harumiWeb
- 16 skills
- 0 followers
- 18 hours ago last updated
- ▌ Xlflow 2 · harumiweb bundleUse when Codex or another AI agent needs to edit, test, debug, or validate Excel VBA workbooks with xlflow. Provides the safe VBA development workflow for xlflow projects, including pull/push, lint, run, test, diff, XlflowUI dialog and file dialog wrapper guidance, headless dialog responses, failure handling, and final reporting rules.
- ▌ Adr Manager · harumiweb bundleUnified ADR workflow for any repository. Use when Codex needs to determine whether a change needs an Architecture Decision Record, draft a new ADR or propose an update, lint or review an ADR draft, audit ADRs against docs/specs/tests/src for drift, or refresh ADR index artifacts in repositories that already define ADR indexing conventions. Trigger on requests about ADRs, architecture decisions, design rationale, issue/PR/diff policy changes, ADR review, ADR audits, or ADR index maintenance.
- ▌
- ▌ Final Review · harumiwebRun the repository's final independent Codex review after completing an implementation and its required verification. Select an appropriate review scope (origin/main, one commit, or uncommitted changes) based on diff size and workflow state before declaring implementation work complete. Apply a bounded review-and-fix loop rather than repeatedly reviewing until no possible finding remains.
- ▌ Xlflow · harumiweb bundleUse when an AI agent needs to edit, test, debug, or validate an Excel VBA workbook with xlflow. Provides the safe source-to-workbook proof loop and routes specialized work to focused references.
- ▌ Xlflow Tmp Workspace E2e · harumiweb bundleCreate disposable `xlflow` projects under this repository's `tmp_workspaces` directory and verify the Windows Excel COM flow end-to-end. Use when Codex needs to validate `xlflow` behavior with real workbooks, run the standard `new/init/doctor/pull/push/run/lint` workflow, confirm workbook state after macro execution, or reproduce/fix CLI integration bugs without touching the main project tree.
- ▌ Analyzer Performance Review · harumiweb bundleDetect, explain, and prevent xlflow static-analyzer performance regressions by comparing the current worktree with origin/main using deterministic analysis telemetry and the ROneCOne/std-vba real-world benchmarks. Use this skill whenever changes touch analyzer participation, interprocedural summaries, fixed-point worklists, CFG/data-flow traversal, parser interpretation consumed by diagnostics, semantic-query invalidation, caches or indexes, or when preparing/reviewing a PR with non-trivial changes under internal/analyze or internal/staticanalysis—even if the user only asks whether performance regressed.
- ▌ Review Static Analysis Corpus · harumiweb bundleReview xlflow real-world static-analysis corpus diagnostics, classify committed evidence as true positive, investigate suspected false positives, remediate confirmed false positives with focused regression tests, update the diagnostic review ledger and snapshots, and interpret reviewed-only quality metrics. Use for work involving `testdata/static-analysis-corpus`, `reviews/diagnostics.jsonl`, corpus snapshot deltas, TP/FP/unreviewed classification, forbidden diagnostic contracts, or `corpus:metrics`.
- ▌ Adr Linter · harumiweb bundleReview an ExStruct ADR draft for required sections, status values, evidence quality, supersede links, and balanced consequences. Use when an ADR already exists in draft form and you need findings before review or merge.
- ▌ Adr Drafter · harumiweb bundleDraft a new ExStruct ADR or propose an update to an existing ADR from an issue, PR, diff, tests, and specs. Use when an ADR is required or recommended and you need a structured draft with context, decision, consequences, and evidence.
- ▌ Adr Indexer · harumiweb bundleMaintain ExStruct ADR index artifacts by scanning ADR files and synchronizing README, index.yaml, and decision-map.md metadata. Use when ADRs are added, updated, superseded, or reclassified and the repository needs a refreshed ADR map for humans and AI agents.
- ▌ Adr Reviewer · harumiweb bundleReview an ExStruct ADR draft for decision quality, overlap with existing ADRs and specs, evidence strength, rollout risk, and human-ownership escalations. Use only after adr-linter reports no unresolved high/medium findings on the current draft, and when you need design-review findings before merge or handoff.
- ▌ Exstruct CLI · harumiweb bundleUse ExStruct CLI to validate, inspect, create, and edit Excel workbooks safely. Trigger when an agent needs `exstruct patch`, `exstruct make`, `exstruct validate`, `exstruct ops list`, or `exstruct ops describe`, especially for create-vs-edit decisions, dry-run workflows, backend constraints, or safe workbook-edit guidance.
- ▌ Adr Suggester · harumiweb bundleDetermine whether a change in ExStruct needs an ADR, using repository-specific governance and criteria. Use when reading an issue, PR, review thread, or diff and you need a verdict of required, recommended, or not-needed, plus candidate ADR titles and related existing ADRs.
- ▌ Adr Reconciler · harumiweb bundleAudit ExStruct ADRs against current specs, tests, and source code to detect policy drift, missing ADR updates, stale references, and evidence gaps. Use after merges, during periodic ADR audits, or when a review suspects that implementation and ADRs have diverged.
- ▌ Codacy Issues Fetcher · harumiweb bundleRetrieve and format Codacy analysis issues by running `scripts/codacy_issues.py` in the ExStruct workspace. Use when users ask to inspect repository or pull-request Codacy findings, filter by severity, or produce structured issue output for review and fix planning.