agentleFS
QuirkybrainQuirkybrain/claude-code-swe-framework/.claude/skills/architecture-decision/SKILL.md

architecture-decision

Skill1 starsChanged 54 days agoMITView on GitHub

Evaluate significant technology or architecture alternatives and record an Architecture Decision Record. Use when a choice affects system structure, Contracts, data, security, deployment, compatibility, cost, or long-term evolution.

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use team-level, team-narrative and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 10 projects that use this

  • CoralGameSkill

    team-narrative

    Orchestrate the narrative team: coordinates narrative-director, writer, world-builder, and level-designer to create cohesive story content, world lore, and narrative-driven level design.

    Also in 10 projects that use this

  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 9 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 9 projects that use this

  • Microsoft AzureSkill

    component-release

    Prepares a verifiable Agent Landing Zone UI release. Use for release branches, VERSION, changelog entries, tags, release notes, and compatibility evidence; never publish without explicit human approval.

    Also in 4 projects that use this

  • +7 more from lilangMax

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 30 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run for major architecture/technology choices, meaningful deviations from existing architecture, or when an old decision must be superseded.

    line 14
  2. Distinctive:

    If authority belongs to the user, invoke Clarification Gate with bounded options before selecting.

    line 34
  3. Distinctive:

    Do not create an ADR for trivial, local, easily reversible implementation choices unless required by policy.

    line 42
  4. Distinctive:

    Do not choose technology from familiarity alone.

    line 43
  5. Distinctive:

    Only one option is presented without evidence that alternatives are infeasible.

    line 62
  6. Very specific:

    Use Clarification Gate for user-owned choices.

    line 68
  7. Very specific:

    Stop with an accepted/rejected/superseded ADR and impact plan, or at USER_DECISION_REQUIRED/BLOCKED.

    line 72

“Common” is measured: kept by at least 6 in 10 of the 30 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Architecture Decision

Purpose

Make consequential technical choices explicit, evidence-based, traceable, and reversible where possible through an ADR.

Trigger

Run for major architecture/technology choices, meaningful deviations from existing architecture, or when an old decision must be superseded.

Inputs

  • Decision question, scope, owner, and urgency.
  • Validated Requirements, quality attributes, Project Constraints, risks, existing architecture, and target.
  • Candidate options with operational, security, data, cost, compatibility, and maintenance implications.

Prerequisites

  • Confirm the issue is architectural rather than an implementation detail.
  • Identify who has authority when the decision embodies product preference, budget, organizational policy, or risk acceptance.

Procedure

  1. Define the ADR Context, forces, constraints, affected scope, and decision deadline.
  2. Establish evaluation criteria tied to Requirements and quality attributes.
  3. Identify viable Options, including retaining the current design when legitimate.
  4. Compare options using evidence, tradeoffs, risks, reversibility, migration, and total lifecycle cost.
  5. Reject options only with recorded rationale.
  6. If authority belongs to the user, invoke Clarification Gate with bounded options before selecting.
  7. Record the Decision and why it best satisfies the criteria.
  8. Record positive/negative Consequences, constraints, follow-up work, and rollback/supersession conditions.
  9. Link Affected Artifacts and invoke Change Impact for existing downstream work.
  10. Validate ADR consistency with Requirements, Project Constraints, and related ADRs.

Decision Rules

  • Do not create an ADR for trivial, local, easily reversible implementation choices unless required by policy.
  • Do not choose technology from familiarity alone.
  • Major product behavior, cost, data ownership, security posture, deployment model, or organizational commitment requires user authority.
  • A superseding ADR keeps the old decision as history and links both revisions.
  • An undecided ADR is PROPOSED, not falsely ACCEPTED.

Outputs

An ADR containing:

  • Context
  • Options and evaluation evidence
  • Decision and status
  • Consequences and risks
  • Constraints and assumptions
  • Affected Artifacts, dependencies, traceability, and follow-up validation

Failure Cases

  • Requirements or quality attributes are too ambiguous to compare options.
  • Only one option is presented without evidence that alternatives are infeasible.
  • Required cost/security/deployment information is unavailable.
  • The actor lacks decision authority.

Escalation

Use Clarification Gate for user-owned choices. Escalate missing domain/security/data evidence to the appropriate specialist. Increase Workflow Level when the decision's possible impact exceeds current rigor.

Stop Conditions

Stop with an accepted/rejected/superseded ADR and impact plan, or at USER_DECISION_REQUIRED/BLOCKED. Do not implement the decision in this Skill.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.