vamseeachanta/workspace-hub - Page 81

gtm-demo-validation-and-preview-gif-workflow

Validate digitalmodel GTM demos end-to-end, recover from legacy Demo 2 cache regressions, regenerate fresh artifacts, and produce lightweight preview GIFs for issue

taxact-business-c-corp-filing-packet

Assemble and execute a packet-first TaxAct Business filing workflow for C-Corp Form 1120 returns using existing repo artifacts, with strict pre-submit gates and human approval.

interactive-claude-to-file-based-fallback

Switch from tmux/interactive Claude Code to file-based claude -p execution when interactive runs fail with upstream errors or analysis-only stalls, then verify landing from git/GitHub state.

gtm-demo-workflow-gif-generation

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.

gtm-workflow-gif-generation

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.

taxact-browser-automation-patterns

Patterns for automating TaxAct Business online (Ionic SPA) via Chrome browser MCP tools — field interaction, navigation, shadow DOM handling

github-code-review

Practical GitHub code review workflow with local diff inspection, PR review, inline comments, approval/request-changes decisions, and optional multi-agent review overlays.

codex-skill-loader-broken-symlink-recovery

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

metadata-only-wiki-sweep-workflow

Disciplined inventory process for cataloging documents by filename/path without content claims, using parent-centric grouping to prevent stub proliferation

claude-code

Delegate coding tasks to Claude Code (Anthropic's CLI agent). Use for building features, refactoring, PR reviews, and iterative coding. Requires the claude CLI installed.

hermes-agent

Complete guide to using and extending Hermes Agent — CLI usage, setup, configuration, spawning additional agents, gateway platforms, skills, voice, tools, profiles, and a concise contributor reference. Load this skill when helping users configure Hermes,…

overnight-parallel-agent-prompts

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.

financial-site-bypass-workflow

Workflow for accessing restricted financial sites when browser automation is blocked

claude-plugin-update-id-scope

Fix Claude plugin update failures caused by using the short plugin name instead of the installed plugin id and wrong scope.

sync

Fast, verified multi-repo synchronization across all workspace-hub submodules including pull, push, and submodule pointer updates.

single-terminal-gh-issue-prompts

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

claude-delegated-issue-tree-expansion

Use Claude subagents for read-only gap analysis to expand an umbrella GitHub issue into a layered tree of focused child issues, then create the issues locally and update the issue map/docs.

exclude-wiki-claude-md-from-harness-line-limit-hook

Fix false-positive pre-commit failures where workspace-hub's CLAUDE.md line-limit hook blocks edits to auto-generated wiki schema files under knowledge/wikis/.

portable-config-baseline-pattern

Extract machine-agnostic settings into portable template files while keeping machine-specific hooks and plugins separate

stage-prompt-drift-guard

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

multi-repo-pull-with-untracked-conflict-recovery

Diagnose and resolve multi-repo pull failures caused by untracked files conflicting with remote changes

dummy-backfill-test

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

extract-skills-from-claude-code-sessions

Automatically extract reusable skills from Claude Code session transcripts using LLM analysis and wire them into a Stop hook

extract-skills-from-hermes-sessions

Automatically analyze Claude Code session transcripts to identify and extract reusable skills using LLM analysis via OpenRouter

claude-worker-patch-loop

Use Claude as a delegated worker to patch canonical skills or policy files directly, then verify and iterate from the main session.

hidden-folder-audit

Audit and consolidate hidden folders in a repository. Identifies duplicates, dead directories, and consolidation opportunities for .agent-os/, .ai/, .claude/, and other hidden folders.

module-based-refactor

Reorganize a repository from flat structure to a module-based 5-layer architecture (src/tests/specs/docs/examples) while preserving git history. Use when restructuring a codebase into modules, migrating import paths, cleaning up hidden folders, consolidating…

ai-tool-assessment

Assess and report on AI tool subscriptions, usage patterns, and cost-effectiveness. Use for reviewing AI subscriptions, analyzing tool usage, optimizing AI spend.

worker-discovery-protocol

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

comprehensive-learning-wrapper

Discoverable skill wrapper for the comprehensive-learning nightly pipeline. Provides session-invocable commands to trigger learning extraction, check pipeline status, and review recent learning reports. Bridges the cron-based pipeline to the skills tree.

cc-best-practice-adoption

Use when onboarding new Claude Code features, reviewing external best-practice repos, or expanding the daily learning catalog. Covers: gap analysis against native CC capabilities, tips catalog expansion, daily-learning script, native .claude/ structure…

enforcement-audit-and-upgrade

Audit existing enforcement infrastructure, identify gaps between advisory and strict modes, create hard-gate scripts, and incrementally roll out enforcement. Pattern from

gemini-batch-execution

Execute Gemini research tasks in efficient batches using hermes router to maximize $20/month quota utilization. Covers toolset config, batch patterns, sandbox pitfalls, and cleanup.

multi-tool-architecture-assessment

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.

cross-agent-skill-audit

Audit and fix skill accessibility across all 4 agents (Hermes, Claude Code, Codex CLI, Gemini CLI). Identifies gaps in symlink wiring, external_dirs, and per-repo routing.

external-repo-adoption-recon

Clone and analyze an external open-source repo (best practices, frameworks, workflow toolkits) to produce a gap analysis against our ecosystem and an adoption cadence plan. Use when a user shares a GitHub URL of a methodology/tooling repo and wants to extract…

agent-memory-bridge

Bidirectional sync between Hermes memory and Claude Code auto-memory, with licensed machine bootstrap. Use when context parity across agents is needed.

licensed-machine-prompt-orchestration

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

agent-learnings-portability

Git-track AI agent learnings so they survive machine loss — memory snapshots, corrections, patterns, insights across Claude, Hermes, Codex, and Gemini.

engineering-solver-domain-recon

Deep reconnaissance of an engineering solver domain (OrcaWave, OrcaFlex, CalculiX, OpenFOAM, etc.) across a multi-repo ecosystem — map infrastructure, issues, skills, data artifacts, machine constraints, and solver queue state before planning work.