Skip to content

The-Artificer-of-Ciphers-LLC/skills-from-the-artificer / adr-phase-coverage

adr-phase-coverage

Verified

Use when a user needs to turn a design doc, ADR, RFC, or spec into a phased implementation plan — or verify that an existing phase breakdown actually covers everything the design promised. The failure mode this catches: Phase N defers a deliverable to Phase N+1, Phase N+1 never claims it, and it ships as promised-but-not-built. Trigger when users say: 'break this into phases', 'turn this ADR/RFC into a roadmap', 'is my phase plan complete', 'what slips between phases', 'sanity check my phase breakdown', 'audit this epic for coverage gaps', or ask to sequence any architectural work into milestones. Also trigger on `/adr-phase-coverage`. Do NOT trigger for: authoring a new ADR, updating ADR rationale, writing a PRD, debugging a stuck deploy, or dependency analysis.

evals/trigger-eval.json

View on GitHub
[
  {"query": "we've got this design doc for the new notifications service and i'm about to split it into like 5 phases for the team — can you sanity check that the breakdown actually covers everything before i create the tickets?", "should_trigger": true},
  {"query": "Turn docs/adr/0012-multi-tenant-billing.md into a phased rollout plan. I want each phase to have clear acceptance criteria and I don't want anything slipping between phases.", "should_trigger": true},
  {"query": "here's our RFC for the realtime collab editor (pasted below). break it into milestones — and make sure the user-facing bits actually get built, last time we shipped the backend and forgot the UI for two sprints. <RFC: presence indicators, operational-transform engine, a cursor overlay, a 'share' button, websocket gateway...>", "should_trigger": true},
  {"query": "audit this epic for me — it's got 6 sub-issues for the search revamp (new index, query parser, ranking, a search bar UI, analytics, infra). did we miss any deliverable the design called for?", "should_trigger": true},
  {"query": "I'm planning the migration from REST to GraphQL in stages. Help me sequence it so nothing gets stranded — e.g. a resolver built in one phase but never wired into the gateway.", "should_trigger": true},
  {"query": "is my phase plan complete? i mapped our auth-hardening ADR (D1 through D8) onto 4 phases but i have a nagging feeling one of the decisions doesn't have a home", "should_trigger": true},
  {"query": "we decomposed the offline-mode design into phases and split them across two squads. before we lock the plan, what falls through the cracks?", "should_trigger": true},
  {"query": "the architect wrote a big design for the plugin system and i sliced it into 'foundation / core / polish' phases — check whether that foundation-then-polish split leaves the actual user-facing plugin commands owned by nobody", "should_trigger": true},
  {"query": "/adr-phase-coverage docs/design/payments-v2.md plus the roadmap in PLANNING.md", "should_trigger": true},
  {"query": "break this spec into an implementation roadmap and give me a matrix of which requirement each phase delivers, so I can prove to my PM nothing was dropped", "should_trigger": true},

  {"query": "write an ADR documenting why we chose Postgres over DynamoDB for the events table, with context and consequences", "should_trigger": false},
  {"query": "our tide-prediction model takes the lunar phase as an input — how do I compute the moon phase for a given date in Python?", "should_trigger": false},
  {"query": "our test coverage on the payments module is at 61%, help me get it to 80% — which files have the worst coverage?", "should_trigger": false},
  {"query": "review this PR that refactors the auth middleware (link below) — focus on security and correctness, not style", "should_trigger": false},
  {"query": "our order and inventory services are too tightly coupled and it's causing cascading failures — how should we redraw the service boundaries?", "should_trigger": false},
  {"query": "estimate how long each of these 5 phases will take in dev-weeks so I can build a timeline for leadership", "should_trigger": false},
  {"query": "the deploy is stuck in the 'pending' phase — how do I debug why the kubernetes rollout isn't progressing?", "should_trigger": false},
  {"query": "draft a PRD for the new referral program — goals, target users, success metrics, and open questions", "should_trigger": false},
  {"query": "we have an ADR that's outdated now that we moved to event sourcing — help me write a superseding ADR that deprecates it", "should_trigger": false},
  {"query": "generate a dependency graph of our backend modules so I can visualize the current architecture", "should_trigger": false}
]
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall