Chalk Labs
Need help deploying 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. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sd0xdev-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
Use cases: design, frontend, data, writing
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/architecture
Tools it pre-approves 10
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Grep,Glob,Bash(git:*),Bash(node:*),Bash(bash:*),Write,Agent,Skill,AskUserQuestion
What's inside
- Skill name
architecture- Description
- Architecture design and documentation. Produces 3-architecture.md with component diagrams, data flow, integration points, and architecture decisions. Reads existing tech-spec as input. Use when: designing system architecture, documenting component interactions, creating architecture docs, producing 3-architecture.md. Not for: tech spec writing (use tech-spec), code implementation (use feature-dev), architecture consulting only (use codex-architect).
- License
- MIT
- Allowed tools
- Read,, Grep,, Glob,, Bash(git:*),, Bash(node:*),, Bash(bash:*),, Write,, Agent,, Skill,, AskUserQuestion
- Instructions
- 306 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Agent Skills spec issues
- files: referenced but missing: scripts/lib/doc-classifier.js
Files (3)
- SKILL.md
- codex-prompt.md · references/
- template.md · references/
SKILL.md (first lines)
# Architecture Design Skill
## Trigger
- Keywords: architecture, architecture design, architecture doc, component diagram, 3-architecture, system design, document architecture
## When NOT to Use
- Tech spec writing (use `/tech-spec`)
- Code implementation (use `/feature-dev`)
- Architecture consulting only (use `/codex-architect`)
- Implementation roadmap (use `/deep-analyze`)
## Usage
```bash
/architecture # Auto-detect feature, create/update
/architecture <feature-keyword> # Specify feature
/architecture --skip-debate # Skip Phase 3 adversarial debate
```
## Workflow
```mermaid
sequenceDiagram
participant U as User
participant C as Claude
participant E as Explore Agent
participant X as Codex
participant D as Architecture Designer
participant B as /codex-brainstorm
C->>C: Phase 0: Context Resolution
par Phase 1: Research
C->>E: Track A: Code pattern analysis (background)
C->>C: Track B: Read tech-spec (inline)
end
E-->>C: Component list + dependencies
C->>X: Track C: Architecture advice
X-->>C: Independent recommendations
C->>D: Phase 2: Architecture Design
D-->>C: Component + flow + decisions
C->>B: Phase 3: Verification (debate)
B-->>C: Equilibrium conclusion
C->>C: Phase 4: Write 3-architecture.md
C->>U: Auto-trigger /codex-review-doc
```
## Phase 0: Context Resolution
Detect the target feature using the 5-level cascade.
See `@skills/create-request/references/feature-context-resolution.md` for the full algorithm.
```bash
# The wrapper, not the CLI directly: it owns the failure payload, so the full shape with
# `scan_error: true` arrives however the CLI fails — nonzero exit, signal, partial write, or a
# payload that is not the agreed shape. (Not when `node` itself is unavailable: nothing running
# under node survives that.) `|| echo '{}'` would produce a payload the gate cannot see as failure.
node scripts/resolve-feature.js
```
> **`scan_error` gate.** Gate on **`scan_error !== false`**, not on `scan_error === true`. When it
> is not exactly `false` the four source sets are **unknown, not empty** — the corpus could not be
> enumerated (unreadable directory, broken taxonomy, no repository), *or* the resolver never ran
> and a shell fallback supplied a payload with no such field at all. `{}` is the shape that made
> the stricter test useless: it has no `scan_error`, so `=== true` is false and the gate passes a
> payload that contains nothing. Do not proceed as though the feature has no authority documents —
> report and take the ⚠️ Need Human exit. A `key` may still be present, so a non-null `key` is not
> evidence the sets are complete.
| State | Mode |
|-------|------|
| `3-architecture.md` exists | Update (incremental) |
| `3-architecture.md` absent + a tech spec resolves | Create (tech-spec-informed) |
| `3-architecture.md` absent + no tech spec resolves | Create (code-only research) |
| Feature not resolved | Gate: Need Human |
"A tech spec resolves" means `design_records` holds an entry of `type: tech-spec` — the same
resolution Track B uses.
