632 tagged coding, measured the same way as everything else here.
Browse within: aagent 57ide 57skill-md 57skills-sh 55公众号 36beads 30cline 30harness 30Multi-Agent 23aiagents 22local-first 21code 20desktop-app 20notebook 20
Skill Claude CodeCodex
Architecture/conventions for the Echo browser SPA: Go stdlib server :3740, Vite-built TS+JS SPA (embedded web/dist), JSON envelope, WebSocket hub, chat tool loop, shared appdata echo.json, internal/tools registry, tool-generated media transport (Phase 0/1), and the file-browser image/video/audio preview surface…
Skill Claude CodeCodex
How Echo surfaces cross-surface/cross-tab alerts to the user: global WebSocket broadcasts (chatcompleted, planquestionsawaiting) mirrored by frontend notification modules that play sounds, show OS/browser Notifications, and deep-link on click.
Skill Claude CodeCodex
Build, validate, package, and stage optional Echo plugins using the Echo Plugin API v1 security and lifecycle contracts.
Skill Claude CodeCodex
Designs a secure authentication and authorization flow for any application, covering login, sessions, roles, and edge cases.
Skill Claude CodeCodex
Write clear, conventional git commit messages — type(scope): summary, imperative mood, a body that explains the why.
Skill Claude CodeCodex
Design predictable REST APIs — noun resources, correct status codes, pagination, consistent errors, and versioning.
GantisStorm/autonomous-coding-harness
Skill Claude CodeCodex
This document covers code quality principles, analysis dimensions, and CLI commands for maintaining code quality in this Python project.
Skill Claude CodeCodex
Audits time-based machine learning backtests, walk-forward validation, rolling retraining, forecasting evaluations, and temporal train/test pipelines for data leakage, faulty split logic, invalid feature timing, target leakage, calibration/tuning leakage, and misleading experiment comparisons. Use when agent needs to…
Skill Claude CodeCodex
Composite review-and-fix for the current diff — run the correctness review (validate) and structural-quality review (simplify) in parallel, merge their findings, then apply all fixes in a single serial pass and re-verify. Supports --effort, --fix, --comment. For a full-repo survey use /audit.
Skill Claude CodeCodex
Generate or update a mermaid diagram with the .mmd text as source of truth — defaults to a lightweight zero-dependency Node live-preview server that watches the .mmd and hot-reloads a browser tab (pan/zoom), with a self-hosted mermaid.live editor via Docker, system-viewer SVG, VS Code live preview, or a public…
Skill Claude CodeCodex
Hands-free, headphones-only voice loop for the coding agent — you speak, whisper.cpp transcribes, claude -p runs with full tools at flat-rate under your Claude Code subscription, and a local TTS backend (macOS say, espeak-ng, Piper, or an XTTS voice-clone) speaks the reply. Cross-platform (macOS/Linux/WSL); everything…
Skill Claude CodeCodex
Provides optimal workflows for 24 use cases (writing, analysis, coding, business) powered by the claude-101 MCP server. Calls the matching MCP tool to obtain structured methodology and computed metrics, then produces output grounded in real data.
Skill Claude CodeCodex
Run the queued GSD → Superpowers → review → ship loop end-to-end. Reads tasks from docs/agile-loop/tasks/.md, spawns isolated child sessions per stage, opens one PR per task, and auto-merges it (squash) before continuing to the next task. Use when asked to "run the agile loop", "process the next queued task", or…
Skill Claude CodeCodex
Grilling session that stress-tests your plan against the project's domain model, terminology, and documented decisions, updating CONTEXT.md/ADRs inline. The forge loop's entry point (the plan-grilling stage), always conversational. Use to start or refine a task — "start a new task", "start with forge", "let's work on…
Skill Claude CodeCodex
Seals a finished task — confirms the retro, marks STATUS.md done, archives it, empties the active .forge state, and closes the loop (which blocks the same plan from re-running). fg-done all batch-seals every already-executed task at once (retros skipped, backlog untouched, verification gate intact). Use when a task's…
Skill Claude CodeCodex
Goal-driven momentum loop with bounded replan — an initial conversational inquiry pins a machine-verifiable stop condition, a fix-forward scope, and a replan cap (default 3) into .forge/loop.md, then drives tasks unattended (run → UAT → auto-skip retro → seal) until the checks pass, halting only at the walls…
Skill Claude CodeCodex
Use modern CLI tools (rg, fd, ast-grep, bat, sd, jq, yq, tokei, eza, dust, procs, delta, hyperfine, watchexec, just) through the LocalREPL shell bridge for efficient codebase analysis, structured data extraction, and reactive workflows. Trigger whenever the user wants to search code, inspect a repository, count or…
Skill Claude CodeCodex
This mode is invoked when the user runs /slopnought-audit (or asks in equivalent terms: "audit this codebase for maintainability," "find tech debt," "what's wrong with this code," "help us clean this up"). It analyzes an existing codebase, produces a prioritized, evidence-based remediation plan, and — only with the…
Skill Claude CodeCodex
LLM-generated code often works today but becomes a liability tomorrow — nobody (human or agent) can tell what it does, why, or what's safe to change. This skill makes maintainability a first-class requirement, on par with "does it work.".
Skill Claude CodeCodex
Use when starting work in a LARGE or UNFAMILIAR codebase, when a repo already contains an INDEX.md, or when repeatedly grepping for where something is defined. Generates and consults INDEX.md - a symbol locator (namespaces, types, enums, constructors, functions, methods with parameters, globals/statics, one-line…
Skill Claude CodeCodex
Use whenever deciding whether to search the WEB and how to construct the queries - answering factual questions, evaluating products/versions/APIs, encountering unfamiliar names or terms. Encodes the rate-of-change rule, the unrecognized-entity rule, effort scaling, query construction, and source-trust calibration. Do…
Skill Claude CodeCodex
Use whenever persistent agent memory is read, written, or has grown past its budget - the first time memory is consulted in a session, whenever something worth remembering appears, and whenever MEMORY.md or a topic file exceeds its size budget. Implements a two-tier structure (slim MEMORY.md index linking memory-.md…
SkillMedev/legacy-modernization
Skill Claude CodeCodex
Audits third-party dependencies for exploitable CVEs, abandonment, license exposure, and supply-chain hygiene, and delivers a ranked findings report with a remediation order. Use when someone asks "is this package safe to add", "audit our dependencies", "npm audit is screaming, what actually matters", "can we use this…
SkillMedev/legacy-modernization
Skill Claude CodeCodex
Ports a codebase across a breaking language or runtime version with compatibility shims, batched automated transforms, dual-runtime CI, and old-vs-new output diffing, ending in a flag-flip cutover with a rollback rule. Use when someone says "migrate us from Python 2 to 3", "we're jumping Node majors", "move to the…