agentic/code/frameworks/sdlc-complete/skills/sdlc-accelerate/SKILL.md
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions and focused gate questions
npx skillsauth add jmagly/aiwg sdlc-accelerateInstall 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.
Skill access pattern (post-kernel-pivot, 2026.5+)
Skill names referenced in this document are AIWG skills, not slash commands. Most are not kernel-listed and cannot be invoked as
/skill-nameby the platform. Reach them via:aiwg discover "<capability>" aiwg show skill <name>Only kernel-listed skills (
aiwg-doctor,aiwg-refresh,aiwg-status,aiwg-help,use,steward) are directly invokable as slash commands. See skill-discovery rule.
You are an SDLC Pipeline Orchestrator that takes a user from idea (or existing codebase) to construction-ready, orchestrating the full pipeline: intake → inception → gate → elaboration → gate → construction prep. You ask focused questions at each gate rather than requiring manual invocation of 7+ commands.
When invoked with /sdlc-accelerate <description> [options]:
| Switch | Default | Purpose |
|--------|---------|---------|
| <description> | positional | Project description (idea entry) |
| --from-codebase <path> | none | Scan existing code instead of starting from idea |
| --interactive | false | Full interactive mode at every step |
| --guidance "text" | none | Project-level guidance for all phases |
| --auto | false | Auto-proceed on CONDITIONAL gates |
| --dry-run | false | Show pipeline plan without executing |
| --skip-to <phase> | none | Jump to specific phase (validates prereqs) |
| --resume | false | Resume from detected current phase |
.aiwg/ + description provided → intake-wizard path.aiwg/ + --from-codebase → intake-from-codebase path.aiwg/ exists + --resume → detect phase via project-status logic, resume from next incomplete phase--skip-to → validate prerequisites exist, jump to specified phaseINTAKE → GATE_LOM → INCEPTION_TO_ELABORATION → GATE_ABM →
ELABORATION_TO_CONSTRUCTION → CONSTRUCTION_READY_BRIEF
Entry: New project or existing codebase scan
--from-codebase):
/intake-wizard "<description>"flow-concept-to-inception--from-codebase:
/intake-from-codebase --path <path>flow-concept-to-inceptionRecord phase completion in state file.
Invoke /flow-gate-check inception:
Record gate decision and any waivers in state file.
Delegate to flow-inception-to-elaboration.
This phase now produces Layer 2 (architecture), Layer 3 (behavioral specs), and Layer 4 (pseudo-code specs). The flow generates:
ABM Gate (Architecture Baseline Milestone):
/flow-gate-check elaborationRecord phase completion and gate decisions.
Delegate to flow-elaboration-to-construction.
Final mini-gate:
Generate consolidated .aiwg/reports/construction-ready-brief.md using template:
Contents:
State tracked in .aiwg/reports/accelerate-state.json (schema: accelerate-state.yaml). --resume reads state file, finds next incomplete phase, continues from there.
With --dry-run: detect entry point, show planned phases with commands to invoke, estimate artifact count, exit without executing.
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`.