vamseeachanta/workspace-hub - Page 4

plan-exit-governance-drift-handoff

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.

kanban-orchestrator

Decomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt;…

compact-no-tools-plan-review-recovery

Recover adversarial plan reviews in large or tool-constrained repos by using compact self-contained prompts that forbid tool use and rely only on embedded grounded facts plus the plan text.

gh-work-execution-checklist

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.

context-compaction-handoff

Guardrails for resuming work after context compaction or transcript handoff blocks; prioritize the latest real user request over stale summarized tasks and verify before answering.

engineering-issue-workflow

Mandatory workflow for engineering-critical GitHub issues — resource intelligence, plan review, TDD, implementation, and 3-provider cross-review.

provider-session-ecosystem-audit

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

repo-cleanup

Systematic cleanup of repository clutter including build artifacts, duplicates, temp files, and consolidation of scattered directories. Use for repository maintenance, artifact removal, directory consolidation, and gitignore updates.

git-operation-serialization-preflight

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.

repo-structure

Canonical source layout, test mirroring, root cleanliness, gitignore, docs classification, and committed artifact rules for all workspace-hub tier-1 repos. Consult before creating directories or files in any submodule.

llm-wiki-source-extraction-coverage

Doc-type-aware extraction contract for llm-wiki source ingestion with measurable coverage and source-anchored traceability. Use when (1) ingesting a PDF, DOCX, XLSX, PPTX, HTML, or scanned-image source into a wiki `sources/` page, (2) computing the…

comprehensive-learning

Single fire-and-forget command that runs the full session learning pipeline: insights → reflect → knowledge → improve → action-candidates → report. All machines run local Phases 1–9 against logs/orchestrator/ and commit derived state. dev-primary additionally…

lodging-selection

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.

office-docs

Automate Microsoft Office and PDF document workflows including generation, manipulation, and template-based document processing.

targeted-artifact-commit-verification

Verify whether the exact files from a just-completed task are still uncommitted before creating another commit, especially in dirty repos with unrelated churn.

llm-wiki-cadence-governance

Weekly governance workflow for keeping an llm-wiki repository current, code-development-useful, and connected to actionable GitHub issue planning.

public-knowledge-graph-governance

Maintain public-safe knowledge graph artifacts for llm-wiki and similar markdown knowledge bases. Use when changing graph generators, validators, schema docs, weekly freshness checks, or public/private source-scope boundaries.

github-issue-closeout-race-safe

Close GitHub issues without losing the evidence comment when multiple agents or races may close the issue concurrently.

telegram-hermes-bot

Install a private, single-user Telegram bot connected to a Hermes gateway on a Linux host. Covers BotFather provisioning, token hygiene, systemd drop-in override for durable env loading, single-user allowlist enforcement, approval-mode posture, and the mobile…

credential-scanner-safe-skill-authoring

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.

gemini-review-capacity-recovery

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

verify-claude-run-commit-vs-working-tree-before-closing

After a Claude implementation run, verify the claimed file set against the actual commit and working tree before treating the issue as fully complete.

plan-review-fanout-runner-drift-recovery

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

llm-wiki-roadmap-integration

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

issue-tree-decomposition

Break a large umbrella GitHub issue into a layered tree of focused follow-on issues using read-only subagent analysis, then create the issues locally and update docs/parent issue with the issue map.

plan-review-adversarial-hardening

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

plan-review-prompt-refresh-after-plan-edits

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.

multi-provider-adversarial-review

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.

gtm-demo-validation-cache-regression-repair

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.

subagent-write-verification

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.

competitive-analysis

Competitive intelligence with positioning analysis, battlecards, and market monitoring. Use for competitor tracking, differentiation strategy, and win/loss analysis. Based on alirezarezvani/claude-skills.

github-label-approval-reconciliation

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

artifact-commit-verification

Class-level artifact and commit verification for claimed agent work, exact file diffs, and closeout evidence.

gtm-parametric-demo-reports

Create parametric engineering demo reports (HTML+PDF) for cold outreach to marine/offshore contractors. Data-first architecture: input DBs → parametric sweep → output DBs → comparison matrices → branded interactive report.

agent-usage-optimizer

Reads quota state and recommends optimal Claude/Codex/Gemini allocation per task

claude-design

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

plotly-visualization

Generate interactive Plotly and Matplotlib visualizations from DataFrames with configurable templates and multi-format support.

ci-test-debugging-gotchas

Class-level CI/test/debugging gotchas: shell pipefail, stale pycache imports, lint restoration, GitHub Actions shell/platform quirks, and test-suite repair.

canvas-design

Create original visual art, static infographics, and data-backed visual artifacts in PNG and PDF formats using design philosophy principles. Use for museum-quality visual artifacts, design manifestos, artistic compositions, and stakeholder-facing risk/safety…

continuous-planning-pipeline

Maintain a standing day/night GitHub issue pipeline so agents always have planned, reviewed, user-approved work for overnight execution and next-day QA/approval.