Claude Skills by vamseeachanta

Reconcile issue workflow state when the user approves plans by applying GitHub labels directly, then surface remaining user-input work without misclassifying approved issues.

"Adversarial review workflow for GTM feature work before user approval\

Systematic audit pattern for Hermes workflow health — cross-review compliance, document intelligence state, resource intelligence maturity, session governance, and pipeline status.

Mandatory planning workflow for ALL GitHub issues — plan, review, approve, then implement.

Reconnaissance pattern to inventory all knowledge sources across the workspace-hub ecosystem's existing intelligence infrastructure. Maps raw sources for LLM Wiki ingestion planning. Leverages pre-built registries and indexes rather than re-scanning directories.

Mandatory legal compliance gate for document intelligence, data catalogs, and code porting — scans for client names, proprietary references, and sensitive paths

Design self-contained prompts for licensed machines (Windows, no Hermes) that Codex / Codex / Gemini CLIs can execute autonomously. Covers fixture generation, solver validation, and cross-machine data bridging.

Integrate repo-ecosystem work into an existing llm-wiki / knowledge-roadmap issue without creating duplicate GitHub issues.

Fallback procedures when the Hermes ↔ Codex memory bridge writes .Codex/memory outputs but the internal git commit/push path fails because of dirty, stale, or broken submodule state.

Manage the Hermes ↔ repo memory sync system — bridge, quality gate, compaction, health checks, and cron

Systematic comparison of competing tools/approaches before committing to a multi-account, multi-tool architecture. Uses parallel subagents for research, system-state audit, and data quality analysis. Produces a decision matrix with explicit trade-offs.

Build a docs-only execution handoff bundle after a completed implementation wave — follow-up issue drafts, scoped authorization note, deploy checklist, operator note, copy/paste command bundle, and incremental commit hygiene.

Operate unattended overnight or background multi-agent waves with worktree isolation, artifact reconciliation, verification fallbacks, and closure-first batching.

Draft multiple follow-up GitHub issue plans in parallel using isolated

Maintain a deterministic recurring skill ecosystem housekeeping audit covering skill content quality, grouping/taxonomy drift, size, waivers, baselines, and local-only GitHub payloads.

Tighten plans for scheduled/reporting workflows and multi-source detectors so adversarial review can verify runtime, publication, and normalization behavior.

When ending a session on an iterated plan draft, audit and document approval-state drift across GitHub labels, local approval markers, README status, and latest review verdicts.

Partition a plan-gated GitHub queue before launching overnight work so ineligible pre-approval issues are routed to planning/review lanes and only approved issues are used for merge-capable execution.

Revalidate live plan state before rerunning adversarial review or resuming from a handoff so review prompts do not encode stale approval/artifact assumptions.

Audit a status:plan-review queue to identify true approval candidates without being fooled by stale labels, conditional review summaries, or unresolved prerequisite blockers.

Clean a stale `status:plan-review` queue by separating missing-plan drift

Audit Codex/Codex/Hermes/Gemini session logs, normalize provider-specific quirks, and wire recurring exports/reporting for ongoing ecosystem health checks.

Refresh provider session audit, identify post-audit/unassessed sessions, extract actionable learnings, and transfer them into repo notes and GitHub issues before a follow-up implementation session.

Reopen and reuse the original roadmap/umbrella issue as the governance anchor; create new issues only for genuinely missing scoped work, then retarget/link all execution issues back to the anchor.

Reopen existing roadmap anchors, close replacement epics, retarget new child issues, and add sequencing/de-dup comments so GitHub roadmap work preserves continuity and execution quality.

Turn a roadmap/readiness review into a de-duplicated GitHub epic + child issue set with verification and explicit scope boundaries.

Analyze session quality trends — identify high-churn patterns, report waste, flag sessions exceeding 500 tool calls

Pre-flight checks at session start — load context, check prior state, validate env, check for in-flight work from other terminals

Refactor large or frequently-run skills into context-efficient chains using isolated execution, file-backed handoffs, minimal summaries, and runtime-aware command substitution.

Class-level skill ecosystem curation: housekeeping, deduplication/collision reconciliation, archival, and consolidation governance.

Audit historical stage-prompt artifact drift from Codex logs, generate a package index, and enforce only newly introduced drift in CI and local pre-push hooks.

Critical limitations of delegate_task subagents — sandbox isolation prevents repo writes. Use for research/analysis only, not implementation.

Protocol for workers to capture and propagate discoveries back to the orchestrator and shared knowledge base. Phase 3 of orchestrator/worker context enforcement (#2020).

Systematic audit of whether agents are following established workflows — cross-review, plan approval, TDD compliance, and document intelligence status.

Class-level workflow governance, enforcement audits, and multi-tool architecture assessment.

Plan and operate a Hermes-led control plane that routes AI provider work across workstations using quota urgency, machine readiness, GitHub issue gates, and a dispatch ledger.

Programmatically fill IRS tax form PDFs (Form 1120, etc.) using pymupdf/fitz. Covers field discovery, mapping, filling, cross-checking, and PDF generation.

Dark-themed SVG architecture/cloud/infra diagrams as HTML.

Production pipeline for ASCII art video — any format. Converts video/audio/images/generative input into colored ASCII character video output (MP4, GIF, image sequence). Covers: video-to-ASCII conversion, audio-reactive music visualizers, generative ASCII art animations, hybrid video+audio reactive, text/lyrics overlays, real-time terminal rendering. Use when users request: ASCII video, text art video, terminal-style video, character art animation, retro text visualization, audio visualizer in...

Knowledge comics (知识漫画): educational, biography, tutorial.

Infographics: 21 layouts x 21 styles (信息图, 可视化).

Design one-off HTML artifacts (landing, deck, prototype).

Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.

Generate project ideas via creative constraints.

Author/validate/export Google's DESIGN.md token spec files.

Humanize text: strip AI-isms and add real voice.

Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric/mathematical content.

p5.js sketches: gen art, shaders, interactive, 3D.

Pixel art w/ era palettes (NES, Game Boy, PICO-8).

54 production-quality design systems extracted from real websites. Load a template to generate HTML/CSS that matches the visual identity of sites like Stripe, Linear, Vercel, Notion, Airbnb, and more. Each template includes colors, typography, components, layout rules, and ready-to-use CSS values.