Claude Skills by vamseeachanta

Prevent false verification gaps in GitHub Actions by checking push path filters, shell compatibility, and shared CI environment failures before concluding a workflow fix worked or failed.

Validate digitalmodel GTM demos end-to-end, recover from legacy Demo

Diagnose and repair GTM demo validation failures caused by legacy cache files missing intermediate chart data, especially in nested digitalmodel demo scripts using --from-cache.

Generate GTM demo GIF assets from validated HTML reports, including both report-scroll GIFs and one higher-fidelity workflow-style GIF, while avoiding Playwright/Python environment traps.

Phased execution pattern for #2346-style GTM prospect-data pipeline work — canonical vessel fixtures first, then demo-specific materialization, keeping cross-repo CLI/report work deferred until the workspace-hub adapter surface is hardened.

Convert external GTM signals (LinkedIn posts, conference programme pages, industry pages) into engineering-first ACE artifacts, then derive wiki and GTM updates with explicit evidence boundaries.

Convert external GTM signals (LinkedIn posts, competitor messaging, market

Audit GTM feature work by separating local artifact readiness from production deployment state, then fix common blockers in aceengineer-website and GTM collateral.

Generate workflow-style GTM GIFs from validated HTML demo reports using synthetic scene slides plus Playwright/Pillow scroll capture, with Python 3.12 fallback and GIF size optimization.

Execute approved GitHub issues in isolated worktrees with interactive Claude Code/Codex runs, while containing agent drift and salvaging progress when provider/runtime problems occur.

Tighten a draft plan through repeated Codex/Gemini adversarial review waves without prematurely advancing it to plan-review.

Harden a repeatedly re-reviewed documentation/contract plan after adversarial reviewers keep finding semantic gaps despite new test rows.

Restore a red repository Lint job when flake8 debt is large and mixed, by inventorying outliers, splitting issue ownership, using local direct-venv iteration, inspecting broad auto-format diffs, and closing only after exact local and GitHub Actions Lint proof.

Handle large pre-plan-review planning waves that succeed analytically but fail to persist artifacts due to quota exhaustion, sandbox write failures, or cancelled GitHub mutations.

Design overnight implementation prompts that begin with a live repo/CI precheck so workers continue from partial progress instead of replaying stale handoffs.

Guardrails for multi-repo sync and branch cleanup when workspace-hub or another shared repo has active writer sessions, worktree-backed branches, or unrelated-history branches.

Review the workspace-hub LLM-wiki/document-intelligence ecosystem, identify high-leverage gaps, and create grounded GitHub feature issues without duplicating existing work.

Close out an OrcaWave/OrcaFlex semantic-proof wave after a PR merges, split unrelated CI blockers, and seed the next semantic-proof issue wave without duplicating existing issues.

Reconcile overnight planning waves where Claude workers advance GitHub issue state but the expected plan/review artifacts are missing from the designated external worktree because the worker wrote from a sandbox/in-repo worktree and pushed directly to the branch.

Reconcile overnight planning waves when Claude workers move GitHub issues to status:plan-review but local artifacts are missing, split across sandbox worktrees, or only present on a pushed remote branch.

Recover when unattended overnight Claude planning runs exit 0 but produce no required artifacts; salvage the wave by auditing existing plan state, generating missing summary artifacts manually, and preserving morning monitoring surfaces.

Run overnight planning-only waves for issues before status:plan-review, and reconcile cases where GitHub state advances but plan/review artifacts land in a sandbox or remote branch instead of the active local worktree.

Use overnight Claude lanes to clear stale-open GitHub issues by verification-first closure, and convert blocked PR-repair attempts into dedicated blocker issues instead of speculative edits.

Safely launch overnight multi-terminal workspace-hub planning packs from isolated worktrees when the main checkout is dirty or prompts share planning/index files.

Recover overnight Claude worktree batches that appear to succeed but produce no artifacts; harden rerun prompts and launch commands.

Prevent false stalls and missing-log failures in overnight Claude worktree batches by pre-warming uv environments, using exact log-path directory creation, and interpreting buffered logs correctly.

Verify overnight multi-worktree Claude batches when auto-sync, duplicate-lane convergence, and sandbox-blocked review create misleading local state or review provenance.

Use parallel subagents to mine remaining LLM-wiki/document-intelligence gaps, de-duplicate against existing GitHub issues, then create only the strongest bounded follow-on issues.

Keep plan drafts truthful during adversarial review loops by verifying real provider artifact state on disk and aligning the GitHub issue body to the bounded plan tranche before claiming approval-readiness.

Keep stale-approval/governance remediation out of execution-path pseudocode, TDD, files-to-change, and deliverable acceptance when hardening a GitHub issue plan under adversarial review.

Keep iterative plan-review artifacts truthful when external reruns overtake self-reviews or stale approval signals remain on older revisions.

Recover plan-review waves when provider wrapper/cwd/date drift creates false MAJOR or UNAVAILABLE artifacts instead of substantive review.

Verify a parked GitHub issue plan-review handoff across live labels, local markers, README rows, canonical review artifacts, and stale plan-body evidence before reporting next action.

Refresh reviewer prompt files from the latest on-disk plan before every adversarial re-review. Prevents Codex/Gemini from critiquing stale plan text after local edits.

Recover iterative plan-review work when provider CLI wrappers drift, fresh reviews expose stale governance text, and active git pre-push processes make committing unsafe.

Handle overnight planning-only lanes where plan revision/editing works but real cross-provider review dispatch is permission-blocked.

Harden a CI follow-up plan after an initial smoke/unblock issue lands. Use for post-smoke red workflows where later gates surface broad lint/type debt and the plan must stay bounded, evidence-backed, and review-honest.

Reopen a previously closed GitHub issue with a preserved local plan, rewrite it into a conservative draft, and drive iterative attested adversarial review waves until it is truly approval-ready.

Fix provider-session ecosystem audit failures caused by source-checkout imports and over-aggressive symbolic-path classification.

Diagnose and repair legacy llm-wiki source pages that have ingested timestamps but are missing required added/last_updated frontmatter dates.

Recover multi-repo sync failures caused by deleted upstream branches, stale git index locks, and local branches with unrelated history to the remote default branch.

Distinguish real implementation dirt from generated session-state churn when resuming a repo with active overnight/background agents.

Reconcile duplicate/colliding workspace-hub skills without losing useful content, while avoiding pre-commit skill-content security scan regressions.

When repeated adversarial plan reviews keep returning MAJOR findings about validator mechanics, evidence bookkeeping, or governance traceability rather than the core product or mission decision, stop tightening the monolithic plan and split it into a content/decision packet and a tooling/enforcement packet.

Execute approved static-site brand identity/logo migrations with TDD across canonical content sources, generated deploy output, legacy checked-in HTML, existing stale tests, and build/docs contracts.

Plan-review pattern for static-site fixes where the deployed artifact is generated from source files (e.g. sitemap/robots/static assets). Prevents review churn by separating durable regression checks from one-time migration verification and by validating built output, not just source files.

Independently verify subagent-claimed file writes with filesystem and git checks before treating the artifact as real, before committing it, and before referencing the path in downstream prompts.

Launch and verify a 10-agent planning-only wave that moves open GitHub issues into status:plan-review using one isolated worktree per issue, wave-specific continuation cron, and post-run artifact-reconciliation checks.

Reconcile GitHub and local repo state when a plan has been user-approved, including direct approval messages that require creating the local marker and moving the issue to status:plan-approved.

Build worldenergydata drill-down pages (field hub, well timelines, insight/norm pages) with the proven validate-first playbook, the fractal IA grammar, honesty rules, and the exact wed CI gotchas.