plugins/codex-sdlc/skills/tot-decide/SKILL.md
Evaluate architectural decisions using Tree of Thoughts exploration
npx skillsauth add jmagly/aiwg tot-decideInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Evaluate architectural decisions by generating and scoring k alternatives using the ToT methodology.
When invoked, perform structured Tree of Thoughts exploration for architecture decisions:
Parse Decision Context
.aiwg/requirements/nfr-modules/.aiwg/architecture/Load ToT Protocol
Define Evaluation Criteria
Generate Alternatives (k=3 default)
Score and Compare
Generate ADR
Output
.aiwg/architecture/[decision-context] - Description of the architectural decision (required)--alternatives [k] - Number of alternatives to generate (default: 3, max: 7)--depth [levels] - Depth of exploration per alternative (default: 2)--output [path] - Custom output path for ADR (default: .aiwg/architecture/)--criteria [list] - Override criteria (comma-separated)--quick - Skip detailed analysis, produce summary matrix only/tot-decide "Select authentication approach for multi-tenant SaaS platform"
Output:
Tree of Thoughts Decision Analysis
===================================
Decision: Authentication approach for multi-tenant SaaS
Criteria (from NFRs):
Security [30%] - Multi-tenant isolation required
Scalability [25%] - 10K+ tenants expected
Cost [20%] - Startup budget constraints
Dev Speed [15%] - MVP in 3 months
Maintenance [10%] - Small ops team
Alternatives Generated:
A: OAuth2 + OIDC with tenant-scoped JWTs
B: Session-based with Redis cluster per tenant
C: API key + HMAC with per-request validation
Scoring Matrix:
| Criterion | Wt | A | B | C |
|---------------|-----|------|------|------|
| Security | 30% | 5 | 4 | 3 |
| Scalability | 25% | 5 | 3 | 4 |
| Cost | 20% | 3 | 2 | 5 |
| Dev Speed | 15% | 3 | 4 | 5 |
| Maintenance | 10% | 4 | 2 | 4 |
| Weighted | | 4.15 | 3.10 | 4.00 |
Recommendation: Option A (OAuth2 + OIDC)
Confidence: HIGH (gap > 0.5 from runner-up)
Trade-off accepted: Higher initial dev cost for superior security/scale
ADR saved: .aiwg/architecture/adr-auth-approach.md
/tot-decide "Database for event sourcing" --alternatives 4 --quick
/tot-decide "Microservices vs modular monolith" --depth 3 --criteria "scalability,team-autonomy,ops-complexity,latency"
data-ai
Report which research-corpus radar sidecars are overdue for refresh. Computes staleness (days since last refresh vs the cadence window) for every radar, sorted most-overdue-first. Runs via `aiwg corpus radar-status`.
data-ai
Aggregate research-corpus radar sidecars into a corpus or per-cluster freshness report — totals, overdue count, per-cluster / per-GRADE / per-trajectory breakdowns, an overdue table, and per-radar rationale snippets. Runs via `aiwg corpus radar-report`.
testing
Scaffold radar/freshness sidecars for research-corpus REFs. Pulls title/authors from the citation sidecar and GRADE from the analysis doc, defaults the refresh cadence from GRADE and the cluster from a corpus-local map, and stamps documentation/radar/REF-XXX-radar.md. Runs via `aiwg corpus radar-init`.
data-ai
Compute an entity's publication trajectory — per-year paper counts, topic drift, hot-streak detection (≥3 consecutive A-grade years), and career phase. Runs via `aiwg corpus profile-temporal`.