mcpField
A
architect

architect

github.com/akshay-diwadkarDevelopment173 installsUpdated today
Repository

About architect

architect is a repository skill for deciding structural direction and recording architecture, without editing implementation files. It guides discovery, evidence gathering, and sealing a concise architecture record.

Key features

  1. 01Opportunity discovery before target selection
  2. 02Architecture protocol and evidence review
  3. 03Structural decision and consequence recording
  4. 04Sealed architecture record in repository

Use cases

  1. 01Assessing whether a proposed change needs structural redesign
  2. 02Recording ownership boundaries and architectural constraints
  3. 03Capturing unknowns and evidence before blueprint planning

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/akshay-diwadkar/first-four-hours --skill architect

After installing, type/architectin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

README.md
skill-protocol.json
agents/
openai.yaml
references/
architecture-protocol.md
architecture-template.md
calibration-examples.md
delegation-protocol.md
opportunity-discovery.md
structural-techniques.md
worked-examples.md
scripts/
_diagnostic_contract.py
_skill_protocol_runtime.py
architecture_contract.py
architecture_handoff.py
architecture_workspace.py
cli.py
seal_assessment.py

Details

From the project README

Architect

Authority

Decide architecture. If no target is supplied, run Opportunity Discovery before selecting target, no-design-change, or blocker. Seal ignored .first-four-hours/architectures/<slug>/architecture.md for blueprint; do not edit implementation files.

Stop at architecture. Never classify implementation tier, perform a full propagation sweep, prescribe file-level edits, write test or execution blueprints, order migrations or rollout, or attack an implementation. Those responsibilities belong to blueprint. Paths and optional views are evidence bearings, not edit instructions.

Workflow

  1. Follow Architecture Protocol. Consult reason before committing to an approach, after a failure or direction change, and before sealing. Load Structural Techniques only where the protocol or discovery points to it.
  2. Use Bounded Delegation Protocol only for optional evidence workers or earned specialist review.
  3. Draft from the Handoff Template.
  4. Use Worked Example only for optional alternatives, user policy, or view calibration, and Calibration Examples before framing a target inside one module or class or selecting any structure other than no-design-change.
  5. Seal once:
python /absolute/skill-root/scripts/cli.py --repo-root /absolute/repo \
  --input draft=/absolute/architecture-draft.md \
  --input slug=<architecture-slug> --format json run

Persist settled structural truth: pressure or no-change outcome, owner/boundary, constraints, selected architecture, consequences, evidence, trust-relevant unknowns, and any user-owned policy.

Completion

Complete only when the command returns status: complete with result.path at .first-four-hours/architectures/<slug>/architecture.md; report result.git_ignored. If sealing fails, repair the named draft or workspace conflict and rerun. If evidence changed, refresh and seal against the new snapshot. Final and stop reports trace reason checkpoints per its Checkpoint trace. End with one optional next step fitting this outcome: a fenced, self-contained prompt naming any repository, issue, PR, or artifact it needs, or say none is needed. Only a "yes" starts it, via any skill it names, but the user runs a charter, diagnose, or ticket step as its /<skill> command.

Comments

Markdown supported