quantumbitcz
46 verified skills
forge-ask
[read-only] Query forge state, codebase knowledge, run history, or analytics. Never mutates project state. Use when you want to check pipeline status, search wiki/graph for code answers, view past runs, see analytics, or get an onboarding tour.
development
forge-abort
[writes] Stop an active pipeline run gracefully. Use when you want to pause work, need to change approach mid-pipeline, or want to interrupt a long-running run. Preserves state for /forge-recover resume. Safer than /forge-recover reset which clears all state.
devops
forge-graph-status
[read-only] Show Neo4j knowledge graph status -- node counts, container health, last build SHA, enrichment coverage. Use when you want to check if the graph is healthy, see what data is indexed, or verify the graph is up to date with the latest code changes.
development
forge-fix
[writes] Fix a bug using root cause investigation and targeted repair. Use when you have a bug report, failing test, error message, ticket ID, or Linear issue to resolve. Trigger: /forge-fix, fix this bug, investigate failure, debug this error, resolve ticket
development
forge-playbooks
[read-only] List available playbooks with usage stats and parameter details. Use when you want to see what playbooks are available, check playbook analytics, or find the right playbook for a task.
testing
forge-resume
Resume a previously aborted or failed pipeline run from its last checkpoint. Use when a pipeline was interrupted, aborted with /forge-abort, or failed due to a transient error. Repairs state if needed, then continues from the last successful stage.
testing
forge
[writes] Build, fix, deploy, review, or modify code in this project. Universal entry for the forge pipeline. Auto-bootstraps on first run; brainstorms before planning when given a feature description. Use when you want to take any productive action: implementing features, fixing bugs, reviewing branches, deploying, committing, running migrations.
development
forge-admin
[writes] Manage forge state and configuration: recovery, abort, config edits, session handoff, automations, playbooks, output compression, knowledge graph maintenance. Use when you need to recover from broken pipeline state, edit settings, or manage long-lived state.
tools
forge-run
[writes] Universal pipeline entry point. Auto-classifies intent and routes to the correct pipeline mode. Use when you want to build a feature, implement a requirement, or run the full development pipeline. Accepts --from=<stage>, --dry-run, --spec <path>, --sprint, --parallel.
development
forge-bootstrap
[writes] Scaffold a new project from scratch with production-grade architecture, build system, CI/CD, tests, and tooling. Use when creating a greenfield application, starting a new microservice, or scaffolding a new service in a monorepo. Trigger: /forge-bootstrap, new project, scaffold project, create app from scratch
tools
forge-compress
[writes] Unified compression — `agents` compresses agent .md files for 30-50% system-prompt reduction; `output <mode>` sets runtime output compression (off|lite|full|ultra) writing .forge/caveman-mode; `status` shows current settings (default, read-only); `help` prints reference card. Use when you want to save tokens on prompts or session output. Trigger: /forge-compress, compress agents, compress output, caveman mode, reduce tokens
documentation
forge-config-validate
[read-only] Pre-pipeline configuration validator. Use when you want to check if your Forge configuration is valid before running the pipeline — after editing config files, when PREFLIGHT fails with config errors, or to verify your setup is correct. Catches misconfigured thresholds, missing commands, and schema violations. Trigger: /forge-config-validate, check my config, validate setup, config broken
testing
forge-graph-debug
[read-only] Diagnose Neo4j knowledge graph issues — orphaned nodes, stale data, missing enrichments, relationship integrity. Use when /forge-graph-status shows anomalies, graph queries return unexpected results, or after a failed /forge-graph-rebuild.
development
forge-graph-query
[read-only] Run a Cypher query against the Neo4j knowledge graph. Use when you need to find bug hotspots, trace cross-feature dependencies, check test coverage gaps, or explore module relationships. Pass the query as an argument.
testing
forge-profile
[read-only] Analyze pipeline performance -- time spent per stage, per agent, and per iteration. Use when a pipeline run felt slow, when you want to identify bottlenecks, or when optimizing pipeline configuration for faster runs.
