AGENT SKILL

using-skills

Use when starting any conversation and before taking any non-trivial action.

License 许可
MIT
最近更新
2026-11-15
Stars
★ 0
Forks
1

01 前言 Front Matter

name
using-skills
triggers
[ "user", "model" ]
description
Use when starting any conversation and before taking any non-trivial action.

03 SKILL.md 正文

If you were dispatched as a subagent to execute a specific task, ignore this skill.

If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.

IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.

This is not negotiable. You cannot rationalize your way out of this.

The Rule

Invoke relevant or requested skills BEFORE any response or action - including clarifying questions, exploring the codebase, or checking files. If it turns out wrong for the situation, you don't have to use it.

Before entering plan mode: if you haven't already brainstormed, invoke the /grilling skill first.

Then announce "Using [skill] to [purpose]" and follow the skill exactly. If it has a checklist, create a todo per item.

Skill Priority

When multiple skills apply, process skills come first - they set the approach, then implementation skills carry it out. /grilling and /diagnosing-bugs are the most common process skills, but the rule holds for any of them.

  • "Let's build X" → /grilling first, then implementation skills.
  • "Fix this bug" → /diagnosing-bugs first, then domain skills.
  • "Just change a button color" or "rename this" → /review-cadence first to decide whether to skip grilling and review at the end.

Red Flags

These thoughts mean STOP-you're rationalizing:

Thought Reality
"This is just a simple question" Questions are tasks. Check for skills.
"I need more context first" Skill check comes BEFORE clarifying questions.
"Let me explore the codebase first" Skills tell you HOW to explore. Check first.
"I can check git/files quickly" Files lack conversation context. Check for skills.
"Let me gather information first" Skills tell you HOW to gather information.
"This doesn't need a formal skill" If a skill exists, use it.
"I remember this skill" Skills evolve. Read current version.
"This doesn't count as a task" Action = task. Check for skills.
"The skill is overkill" Simple things become complex. Use it.
"I'll just do this one thing first" Check BEFORE doing anything.
"This feels productive" Undisciplined action wastes time. Skills prevent this.
"I know what that means" Knowing the concept ≠ using the skill. Invoke it.

Platform Adaptation

You are running in Devin CLI. Invoke skills with /<skill-name>. If a skill is not installed or you are unsure which skill applies, invoke /tool-and-skill-discovery first, or read SKILL.md files from your configured skill directories:

  • Windows: %APPDATA%\devin\skills\
  • macOS/Linux: ~/.config/devin/skills/

User Instructions

User instructions (.devin/global_rules.md, .devin/rules/*.md, direct requests) take precedence over skills, which in turn override default behavior. Only skip skill workflows or instructions when your human partner has explicitly told you to.

Cross-skills

  • If the user uses AI-coding jargon loosely, invoke ai-coding-dictionary before routing to another skill.
  • If the conversation is long or context is tight, invoke context-window-hygiene.
  • If the task seems trivial or unusually hard, invoke effort-calibration to choose the right reasoning level.
  • If there are many MCP servers or tool definitions, invoke mcp-context-audit then mcp-lazy-enablement.
  • If the task touches API, DB, secrets, endpoints, or infrastructure, invoke security-audit.
  • If the task involves implementation or bugfix, invoke tdd.
  • If the project lacks pre-commit hooks, invoke setup-pre-commit via project-setup or the build flow.
  • If the task risks high token cost or long context, invoke cost-optimization or context-window-hygiene.
  • If the task could be destructive, invoke docker or run inside a dev container.
  • If MCP servers are present or being added, invoke mcp-context-audit and mcp-lazy-enablement.

04 同仓库更多 Skills

Leostruka
Leostruka/devin-bundle

montador-de-ideias

Use when assembling, expanding, or elevating a raw project idea or initial prompt into an ultra-detailed, first-principles dossier and compiled master prompt with journalistic OSINT market research, Tech Lead and Staff Architect justifications, atomic and modular hardening/optimization, and high-impact contact surfaces.

★ 0
Leostruka
Leostruka/devin-bundle

git-github-adaptive-engineering

Use when any task touches git history, GitHub issues/PRs/releases/CI, repo governance, or branch and merge decisions. Runs the Fase Zero situational-awareness battery, picks one of five delivery flows via the adaptive decision engine, and enforces commit/PR information-density standards. Orchestrates the gh, git-workflows, github-actions, pr, and debug/finish skills.

★ 0
Leostruka
Leostruka/devin-bundle

adaptive-agenda-calendar-routine-engine

Use when planning or executing work across hours, days, weeks, or sprints. Turns the calendar into a strict time-blocked agenda (HH:MM-HH:MM blocks carrying a routine profile, expected inputs, and a handoff output artifact), runs the 5-stage cognitive flow (Radar and Hunt -> Triage plus Steve Jobs conception -> workbench manifest -> >=32-cycle loop -> Close plus Open-Minded Scrum), and unfolds macro calendar milestones into micro agenda blocks through extensions/gcal/wrapper.py.

★ 0
Leostruka
Leostruka/devin-bundle

demo

Use when demonstrating a skill in a fixture project.

★ 0
Leostruka
Leostruka/devin-bundle

duplicate-skill

Use when testing duplicate skill name detection.

★ 0
Leostruka
Leostruka/devin-bundle

duplicate-skill

Use when testing duplicate skill name detection.

★ 0