Chalk Labs
Need help deploying specialist-architecture?
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/tiagomoscoso-specialist-architecture
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
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. Checked Oct 25, 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/specialist-architecture
What's inside
- Skill name
specialist-architecture- Description
- Boundaries, ownership, and reuse. Use when a change adds a module, a dependency, or a new abstraction, or touches more than one subsystem.
- License
- MIT
- Compatibility
- Requires forgespec CLI.
- Metadata
- author: forgespec · version: 1.0 · generatedBy: 0.1.0
- Instructions
- 16 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "specialist-architecture" does not match folder "architecture"
Files (1)
- SKILL.md
SKILL.md (first lines)
# Architecture specialist Boundaries, ownership, and reuse. Use when a change adds a module, a dependency, or a new abstraction, or touches more than one subsystem. - Identify existing modules/abstractions that already solve part of the problem before proposing a new one. - Name the seams and ownership boundaries: which module owns this behavior, and does that still hold after the change. - Trace dependency direction; flag a new dependency that points the wrong way (e.g. domain importing infrastructure). - Assess cohesion/coupling: does the change strengthen one responsibility or smear it across modules. - Check fit with existing extension points before adding a new one. - Consider deployment/runtime implications (new process, new startup ordering, new config surface). - Challenge architecture that does not fit the repository, even if it is individually reasonable. - Record decisions and rejected alternatives inside change.md Decisions (### DEC-...), not a separate design.md. This specialist returns reasoning and findings for the parent workflow (forge-explore or forge-propose) to weigh and merge into change.md. It never creates its own standalone document.
From TiagoMoscoso/ForgeSpec, MIT.
More from TiagoMoscoso/ForgeSpec
- 0.523score
forge-propose
forgespec
Write and seal a ForgeSpec change.md contract.
SkillBFreshness: BClaude Code +9 - 0.518score
forge-explore
forgespec
Explore the repository and problem without implementing.
SkillBFreshness: BClaude Code +9 - 0.518score
forge-forge
forgespec
Compile a sealed change.md into plan.yaml via the ForgeSpec CLI.
SkillBFreshness: BClaude Code +9 - 0.518score
forge-archive
forgespec
Archive a ForgeSpec task through the fail-closed evidence gate, then close the change when ready.
SkillBFreshness: BClaude Code +9 - 0.518score
forge-exec
forgespec
Execute exactly one ForgeSpec task with CLI preflight, validators, and evidence.
SkillBFreshness: BClaude Code +9 - 0.515score
specialist-migration
forgespec
Forward/backward compatibility of persisted state and deployments.
SkillBFreshness: BClaude Code +9 - 0.515score
specialist-observability
forgespec
What must be visible to prove the change worked and to diagnose it when it does not.
SkillBFreshness: BClaude Code +9 - 0.515score
specialist-security
forgespec
Trust boundaries and sensitive data.
SkillBFreshness: BClaude Code +9 - 0.515score
specialist-concurrency
forgespec
Shared state and parallel execution.
SkillBFreshness: BClaude Code +9 - 0.515score
specialist-frontend
forgespec
User-facing states and interaction.
SkillBFreshness: BClaude Code +9 - 0.514score
specialist-data
forgespec
Schema, ownership, and consistency.
SkillBFreshness: BClaude Code +9 - 0.514score
specialist-api
forgespec
External contracts.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 11, 2026 (1 month ago)
- Last release
- Sep 11, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0
- License
- MIT
- Repository
- github.com/TiagoMoscoso/ForgeSpec
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from forgespec
- 0.523score
forge-propose
forgespec
Write and seal a ForgeSpec change.md contract.
SkillBFreshness: BClaude Code +9 - 0.518score
forge-explore
forgespec
Explore the repository and problem without implementing.
SkillBFreshness: BClaude Code +9 - 0.518score
forge-archive
forgespec
Archive a ForgeSpec task through the fail-closed evidence gate, then close the change when ready.
SkillBFreshness: BClaude Code +9 - 0.518score
forge-exec
forgespec
Execute exactly one ForgeSpec task with CLI preflight, validators, and evidence.
SkillBFreshness: BClaude Code +9 - 0.518score
forge-forge
forgespec
Compile a sealed change.md into plan.yaml via the ForgeSpec CLI.
SkillBFreshness: BClaude Code +9 - 0.515score
specialist-security
forgespec
Trust boundaries and sensitive data.
SkillBFreshness: BClaude 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 specialist-architecture 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
specialist-architecture skill. Agent Mart. https://agentmart.dev/skills/tiagomoscoso-specialist-architecture (last updated 2026-10-24)