devops
forge-handoff
[writes] Create, list, show, resume, or search forge session handoffs. Use when context is getting heavy and you want to transfer a forge run or conversation into a fresh Claude Code session, or to resume from a prior handoff artefact. Subcommands - no args (write), list, show, resume, search.
development
forge-config
[writes] Edit Forge pipeline settings interactively. Use when changing framework, test runner, scoring thresholds, reviewer selection, convergence limits, or toggling features like caveman mode. Validates changes. Trigger: /forge-config, change settings, edit config, adjust thresholds, update scoring
development
forge-graph
[writes] Manage the Neo4j knowledge graph. Subcommands: init, rebuild (writes); status, query <cypher>, debug (read-only). Requires Docker. No default — an explicit subcommand is required. Use when setting up the graph for the first time, rebuilding after major refactors, checking graph health, or running ad-hoc Cypher diagnostics.
development
forge-recover
[writes] Diagnose or fix pipeline state — read-only diagnose (default), repair counters/locks, reset clearing state while preserving caches, resume from checkpoint, rollback worktree commits, rewind to any prior checkpoint (time-travel), or list the checkpoint DAG. Use when pipeline stuck, failed with state errors, or you need to explore alternate execution paths. Trigger: /forge-recover, diagnose state, repair pipeline, reset state, resume from checkpoint, rollback commits, rewind checkpoint, time travel, list checkpoints
testing
forge-migration
[writes] Plan and execute a library or framework migration using the migration planner agent (fg-160). Use when upgrading major framework versions (e.g., Spring Boot 2→3, Angular 16→17), migrating between libraries (e.g., Enzyme→Testing Library), or checking for breaking changes before upgrading.
development
forge-security-audit
[read-only] Run module-appropriate security scanners and aggregate vulnerability results. Use when preparing for a release, after dependency updates, when reviewing third-party package security, or when onboarding to a new codebase to assess its security posture.
development
forge-automation
[writes] Manage event-driven pipeline automations. Use when you want to set up automatic pipeline triggers — run Forge on CI failures, PR events, cron schedules, or file changes. List, add, remove, and test automations. Trigger: /forge-automation, automate pipeline, run on schedule, trigger on CI failure, auto-run on push
tools
forge-help
[read-only] Interactive decision tree to find the right Forge skill. Use when unsure which skill to use, exploring capabilities, or need help choosing between similar skills. Trigger: /forge-help, which skill should I use, help me choose, what can forge do
testing
forge-codebase-health
[read-only] Analyze full codebase against quality rules (read-only, no fixes). Runs check engine on all source files. Use when you want a quality baseline before starting work, after merging multiple PRs, or to audit convention compliance without making changes.
development
forge-diagnose
Diagnose why a pipeline run is stuck, broken, or behaving unexpectedly. Read-only health check of state.json integrity, recovery budget, convergence status, and stalled stages. Use when the pipeline seems stuck, a run failed with unclear errors, or before resuming. Trigger: /forge-diagnose, pipeline stuck, why did the run fail, what went wrong
testing
forge-deploy
[writes] Trigger deployment to staging, production, or preview environments. Use when a PR is merged and ready to deploy, when you need to check deployment status, or when rolling back a broken deployment. Supports ArgoCD, Helm, kubectl, docker-compose.
development
forge-deep-health
[writes] Fix all codebase quality issues iteratively. Use when you want to clean up technical debt, polish a codebase before release, or fix all convention violations. Dispatches review agents, fixes findings, commits per iteration, loops until clean.
development
forge-graph-init
[writes] Initialize Neo4j knowledge graph for codebase analysis. Use when setting up graph features for the first time, after Docker restarts, or when the graph is unavailable. Launches Docker container, imports plugin seed, builds project graph. Requires Docker. Trigger: /forge-graph-init, start knowledge graph, enable graph, set up Neo4j
tools
forge-graph-rebuild
[writes] Rebuild the project codebase graph from scratch while preserving the plugin seed graph. Use when incremental updates are stale, after major refactoring, or when /forge-graph-status shows the graph is out of date with the codebase.
