Skip to main content

Coding & Development agent skills

Agent skills for software development, debugging, code review, and implementation. Browse reusable SKILL.md agent workflows and prompt templates in this category. Each card links to when-to-use notes and setup steps.

Active filters:Agent skillsClear all
codingAgent skill

F Status

Catch the owner up in plain English on a Topping Out job: where we are, what got done, the state now, what's next. Reads ONLY the live session; no subagents, no git, no file reads, no writes. Use when the user runs /f-status, says "catch me up", "where are we", "I'm lost", "refresh me", or comes back after stepping away. Not the 5-line status block every reply ends with (templates/J-STATUS.md).

Content score 68/100 · provisional14
View skill
codingAgent skill

F Survey

Topping Out's first step: turn a fuzzy ask into a decision-complete, codebase-grounded commission block by settling every open question first. Use when the owner runs /f-survey, says "survey this", "groom this" (the old name), "this is still vague", "tighten this before we build", "what am I missing", or hands over work whose scope or approach is not yet decided. Add --voice (or say "survey this out loud", "talk me through it") to run it aloud as a colleague conversation, one short turn at a time. Also answers to its old name, /f-groom. Next step: /f-blueprint. Not the site walk (the machine check at the start of a job, METHOD §2). Not for writing the plan (f-blueprint) or cutting it into tickets (f-schedule).

Content score 68/100 · provisional14
View skill
codingAgent skill

Fix Dependabot

Fix a Dependabot PR by updating all monorepo instances of the dependency, running bun install, and pushing

Content score 68/100 · provisional70k
View skill
codingAgent skill

Github

GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos, and gh api queries.

Content score 68/100 · provisional394k
View skill
codingAgent skill

Go Idiomatic

Go development following Go proverbs, stdlib-first philosophy, and idiomatic patterns. Use when working on Go projects requiring simplicity, clarity, and performance. Emphasizes table-driven tests and small interfaces. Do NOT use for other programming languages.

Content score 68/100 · provisional19
View skill
codingAgent skill

Graincrawl

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Content score 68/100 · provisional395k
View skill
codingAgent skill

Healthcheck

Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.

Content score 68/100 · provisional394k
View skill
codingAgent skill

Linctl

Use linctl as the Linear control surface for agent-safe issue, project, Cycle, ProjectMilestone, organization, user, team, search, release, initiative, customer, notification, attachment, comment, and metadata work. Prefer it over Linear MCP, raw GraphQL, or ad hoc API calls when linctl covers the operation; use guarded writes only after target confirmation.

Content score 68/100 · provisional12
View skill
codingAgent skill

Model Usage

Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns.

Content score 68/100 · provisional394k
View skill
codingAgent skill

Morph Ppt 3d

3D Morph PPT — extends morph-ppt with GLB model insertion, cinematographic camera, model-content layout, and enriched visual design system.

Content score 68/100 · provisional62
View skill
codingAgent skill

Node Inspect Debugger

Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.

Content score 68/100 · provisional394k
View skill
codingAgent skill

Notcrawl

Notion archive: search, sync freshness, pages/databases, Markdown exports, SQL counts, and Notcrawl repo work.

Content score 68/100 · provisional395k
View skill
codingAgent skill

Notion

Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.

Content score 68/100 · provisional394k
View skill
codingAgent skill

Openai Whisper Api

OpenAI Audio Transcriptions API via curl; gpt-4o-transcribe, mini, diarize, or whisper-1.

Content score 68/100 · provisional394k
View skill
codingAgent skill

Openclaw Ghsa Maintainer

Inspect, patch, validate, publish, or confirm OpenClaw GHSA security advisories and private-fork state.

Content score 68/100 · provisional395k
View skill
codingAgent skill

Openclaw Qa Testing

Run, watch, debug, extend, or explain OpenClaw qa-lab and qa-channel scenarios, artifacts, and live lanes.

Content score 68/100 · provisional395k
View skill
codingAgent skill

Penguin Config

Manage model API keys, default models and per-agent vault secrets with the penguin CLI.

Content score 68/100 · provisional3.2k
View skill
codingAgent skill

Pr Body

分析当前分支的全部变更,自动生成或更新 PR 标题和正文。聚焦内容质量:解释 why、归纳 what、标注测试方式,遵循 anolisa 项目 PR 模板规范。适用于新建 PR 前生成描述,或已有 PR 需要更新描述。

Content score 68/100 · provisional659
View skill
codingAgent skill

Project Guidelines Example

Project-specific skill template covering architecture, patterns, testing, and deployment guidance.

Content score 68/100 · provisional298k
View skill
codingAgent skill

Python Debugpy

Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.

Content score 68/100 · provisional394k
View skill
codingAgent skill

React Web

React/TypeScript web development with modern patterns, component architecture, and testing discipline. Use when building React web applications, hooks, state management, or frontend components. Do NOT use for React Native mobile development or other frameworks.

Content score 68/100 · provisional19
View skill
codingAgent skill

Run

Launch and verify AgentMux's own task dev build on Windows — the MAXPATH subst workaround, a real free-port check instead of trusting the hash, how to confirm the window is actually ready (poll state, not logs), and a safe cleanup pattern for a host running several agents' dev sessions at once.

Content score 68/100 · provisional24
View skill
codingAgent skill

Security Triage

Triage OpenClaw security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof.

Content score 68/100 · provisional395k
View skill