skills/sprint-status/SKILL.md
Track parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.
npx skillsauth add rohitg00/pro-workflow sprint-statusInstall 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.
When running multiple Claude Code sessions in parallel, confusion is the enemy. This skill ensures every session identifies itself and every step reports its state.
Every response that involves a decision, plan, or significant action starts with orientation:
SESSION: my-app | branch: feat/auth | task: Add JWT refresh tokens
This takes one line. It costs almost nothing. It prevents the user from applying feedback to the wrong session.
Check for sibling Claude Code processes:
pgrep -af "claude" | grep -v "$$" | head -5
Or check for active worktrees:
git worktree list 2>/dev/null
Or look for session markers (written by session-start.js / session-end.js):
ls $TMPDIR/pro-workflow/sessions/ 2>/dev/null | tail -5
If multiple sessions are detected, always include the session identification header. If only one session is running, include it at task boundaries and before presenting options.
End every major step with exactly one status line. No ambiguity.
All work for the current step is done. Ready to commit, merge, or move to the next task.
STATUS: COMPLETE
Changed: src/auth/refresh.ts, src/auth/refresh.test.ts
Tests: 14 pass, 0 fail
Ready to commit.
Done, but flagging something the user should know about.
STATUS: COMPLETE_WITH_NOTES
Changed: src/api/upload.ts
Tests: 8 pass, 0 fail
Notes:
- Upload size limit is hardcoded to 10MB, should be configurable
- No rate limiting on this endpoint yet (separate task)
Notes are for things that work but could be better. Not blockers — observations.
Cannot proceed without user input or an external dependency.
STATUS: BLOCKED
Blocker: Need database migration approved before writing the ORM layer
Waiting on: DBA approval for schema change in migrations/0042_add_tokens.sql
Can continue: Nothing else in this task until unblocked
Missing context to make a good decision. Asking before guessing.
STATUS: NEEDS_INFO
Question: Should refresh tokens expire after 7 days or 30 days?
Impact: Changes token cleanup job schedule and storage requirements
Default if no preference: 7 days (more secure, standard practice)
Always provide a sensible default so the user can say "go with the default" without context-switching into the decision.
Session 1: feat/auth → implementing JWT refresh
Session 2: feat/auth-tests → writing test suite for auth module
Both sessions work on the same feature but don't touch the same files. Session 2 can start writing tests against the interface before Session 1 finishes the implementation.
Session 1: feat/upload → file upload endpoint
Session 2: feat/billing → billing webhook handler
Session 3: fix/login-bug → login redirect fix
Completely independent. Merge order doesn't matter.
Session 1: feat/base-types → shared type definitions (must merge first)
Session 2: feat/api → API layer (depends on Session 1)
Session 3: feat/ui → UI layer (depends on Session 1)
Session 1 merges first. Sessions 2 and 3 rebase after. Flag the dependency in every status update.
| Event | Include Status? | |-------|----------------| | File edit completed | No (too granular) | | Test suite run | Yes, if pass/fail changed | | Phase completed (research, plan, implement) | Yes | | Presenting options to user | Yes (with session header) | | Hitting a blocker | Yes, immediately | | Before asking a question | Yes (NEEDS_INFO) | | After committing | Yes (COMPLETE) | | End of session | Yes (final status) |
When the user asks for status across sessions, compile a sprint view:
SPRINT STATUS
Session 1: feat/auth STATUS: COMPLETE (ready to merge)
Session 2: feat/upload STATUS: BLOCKED (waiting on S3 creds)
Session 3: fix/login-bug STATUS: COMPLETE_WITH_NOTES (works, needs perf review)
## Sprint Status
Every decision and plan starts with: SESSION: project | branch | task
End major steps with STATUS: COMPLETE | COMPLETE_WITH_NOTES | BLOCKED | NEEDS_INFO
NEEDS_INFO always includes a sensible default.
When parallel sessions are detected, always include session headers.
documentation
Apply clear-writing standards to any prose the agent produces - READMEs, docs, UI copy, error messages, commit and PR text, release notes. Use when writing or editing documentation, interface copy, or any text a human will read. Says "write the README", "improve this copy", "draft the docs", "word this error".
development
Drive a change through a red-green-refactor loop - failing test first, minimal code to pass, then clean up. Use when implementing a feature or fixing a bug where correctness matters and a test can pin the behavior. Says "TDD", "test first", "red green refactor", "write the test first".
tools
The index of every pro-workflow skill and command, grouped by job, with when to reach for each and whether it is human-run or auto-triggered. Use when you are not sure which skill fits, want the full map, or ask "what can this do", "which skill for X", "list the workflow".
development
Audit an area of the codebase and propose the smallest structural moves that improve it - untangle boundaries, kill duplication, fix seams, break cycles. Produces a prioritized plan and decision records, not a rewrite. Use when a codebase feels tangled, hard to change, or is becoming a ball of mud, or when asked to improve or refactor architecture.