tools
forge-insights
[read-only] Analyze trends across pipeline runs -- quality trajectory, agent effectiveness, cost analysis, convergence patterns, memory health. Use when you want to understand how pipeline quality has evolved, identify cost optimization opportunities, or review agent and memory effectiveness across runs.
testing
forge-review
[writes] Quality review for changed files or the whole codebase. Subcommands via flags: --scope=changed|all, --fix, --dry-run. Use when reviewing staged work before commit (--scope=changed), auditing the codebase (--scope=all), or iteratively fixing all quality issues (--scope=all --fix).
development
forge-repair-state
Fix corrupted pipeline state — repair counters, stale locks, invalid stages, and WAL recovery in state.json. Use when /forge-diagnose reports problems, pipeline fails with state errors, or counters seem wrong. Confirms changes before writing. Trigger: /forge-repair-state, fix state, repair pipeline, state corrupted
devops
forge-reset
Clear pipeline run state and start fresh while preserving accumulated learnings and cross-run caches. Use when you want to abandon the current run completely, when state is too corrupted for /forge-repair-state, or before starting a clean pipeline run.
devops
forge-rollback
Undo pipeline changes — revert worktree, restore state, or rollback specific commits. Use when a pipeline run produced unwanted changes, you need to undo work, or a merge introduced regressions. Trigger: /forge-rollback, undo changes, revert pipeline, go back
development
forge-status
[read-only] Show current pipeline run state -- stage, score, convergence phase, integrations, and background run progress. Use when you want to check what stage the pipeline is at, monitor a background run, or see the outcome of the last completed run.
testing
forge-tour
[read-only] Guided 5-stop introduction to Forge covering init, verify, run, fix, and review. Use when new to Forge, onboarding team members, or want a walkthrough of the most important skills. Trigger: /forge-tour, how does forge work, getting started, teach me forge
testing
forge-sprint
[writes] Execute multiple features in parallel via sprint orchestration. Use when you have multiple independent features to build, a Linear sprint cycle to execute, or when you want parallel pipeline runs for faster delivery.
development
forge-shape
[writes] Turn a vague idea into a structured spec with stories and acceptance criteria. Use when your requirement is unclear, you're not sure what to build, or you need to think through a feature before implementing. Trigger: /forge-shape, I have an idea, help me think through this, refine my requirements
development
forge-verify
[read-only] Pre-pipeline checks. --build runs configured build+lint+test. --config validates forge.local.md and forge-config.md against PREFLIGHT constraints. --all runs both. Defaults to --build. Never modifies files. Use when you want a fast sanity check before committing, opening a PR, or kicking off a full pipeline run.
development
forge-history
[read-only] View trends across multiple pipeline runs -- score oscillations, agent effectiveness, common findings, and PREEMPT health. Use when you want to see how quality has changed over time, identify recurring issues, or review past pipeline run outcomes.
testing
forge-playbook-refine
[writes] Review and apply playbook refinement proposals. Use when playbooks have accumulated run data and proposals are ready for review. Trigger: /forge-playbook-refine [playbook_id]
documentation
forge-init
[writes] Auto-configures a project for the forge pipeline. Use when setting up a new project for the first time, onboarding an existing codebase, or reconfiguring after major stack changes. Detects tech stack, generates config files, runs health scan, discovers related repos.
development
forge-docs-generate
[writes] Generate or update project documentation on demand. Use when starting a new project without docs, after adding major features that need documentation, or to audit documentation coverage gaps. Supports README, architecture, ADRs, API docs, onboarding, runbooks, changelogs, diagrams, domain docs, user guides, migration guides.
development
forge-caveman
Toggle terse output for Forge pipeline messages. Reduces prose by 40-70% per message (4-10% total session token savings). Use when you want briefer output. Trigger: /forge-caveman [mode], caveman mode, less tokens, be brief
devops
forge-commit
[writes] Generate terse conventional commit messages from staged changes. Use when you have staged files and want a well-structured commit message that follows Conventional Commits format. Analyzes diffs, infers type and scope, presents options.
development
forge-compression-help
Quick reference card for all Forge compression features -- output modes, inter-agent compression, input compression, and configuration. Use when you need a reminder of compression options or want to understand how compression works.
data-ai