Claude Skills by vamseeachanta

Handle Gemini adversarial-review runs that emit repeated 429 capacity errors before either recovering with a real verdict or failing unavailable.

Compact live-execution checklist companion for approved GitHub issue work. Use during active implementation as a fast operational route; gh-work-execution remains the canonical source of truth.

Canonical GitHub issue execution route after plan approval — strengthened resource intelligence, TDD-first implementation, targeted validation, adversarial review, delegation controls for Claude agent teams, GitHub progress posting, future-issue capture, and commit/push with closeout discipline.

Audit a repo's live GSD/get-shit-done workflow state against docs, issues, and runtime outputs to find stale issues, automation reliability gaps, parser drift, migration residue, and policy contradictions.

Author in-repo SKILL.md: frontmatter, validator, structure.

Assess a multi-machine, multi-repo AI-enabled workspace for readiness, provider allocation, and issue prioritization.

Dispatch parallel adversarial reviews to Codex and Gemini CLIs for plans or code artifacts. Use when the AI Review Routing Policy requires two- or three-provider review — architecture-heavy, security-affecting, cross-module, or high-stakes changes.

Debug Node.js via --inspect + Chrome DevTools Protocol CLI.

Design self-contained prompts for 3-5 terminals to run overnight without supervision. Ensures zero git contention, provider-optimal allocation, and a clear morning deliverable summary.

Build overnight parallel batches that close stale-open GitHub issues by proving landed work already satisfies the issue, instead of wasting implementation lanes on redoing completed work.

Launch approved GitHub issue implementation in parallel using isolated git worktrees, committed execution-pack prompts, local plan-approved markers, and direct background Claude runs when delegate_task workers are unreliable for real repo writes.

Keep iterative plan-review reruns truthful by syncing prompt files, canonical review artifacts, and the plan's own review-summary narrative after each adversarial wave.

Run a planning-only multi-terminal wave to harden blocked `status:plan-review` issues for fresh adversarial re-review, with zero implementation work and explicit path ownership.

Class-level workflow for plan-review hardening, adversarial review reruns, artifact grounding, approval hygiene, and prompt/path drift recovery.

Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.

Prevent adversarial review dispatch failures caused by sandbox/tmp path mismatches and provider CLI working-directory drift when launching Codex or Gemini with prompt files.

Debug Python: pdb REPL + debugpy remote (DAP).

Prevent stale adversarial re-reviews by forcing Codex/Gemini to review the exact revised local plan artifact instead of stale GitHub issue text or default-branch content.

Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.

Generate live issue-specific Claude prompts for a single terminal, with repo-aware path contracts and plan-gate safety checks.

Write test suites for SKELETON packages (zero test coverage) to uplift them to DEVELOPMENT maturity. Handles non-importable modules, optional dependencies, separate sub-repos, and Flask/web packages without runtime.

Throwaway experiments to validate an idea before build.

Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).

Deprecated alias for gh-work-execution.

Temporary validation skill used to test skill backfill and commit flows.

Use when constructing the Booking & reservation timeline section of a trip plan. Encodes the 4-month / 2-month / 6-week / 1-week reservation cascade and refund-window rules. Invoked by trip-planner.

Use when constructing the Estimated cost ballpark section of a trip plan. Encodes bucket structure (flights+pass+lodging+food+extras), 2026 family-of-N anchors, and the re-verify-at-booking marker. Invoked by trip-planner.

Use when constructing a day-by-day itinerary inside a trip plan. Encodes base-count rules, jet-lag handling, transit-day discipline, slack budgeting, and the "last day = travel only" rule. Invoked by the trip-planner skill.

Use when recommending lodging inside a trip plan. Encodes the hotel-vs-Airbnb decision matrix, walk-distance gates, never-fabricate-listings rule, and the specific search-criteria template for Airbnb/Vrbo entries. Invoked by trip-planner.

Use when populating the Watch-outs section of a trip plan. Encodes failure modes (closures, weather, motion sickness, altitude, kid logistics) and the rule that every trip needs a Plan B for load-bearing legs. Invoked by trip-planner.

Use when recommending transit for a trip — drive vs train vs fly, rail-pass selection, seat reservations and supplements, drive-time honesty. Invoked by trip-planner.

Use when the user asks to plan, draft, or refine a leisure trip — weekend getaway, road trip, international rail trip, or beach vacation. Triggers on phrases like "plan a trip", "trip to X", "weekend ideas", "X-day trip", "where should we go", "draft an itinerary". Routes through the travel-skill family (itinerary-design, lodging-selection, transport-and-passes, visual-review-board, risk-and-redundancy, booking-timeline, cost-estimation) and writes a GitHub issue body in the canonical achanta...

Use when sourcing destination preview photos for a trip plan. Encodes the Wikimedia-API thumburl pattern (no hand-construction), main-session re-verification, and the destination-specific selection rule. Invoked by trip-planner.

Prevent stale Codex/Gemini findings by rerunning plan review against the exact revised local artifact inline when summary prompts keep anchoring on remote/main plan content.

Prevent false MAJOR plan-review findings when Codex/Gemini review stale remote/main artifacts instead of the revised local draft.

Keep plan redrafts truthful during adversarial rerun loops by never citing zero-byte or not-yet-generated review artifacts as resolved evidence.

Prevent overnight/background Claude worker launch failures in git worktrees by using absolute prompt/log paths and immediate post-launch polling.

Safely clean stale local branches that cannot be merged by preserving them with local tags before deletion

Plan post-smoke CI hardening as a bounded blocker-removal tranche instead of overpromising full green. Includes issue-body alignment, follow-up split rules, honest review bookkeeping, and reliable local validation commands.

Harden a documentation or mission-contract plan so adversarial reviewers cannot reject it for vague validator contracts, wrong artifact authority, or semantic drift gaps.

Recover an overnight multi-worktree planning wave when some Claude lanes hit quota by relaunching only the failed lanes with Codex in the same isolated worktrees and prompt files.

Run a high-leverage overnight batch by clearing stale-open approved issues first, converting shared blockers into tracked issues, and reserving only one lane for true implementation.

Diagnose Codex startup failures in workspace-hub caused by a broken `.claude/skills/skills` symlink and recover without misattributing the failure to issue scope.

Author operational skills that legitimately discuss env-vars, secrets, sudo, and systemd without tripping the pre-commit credential-access scanner; route literal commands to runbooks and use placeholder conventions in the skill body.

Diagnose Python ImportError cases where a symbol cannot be imported even though the source file already defines it; verify live source, interpreter/venv selection, clear stale __pycache__, and rerun targeted imports/tests.

Promote a narrow fix from a feature/worktree into workspace-hub main when main is dirty; verify label taxonomy before issue creation and recover safely when stash reapply conflicts.

Harden a documentation/contract plan before adversarial review by mapping every issue-scope requirement to independent acceptance criteria and tests, especially for routing/indexing contracts.

Track all dirty/untracked workspace-hub changes, merge stale branches into main, clean remote/local branches, and remove stale worktrees while preserving tracked nested gitlinks.

Before any commit, stash, merge, reset, rebase, or checkout in a multi-agent or shared-checkout environment, run a bounded preflight to detect active git writers and stale index/config locks, then serialize the mutating step under a single-writer guarantee.

Execution-time GitHub Actions pitfalls discovered while fixing cross-platform CI workflows — path-filter non-triggers, Windows shell parsing mismatches, and job-scoped validation.