copilot-agents-dojo

In the author's own words, from each skill's SKILL.md — showing the first 29 of 34 files.

• building-mcp-servers

  Authors an MCP server with the official SDK and gates.

  optional-skills/building-mcp-servers/SKILL.md on GitHub (opens in a new tab)

• calling-mcp-tools-via-subprocess

  Bypasses a flaky MCP broker by spawning the server directly.

  optional-skills/calling-mcp-tools-via-subprocess/SKILL.md on GitHub (opens in a new tab)

• using-mcp

  Wires MCP servers into a Copilot client and verifies them.

  optional-skills/using-mcp/SKILL.md on GitHub (opens in a new tab)

• writing-skills

  Authors new SKILL.md files that conform to the dojo spec.

  optional-skills/writing-skills/SKILL.md on GitHub (opens in a new tab)

• architecture-sketching

  Defines types and boundaries before implementation.

  skills/architecture-sketching/SKILL.md on GitHub (opens in a new tab)

• autonomous-bug-fix

  Reproduces, diagnoses, fixes, and verifies bugs unaided.

  skills/autonomous-bug-fix/SKILL.md on GitHub (opens in a new tab)

• behavioral-foundation

  Surfaces the dojo's non-negotiable prime directives.

  skills/behavioral-foundation/SKILL.md on GitHub (opens in a new tab)

• brainstorming

  Refines rough ideas into approved designs before code.

  skills/brainstorming/SKILL.md on GitHub (opens in a new tab)

• code-review

  Reviews diffs by severity to produce actionable feedback.

  skills/code-review/SKILL.md on GitHub (opens in a new tab)

• codebase-onboarding

  Maps an unfamiliar repo before touching its code.

  skills/codebase-onboarding/SKILL.md on GitHub (opens in a new tab)

• debugging

  Systematic root-cause investigation for hard bugs.

  skills/debugging/SKILL.md on GitHub (opens in a new tab)

• demand-elegance

  Challenges hacky fixes on non-trivial changes.

  skills/demand-elegance/SKILL.md on GitHub (opens in a new tab)

• derive-nfr-from-driver

  Derives measurable NFRs from a parent business driver.

  skills/derive-nfr-from-driver/SKILL.md on GitHub (opens in a new tab)

• derive-security-from-risk

  Derives security requirements from a named threat.

  skills/derive-security-from-risk/SKILL.md on GitHub (opens in a new tab)

• dispatching-parallel-agents

  Runs independent subtasks concurrently via sub-agents.

  skills/dispatching-parallel-agents/SKILL.md on GitHub (opens in a new tab)

• durable-work

  Picks the board over sub-agents for cross-turn work.

  skills/durable-work/SKILL.md on GitHub (opens in a new tab)

• executing-plans

  Executes approved plans one task at a time, verified.

  skills/executing-plans/SKILL.md on GitHub (opens in a new tab)

• finishing-a-development-branch

  Verifies, summarises, and closes a development branch.

  skills/finishing-a-development-branch/SKILL.md on GitHub (opens in a new tab)

• plan-before-code

  Plans multi-step work before writing code.

  skills/plan-before-code/SKILL.md on GitHub (opens in a new tab)

• pr-workflow

  Prepares branches and PRs for clean, reviewable merges.

  skills/pr-workflow/SKILL.md on GitHub (opens in a new tab)

• receiving-code-review

  Processes review feedback until the change is approved.

  skills/receiving-code-review/SKILL.md on GitHub (opens in a new tab)

• refactoring

  Safe, test-backed code restructuring in small steps.

  skills/refactoring/SKILL.md on GitHub (opens in a new tab)

• requesting-code-review

  Self-reviews work against the plan before sign-off.

  skills/requesting-code-review/SKILL.md on GitHub (opens in a new tab)

• requirements-elicitation

  Turns vague intent into testable requirements.

  skills/requirements-elicitation/SKILL.md on GitHub (opens in a new tab)

• safety-guardrails

  Flags risky shell commands and unsafe tree ops.

  skills/safety-guardrails/SKILL.md on GitHub (opens in a new tab)

• security-audit

  Detects high-confidence security risks in code.

  skills/security-audit/SKILL.md on GitHub (opens in a new tab)

• self-improvement

  Captures lessons and promotes recurring patterns.

  skills/self-improvement/SKILL.md on GitHub (opens in a new tab)

• subagent-strategy

  Delegates research and parallel work to sub-agents.

  skills/subagent-strategy/SKILL.md on GitHub (opens in a new tab)

• test-writing

  Writes meaningful tests that actually catch bugs.

  skills/test-writing/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• rsc-harnessby ericrisco Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that give… 477 stars · 30 skills
• codex-settingsby feiskyer Curated skills, profiles, and config templates that supercharge Codex CLI — multi-model, deep research, image gen & browser automation. 248 stars · 12 skills
• Nexus-skillsby Haaaiawd AI-native codebase intelligence skills — generate persistent .nexus-map/ knowledge bases and instantly query file structure, dependency gra… 167 stars · 2 skills
• OpenMontageby calesthio World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge… 76.5k stars · 30 skills
• agentsby wshobson Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi 42.2k stars · 30 skills
• superpowers-zhby jnMetaCode 🦸 AI 编程超能力 · 中文增强版 — superpowers（250k+ ⭐）完整汉化 + 4 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemi… 8.5k stars · 21 skills