skills/forge-sprint/SKILL.md
[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.
npx skillsauth add quantumbitcz/dev-pipeline forge-sprintInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Dispatch the sprint orchestrator to analyze and execute multiple features in parallel.
See shared/skill-contract.md for the standard exit-code table.
Before any action, verify:
git rev-parse --show-toplevel 2>/dev/null. If fails: report "Not a git repository. Navigate to a project directory." and STOP..claude/forge.local.md exists. If not: report "Forge not initialized. Run /forge-init first." and STOP..forge/sprint-state.json for status != complete|failed. If active sprint found, offer resume via AskUserQuestion: "Active sprint found ({sprint_id}, {N} features, {status}). Resume / Start fresh / Abort".forge/ directory exists (create if not)After dispatch, fg-090-sprint-orchestrator will:
Total time: 15-60 minutes depending on feature count and complexity. Features with shared file conflicts run sequentially.
/forge-sprint -- reads current active Linear cycle
/forge-sprint CYC-42 -- reads specific Linear cycle
/forge-sprint "Feature A" "Feature B" -- manual feature list
dispatch fg-090-sprint-orchestrator "$ARGUMENTS"
The sprint orchestrator handles everything from here -- gathering features, analyzing independence, getting user approval, dispatching pipelines, and coordinating merges.
If $ARGUMENTS contains --resume or the pre-flight check found an active sprint:
dispatch fg-090-sprint-orchestrator "--resume"
The sprint orchestrator reads .forge/sprint-state.json and resumes from where it left off.
| Condition | Action |
|-----------|--------|
| Prerequisites fail | Report specific error message and STOP |
| No features provided and Linear unavailable | Ask user to provide features manually: /forge-sprint "Feature A" "Feature B" |
| Sprint orchestrator dispatch fails | Report "Sprint orchestrator failed to start. Check plugin installation." and STOP |
| Active sprint conflict | Offer resume, fresh start, or abort via AskUserQuestion |
| Individual feature pipeline fails | Sprint orchestrator handles per-feature failure. Failed features do not block others |
| State corruption | Suggest /forge-recover repair for state.json issues, or /forge-recover reset to start fresh |
/forge-run -- Run a single feature (use --sprint flag for quick parallel dispatch)/forge-shape -- Shape vague features into structured specs before sprinting/forge-status -- Check progress of active sprint runs/forge-abort -- Stop an active sprint gracefullydevelopment
[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.
tools
[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.
development
[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
[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.