**`design_records` is an array, and more than one entry can be a tech spec**, so "the entry" needs a
rule rather than an assumption. `docs/features/auto-loop-evolution/` is the live case: a split spec
contributes `2-tech-spec/2-tech-spec.md` **and** its sub-document `2-tech-spec/1-phase-d-hook-hardening.md`,
both `type: tech-spec` design records. Select in this order, and stop at the first that answers:
**Filter first, then choose — every later rule reads the filtered list, never the whole set.**
Candidates are the `design_records` entries whose `type` is `tech-spec`; a requirements or
architecture record is not a candidate at any step, and a rule phrased over "entries" rather than
over candidates will select one. `docs/features/codex-review-spec/` and
`docs/features/harness-engineering-rebrand/` are the live proof: neither has a tech-spec design
record, each has exactly one canonical requirements record, and a canonicality test applied to the
unfiltered set picks it.
| # | Candidates (`design_records` where `type: tech-spec`) | Result |
|---|---------------------------------------------------|--------|
| 1 | none | **No tech spec resolves** — the ordinary code-only row of the table above. Not an exit: a feature that has not been specced is a normal state, and Track C is given `(none — do not read a spec)` |
| 2 | exactly one | that one |
| 3 | two or more, exactly one with `is_canonical: true` | that one — a split spec's main file keeps the canonical filename, which is what makes it the main file |
| 4 | two or more, and none or several canonical | **Gate: Need Human**, naming the candidates |
Rows 1 and 4 are different answers and must not be collapsed: "there is no spec" is a fact the skill
acts on, "there are two and I cannot tell which" is an ambiguity it must not resolve by picking. **The set decides, and the set also names the file.** `canonical_docs` is
role-blind: it selects the tech spec from `doc_inventory` whatever role that document resolves to,
so a spec that has declared itself `History record` or `Work record` is still non-null there while
being absent from `design_records`. Reading the alias as evidence of design authority is exactly the
confusion the source sets replace — and it is no better as a *path* selector: it is chosen across
the whole inventory by type and canonicality, so a historical canonical `2-tech-spec.md` beside a
design-record variant `2-tech-spec-v2.md` makes the set and the alias name different files. Take
both the decision and the path from the `design_records` entry's own `file`; do not rejoin through
the alias for either. Testing for the literal filename
`2-tech-spec.md` would read a split spec (`2-tech-spec/2-tech-spec.md`) or a variant
(`2-tech-spec-v2.md`) as "no tech spec" and silently drop to code-only mode.
### Scope Gate
For small features (tech-spec WBS has only 1 task, or no tech-spec and < 3 related files), suggest keeping architecture in tech-spec Section 3 instead of creating a separate document. Use AskUserQuestion to confirm.
## Phase 1: Architecture Research (parallel)From sd0xdev/sd0x-harness, MIT.
More from sd0xdev/sd0x-harness
- 0.713score
debug
sd0xdev
Interactive debugging workflow with hypothesis-driven probe loop.
SkillAFreshness: A★ 194Claude Code - 0.713score
contract-decode
sd0xdev
EVM contract error and calldata decoder.
SkillAFreshness: A★ 194Claude Code - 0.713score
best-practices
sd0xdev
Industry best practices conformance audit with mandatory adversarial debate.
SkillAFreshness: A★ 194Claude Code - 0.713score
codex-explain
sd0xdev
Explain complex code via Codex exec.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
ask
sd0xdev
Context-aware Q&A with auto context gathering.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
codex-cli-review
sd0xdev
Code review via Codex CLI with full disk access.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
claude-health
sd0xdev
Claude Code config health check + plugin sync.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
code-explore
sd0xdev
Pure Claude code investigation.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
code-investigate
sd0xdev
Dual-perspective code investigation.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
codex-architect
sd0xdev
Codex architecture consulting.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
codex-brainstorm
sd0xdev
Adversarial brainstorming via Claude+Codex debate.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
deep-explore
sd0xdev
Multi-wave parallel code exploration orchestrator.
SkillAFreshness: A★ 194Claude Code +9
Signals
- Stars
- 194
- Forks
- 26
- Open issues
- 5
- Last commit (this folder)
- Sep 5, 2026 (1 month ago)
- Last release
- Oct 6, 2026 (24 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sd0xdev/sd0x-harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sd0xdev
- 0.713score
code-investigate
sd0xdev
Dual-perspective code investigation.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
claude-health
sd0xdev
Claude Code config health check + plugin sync.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
best-practices
sd0xdev
Industry best practices conformance audit with mandatory adversarial debate.
SkillAFreshness: A★ 194Claude Code - 0.713score
code-explore
sd0xdev
Pure Claude code investigation.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
ask
sd0xdev
Context-aware Q&A with auto context gathering.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
codex-architect
sd0xdev
Codex architecture consulting.
SkillAFreshness: A★ 194Claude 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 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
architecture skill. Agent Mart. https://agentmart.dev/skills/sd0xdev-architecture (last updated 2026-10-24)