delegate
Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself.
- cursor-delegate
Delegate a coding task to the Cursor Agent CLI (cursor-agent) as a background implementer, then review its diff and land it yourself.
- delegate-setup
Configure delegation fleet lanes: which implementer CLI handles which kind of work, with optional model and effort (or variant) dials.
- grok-delegate
Delegate a coding task to the Grok Build CLI as a background implementer, then review its diff and land it yourself.
- kimi-delegate
Delegate a coding task to the Kimi Code CLI (kimi) as a background implementer, then review its diff and land it yourself.
- omp-delegate
Delegate a coding task to Oh My Pi (omp) as a background implementer, then review its diff and land it yourself.
- opencode-delegate
Delegate a coding task to the OpenCode CLI as a background implementer, then review its diff and land it yourself.
- pi-delegate
Delegate a coding task to the Pi coding agent CLI (pi) as a background implementer, then review its diff and land it yourself.
- qoder-delegate
Delegate a coding task to the Qoder CLI (qodercli) as a background implementer, then review its diff and land it yourself.
- vibe-delegate
Delegate a coding task to the Mistral Vibe CLI (vibe) as a background implementer, then review its diff and land it yourself.
- warp-delegate
Delegate a coding task to the Warp Agent CLI (oz) as a background implementer, then review its diff and land it yourself.
- ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge
- supergoal
Objective-driven dev router.
- batonbot
Interact with BatonBot, the visual AI agent workflow orchestrator.
- imagegen
Generate original images, artwork, product visuals, diagrams, or other raster assets with the desktop's configured image provider.
- fable-method
A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first).
- elixir-writing-docs
Guides writing Elixir documentation with @moduledoc, @doc, @typedoc, doctests, cross-references, and metadata.
- exunit-code-review
Reviews ExUnit test code for proper patterns, boundary mocking with Mox, and test adapter usage.
- go-web-expert
Comprehensive Go web development persona enforcing zero global state, explicit error handling, input validation, testability, and documentation…
- llm-artifacts-detection
Detects common LLM coding agent artifacts in codebases.
- pytest-code-review
Reviews pytest test code for async patterns, fixtures, parametrize, and mocking.
- rust-testing-code-review
Reviews Rust test code for unit test patterns, integration test structure, async testing, mocking approaches, and property-based testing.
- strategy-interview
Act as a strategy interviewer who helps the user produce a strategy document grounded in the kernel framework (diagnosis, guiding policy, coherent action), enhanced with three complementary lenses applied when the conversation warrants them
- strategy-review
Pressure-test strategy documents to find where they'll break before reality does it for you.
- adr-writing
Generate Architectural Decision Records (ADRs) following the MADR template with systematic completeness checking.
- superdesign
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models.
- mentor
Generate an /insights-style HTML report across MANY of your agent coding sessions (Claude Code and OpenAI Codex): what you work on, how you…
- reverse-engineer-anything
Reverse engineer native, managed, Electron/JavaScript, packaged, and browser applications with REA.
- harness-writing
> 🌐 [English version](https://github.com/tienenwu/fables/blob/main/en/harness-writing/SKILL.md) · 繁體中文（正本 / canonical）
- test-writing-guide
Provides guidelines for writing test code for Unity projects.
- fable-domain
Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a…
- fable-judge
Adversarial verification of finished work.
- fable-loop
End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an…
- ospec-goal
Create or advance a full OSpec goal using the current document, task graph, worker, review, and evidence workflow.
- work-canvas
Turn an agent's own work — progress, debugging, analysis, comparisons, decisions — into one self-contained, reviewable HTML page (a "work canvas" / 网页看板)…
- lesson-learned
Analyze recent code changes via git history and extract software engineering lessons.
- fixer
Surgical code fixer for Bug Hunter.
- recon
Codebase reconnaissance agent for Bug Hunter.
- referee
Final arbiter for Bug Hunter.
- skeptic
Adversarial code reviewer for Bug Hunter.
- lsp-extract-function
Extract a selected code block into a named function.
- claudexor
Use the local Claudexor control plane for harness-agnostic coding work across Claude Code, Codex, Cursor, and OpenCode.
- gen-test-plan
Analyze repo, detect stack, trace changes to user-facing entry points, generate E2E YAML test plan
- mine-plan-review
Strictly review one implemented repository plan against AGENTS.md, architecture, the immutable plan, implementation commits, real runtime behavior,…
- agent-architecture-analysis
> Reference: [12-Factor Agents](https://github.com/humanlayer/12-factor-agents)
- artifact-analysis
Turn a set of local paths (or a beagle project's conventional knowledge locations) into a cited, structured extraction of insights, context, decisions, and raw detail.
- brainstorm-beagle
Turn a fuzzy idea into a comprehensive, implementation-free project spec through collaborative dialogue.
- deepagents-code-review
Reviews Deep Agents code for bugs, anti-patterns, and improvements.
- humanize-beagle
Invoke the humanize-beagle skill with optional flags: humanize-beagle [--dry-run] [--all] [--category <name>].
- llm-judge
Compare code implementations across multiple repositories using structured evaluation.
- prfaq-beagle
PRFAQ: The Concept Filter (Working Backwards)
- quick-plan
Quick Plan: Conversation Into Implementation Plan
- receive-feedback
Process external code review feedback with technical rigor.
- resolve-beagle
Use as the follow-up to brainstorm-beagle when a spec has an Open Questions section (or quietly carries latent gaps) that need closing before planning or…
- review-ai-writing
Detect AI-generated writing patterns in developer text — docs, docstrings, commit messages, PR descriptions, and code comments.
