Sdlc Skill
[!IMPORTANT] Route a task to the next synced SDLC workflow based on current artifacts and repo state.
Optional args: slug=, ticket=<id/url>, mode=interactive|autonomous|channel, channel=, auto_continue=true|false, profile=business|hybrid|technical.
Instructions
When the user asks to perform this workflow, execute the following steps:
SDLC Router Workflow
Goal: Select the next native workflow without loading every workflow body, while preserving a traceable BA -> PM -> IT Department handoff for offshore delivery.
Steps
- Inspect state:
- User request & sizing: infer
operator_profile(business | hybrid | technical) percommon-operator-profile(carried in every Handoff Payload) and SNC tier percommon-task-complexity-routingor the scoutSNC:line (label as inference until scouted). - Search for the requested task's linked brief/ticket using its stable slug; do not select an unrelated newest document or infer task authority/approval from
git status. If no matching approved task record exists, identify the missing authority/input and route to the appropriate intake. Record the authoritative work-item reference and its approved revision once; carrydelivery_mode(brief | standard | extended), owner, approval reference, and evidence-lane refs instead of letting later stages re-infer authority. Slug = lowercase kebab-case, minted once atbrainstorm-feature, reused verbatim downstream; never re-derived. - If multiple candidates exist, list them and ask whether to focus, consolidate, or sequence.
- Artifacts & repo/system state (baseline:
common-software-requirements/references/requirements-standards-baseline.md, ships with the skill): existing ticket, BRD-lite brief, PRD, SRS/FRS design, implementation plan, task list, walkthrough, UAT signoff, deployment report, release notes, retro; configured system context (Jira, ADO, Zephyr, or other MCP), changed files, and current test status. - Offshore delivery context: business owner, product owner, implementation owners, QA owner, timezone/cadence constraints, environments, release window, and dependency teams
- Requirement trace health:
BRD-OBJ-* -> REQ-* -> AC-* -> SRS-* -> test evidence
- User request & sizing: infer
- Choose next workflow (apply tie-break order):
- Explicit operator request or latest approved/recommended stage, unless a safety prerequisite blocks affected scope.
- Fresh task-linked active harm gives
incident-hotfixpolicy ownership before any ordinary mode execution, even for an explicit diagnose or recover request and even if product learning is stale; do not load an unrelated incident as task context. - Earliest missing required decision or task-linked authority/input—not a missing filename—except sufficiently specified low-risk maintenance with approved evidence; reused approved context skips rediscovery.
- Cross-cutting audits only on request or as a pre-release gate.
- Unclear idea, missing business case, owner, or measurable value (Why lane), or unclear technical direction without BRD/PRD (Direction lane; exempts routine low-risk maintenance) ->
brainstorm-feature - Task-linked unmet customer-evidence/problem/market gap that the decision depends on ->
discover-product(when selected/installed; elsebrainstorm-featurewith capability gap) - Material unresolved critical value hypothesis or assumption needing empirical test ->
validate-product(when selected/installed; elseplan-featurewith capability gap) - BRD-lite exists or business direction clear but product scope, priorities, ACs, rollout, delivery plan unclear ->
plan-feature(explicitly loadsproduct-management/product-requirementsand on-demandreferences/requirements-modeling.md) - Scale, topology, capacity, or store choice unsettled, or existing system needs architecture audit ->
system-design-session - PRD exists but technical behavior/contracts unclear (SRS/FRS / How), auth/trust-boundary/sensitive validation needed, or architecture/compliance/agent-runtime safety needs deeper validation ->
design-solution - BRD-lite, PRD, or SRS/FRS exists but readiness/change impact unclear ->
implementation-readiness - Approved plan with trace and testable ACs, or approved low-risk maintenance contract, needs code ->
implement-feature - Cloud or hosting setup, deployment, live verification, monitoring inspection, diagnosis, or authorized recovery ->
deploy-releasewith an explicitoperation=setup | deploy | verify | monitor | diagnose | recover(omitted meansdeploy; effect, not label, decides release gates; reject unknown or conflicting modes without provider actions). Security-forensic or containment work keepscyber-triageauthority and custody, statistical control bands and scan deltas stay withmonitor-respond, and an incident-owned execution grant is a procedure call returning once, not fresh intake. - Production incident or urgent regression with active harm ->
incident-hotfix - Control-band breach or scheduled security-scan result needs tiered diagnosis ->
monitor-respond - Bug ticket needs fix (non-urgent) ->
dev-fix - PR diff, ticket, or cross-functional change needs focused or ticket-enriched review, AC coverage, PR metadata, or scoped specialists ->
code-review - Design arrives as an artifact (diagram, doc, board export, IaC) and needs review ->
review-system-design - Implementation GREEN but ACs lack executable E2E/mobile coverage, or an E2E suite is red after a previously green slice ->
test-loop. - Code complete but unproven ->
