agent-design
Use when designing Copilot agents, skills, or instruction assets for a shared customization repo.
Skill by ivegamsft
Chalk Labs
Need help deploying agent-design?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ivegamsft-agent-design
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, devops, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-design
What's inside
- Skill name
agent-design- Description
- Use when designing Copilot agents, skills, or instruction assets for a shared customization repo. USE FOR: design a new Copilot agent, scaffold a skill folder, create an instruction file, choose agent vs skill vs instruction, author agent frontmatter and conventions. DO NOT USE FOR: implementing product features, troubleshooting runtime incidents, deploying infrastructure.
- License
- MIT
- Metadata
- domain: agent-development · category: agent-development · maturity: production
- Instructions
- 23 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- compatibility: must be text of at most 500 characters
- allowed-tools: must be a space-separated string
Files (5)
- SKILL.md
- agent-template.md
- eval.yaml
- instruction-template.md
- skill-template.md
SKILL.md (first lines)
# Agent Design Skill Design, scaffold, or author Copilot agent definitions, skill folders, and instruction files for a shared customization repository. ## Template Index | Template | Purpose | Path | |---|---|---| | Agent definition | Scaffold a new `.agent.md` with frontmatter and standard sections | `agent-template.md` | | Skill folder | Scaffold a new skill with `SKILL.md` and supporting structure | `skill-template.md` | | Instruction file | Scaffold a reusable instruction file | `instruction-template.md` | ## Conventions & Guardrails - Agent filenames: `<kebab-case-name>.agent.md`; skill folders: `skills/<name>/SKILL.md`; instruction files: `instructions/<name>.instructions.md` - All files use YAML frontmatter fenced by `---`; descriptions include trigger phrases for discovery - Do not create an agent when a skill or instruction would suffice; check inventory for duplicates - Keep each primitive scoped to a single responsibility; validate frontmatter with a YAML linter ## Agent Pairing Use with `agent-designer` agent (primary consumer). `prompt-engineer` agent optimizes instruction text.
From ivegamsft/basecoat, MIT.
More from ivegamsft/basecoat
- 0.606score
api-security
ivegamsft
Use when securing REST or GraphQL APIs against common auth, authorization, validation, and abuse risks.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
app-inventory
ivegamsft
Use when inventorying legacy applications to capture dependencies, service bindings, framework versions, and migration complexity.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
azure-devops-rest
ivegamsft
Use when building automations that call Azure DevOps REST APIs for work items, pipelines, repos, and artifacts.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
agentic-sdlc-autonomy
ivegamsft
Use when asked to audit, measure, implement, or operate rules-based human-in-the-loop autonomy for agent-operated repositories.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
azure-linux-app-service
ivegamsft
Use when deploying or operating Python, Ruby, or Node.js apps on Azure App Service Linux.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
agentic-cost-audit
ivegamsft
Audits agentic CI workflows for model and token waste and reports ranked remediations.
SkillAFreshness: A★ 4Claude Code +9 - 0.601score
azure-policy-audit
ivegamsft
Use when reviewing Azure Policy definitions, initiatives, exemptions, remediation tasks, or compliance reporting.
SkillAFreshness: A★ 4Claude Code +9 - 0.601score
backend-audit
ivegamsft
Audits generated or implemented backend code output.
SkillAFreshness: A★ 4Claude Code +9 - 0.601score
agentops-audit
ivegamsft
Audits and improves agent/skill specs with a scored rubric and routing rationale.
SkillAFreshness: A★ 4Claude Code +9 - 0.601score
azure-identity-audit
ivegamsft
Use when reviewing Azure identity and access designs across RBAC, managed identities, Entra ID, and federation.
SkillAFreshness: A★ 4Claude Code +9 - 0.601score
azure-waf-review
ivegamsft
Use when assessing an Azure workload against the Well-Architected Framework and prioritizing remediation.
SkillAFreshness: A★ 4Claude Code +9 - 0.601score
api-audit
ivegamsft
Audits API endpoint designs, contracts, versioning strategies, and error handling.
SkillAFreshness: A★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 1
- Open issues
- 10
- Last commit (this folder)
- Jun 26, 2026 (4 months ago)
- Last release
- Oct 11, 2026 (20 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ivegamsft/basecoat
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ivegamsft
- 0.606score
azure-devops-rest
ivegamsft
Use when building automations that call Azure DevOps REST APIs for work items, pipelines, repos, and artifacts.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
agentic-sdlc-autonomy
ivegamsft
Use when asked to audit, measure, implement, or operate rules-based human-in-the-loop autonomy for agent-operated repositories.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
agentic-cost-audit
ivegamsft
Audits agentic CI workflows for model and token waste and reports ranked remediations.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
api-security
ivegamsft
Use when securing REST or GraphQL APIs against common auth, authorization, validation, and abuse risks.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
app-inventory
ivegamsft
Use when inventorying legacy applications to capture dependencies, service bindings, framework versions, and migration complexity.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
azure-linux-app-service
ivegamsft
Use when deploying or operating Python, Ruby, or Node.js apps on Azure App Service Linux.
SkillAFreshness: A★ 4Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get agent-design running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
agent-design skill. Agent Mart. https://agentmart.dev/skills/ivegamsft-agent-design (last updated 2026-10-24)