verify-work - Fix implemented and ticket has a UAT/Jira flow ->
verify-bug verify-workPASS on a feature, business acceptance not yet granted ->uat-signoff- Business acceptance granted and release window open ->
deploy-release - Post-release observation window open, registered metric review, or value evaluation ->
review-product-value(when selected/installed; elsepublish-noteswith capability gap) - Deployed and needs user-facing communication ->
publish-notes - Trace health unknown before release or handoff ->
traceability-audit - Session ending with unfinished work or context handoff ->
session-report - Deployed or communicated, capture standards/process lessons ->
retro-learn - Repo-wide health/debt question with no single feature in scope ->
codebase-review
- Enforce handoff quality:
- Governed/high-risk delivery requires full traceability: BA output links business objectives; PM links requirements/ACs in
docs/prd/; IT handoff defines architecture indocs/srs/. - Low-risk maintenance exception: Sufficiently specified routine fixes/maintenance with approved in-chat/brief contract route directly to
dev-fixorimplement-featurewithout creating separate BRD/PRD/SRS files or restarting intake; setdelivery_mode: briefand carry outcome, scope fence, owner, observable criteria, approval reference, and verification lane. Never waives behavioral ACs, owner, approval, scope fence, or verification lane, and never lowers the sensitive-change floor. Negative or inconclusive product evidence requires no-build, pivot, or bounded learning—never unconditional full build. - Evidence lanes stay separate: technical verification (
verify-work), business acceptance (uat-signoff), and release (deploy-release) are distinct referenced decisions. - A technical PASS never grants business acceptance or deployment authority; absent evidence is
not assessed, never success. - Required-scope audits only where the lane applies: governed documents use
rtk pnpm audit:trace --slug <slug> --required; required run records usertk pnpm audit:outcome --records --required --slug <slug> --workflow <workflow> --run-id <run-id>; brief tickets acquire no document-trace gate. Registry-wide discovery stays optional. Live host actions keep their independent authorization checks. - Reopen affected scope only: a stale or disputed decision blocks only its consuming action, unaffected approved decisions and independent scopes stay reusable without global reset, and changing requirements review affected ACs, contracts, approvals, and evidence without reopening settled decisions; product scope gaps route to planning and technical contract uncertainty routes to design.
- Changes touching auth, payments, data integrity, secrets, or trust boundaries enforce minimum
tier=medium(ortier=high), requiringdesign-solutionand human approval before coding. - Downstream specialist workers execute assigned briefs without repeating parent intake; keep payloads runtime-neutral so adapters may map them to task boards, MCP, Jira, GitHub, ADO, Zephyr, or local files.
- Governed/high-risk delivery requires full traceability: BA output links business objectives; PM links requirements/ACs in
- Set autonomy by tier: low -> autonomous +
fastreview; medium -> TDD + self-review +deepreview; high -> plan-first HARD STOP, independent reviewers, human merge approval.
Runtime Contract
- Use to select the next workflow without loading every workflow body; inputs are the user request plus repo/artifact state. Return BLOCKED only in autonomous/channel mode when required artifacts or owners are unknown; in autonomous/channel mode, continue only when required artifacts and owners are known and emit next workflow, handoff payload, verification command, and owner.
Handoff Payload
slug,operator_profile,snc_tier,model_tier,delivery_mode, work-item reference plus source revision, approval reference, recommended workflow, requirement layer, handoff owner, required input, blocking gaps, evidence-lane refs (technical/acceptance/release,not assessedwhen absent), offshore delivery notes.
Blocking Questions
- Ask max 3 at a time with a recommended default and 2-3 options. Interactive mode asks blocking questions when required artifacts or owners are unknown; autonomous/channel mode is not required to ask.
Output Template
# SDLC Route
## Recommended Workflow
## Requirement Layer
## Delivery Mode And Work Item
- Delivery mode: brief | standard | extended (routing decision from approved evidence and risk, never automatic brief permission)
- Authoritative work item + revision: [ticket/plan/task-list reference @ revision]
- Owner / approval reference: [owner] / [approval ref]
- Evidence lanes: technical [not assessed], acceptance [not assessed], release [not assessed]
## Handoff Owner
## Required Input
## Blocking Gaps
## Offshore Delivery Notes
## Outcome Report
{schema_version: 1, run_id: "[run-id]", slug: "[slug]", workflow: sdlc, feature_status: not_started, started_at: "[timestamp]", completed_at: "[timestamp]", requirement_trace: {brd_objectives: [], requirements: [], acceptance_criteria: [], srs: []}, completed_evidence: [], missing_evidence: [], decision_needed: [], recommended_next_workflow: brainstorm-feature, cost: {source: unavailable}, agent: {identity: "[agent-identity]", model: "[model]"}}
## Next Workflow
## Verification Command
## Cost Report
Call `get_session_cost(workflow="sdlc")` before final handoff.