kramme-cc-workflow/skills/kramme:session:wrap-up/SKILL.md
End-of-session checklist to capture progress, ensure quality, and document next steps. Writes a session summary to SESSION_NOTES.md at the repo root (creating or appending), or appends to siw/LOG.md when an SIW project exists.
npx skillsauth add abildtoft/kramme-cc-workflow kramme:session:wrap-upInstall 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.
A structured end-of-session ritual that ensures nothing is forgotten and captures context for future sessions.
Run git status and report:
git stash list for forgotten stashesSearch for TODOs added during this session.
Uncommitted changes:
git diff --unified=0 | grep -E "^\+.*TODO"
Recent commits — prefer the session's actual start point when determinable (the merge-base with the base branch); otherwise fall back to the last 5 commits:
default=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/@@')
base=""
if [ -n "$default" ]; then
base=$(git merge-base HEAD "$default" 2>/dev/null || true)
[ "$base" = "$(git rev-parse HEAD)" ] && base="" # on the base branch itself; no branch scope
fi
scope="this session"
if [ -z "$base" ]; then
base=$(git rev-parse --verify --quiet HEAD~5 || git rev-list --max-parents=0 HEAD | head -1)
scope="last 5 commits"
fi
git diff "$base" --unified=0 | grep -E "^\+.*TODO"
Report any TODOs found with file locations. When the HEAD~5 fallback was used, label the findings "last 5 commits" (from $scope) instead of "this session" — the window is a proxy, not the actual session start.
Scan recent changes for explicit markers, reusing $base and $scope from TODO detection:
git diff "$base" --unified=0 | grep -E "^\+.*(WIP|FIXME|XXX)"
Then spot-check modified files by judgment for commented-out code blocks and empty or placeholder function bodies. Report anything found.
If there are uncommitted changes, offer to run quality checks:
question: "Run quality checks on uncommitted changes?"
options:
- label: "Yes, run checks"
description: "Run lint, typecheck, and tests on affected code"
- label: "Skip"
description: "Skip quality checks"
If user selects "Yes", invoke /kramme:verify:run and report results.
Prompt the user for session documentation:
question: "What was accomplished this session?"
freeform: true
placeholder: "Brief summary of completed work..."
question: "What are the logical next steps?"
freeform: true
placeholder: "What should be done next session..."
question: "Any blockers or open questions?"
freeform: true
placeholder: "Leave empty if none..."
optional: true
Build the session block, using the current date for the heading:
## Session: [current date]
**Accomplished:** [user's summary]
**Next steps:** [user's next steps]
**Blockers:** [if any, else "None"]
Append it to the active context log so the summary survives the session:
siw/LOG.md exists), append to siw/LOG.md.SESSION_NOTES.md at the repository root, creating the file if it does not exist.Remember the path written so Phase 5 can report it.
Present a summary:
## Session Wrap-Up Complete
### Changes Status
- Uncommitted files: N
- Untracked files: N
- Stashes: N
- TODOs found: N
- Quality checks: PASS/FAIL/SKIPPED
### Documentation
- Session notes: Saved to [path] / Not saved
### Reminders
[List any uncommitted work, failing tests, or blockers]
If user runs /kramme:session:wrap-up quick, skip the quality-check prompt (Phase 2) and run Phases 1, 3, 4, and 5 (audit, summary, context preservation, report).
development
Runs kramme:pr:code-review as a closeout review loop for local or PR branch changes before commit, ship, or final response. Use when the user asks for autoreview, second-model review, or a final code-review pass after non-trivial edits. Not for UX, visual, accessibility, or product review.
development
Guides topic-level understanding verification for a PR, branch, feature, document, spec, design decision, bug fix, or other concrete subject. Use when the user asks to confirm, quiz, drill, teach-and-check, or verify that they understand a topic. Maintains a topic-specific checklist artifact and requires demonstrated understanding before marking the topic complete. Not for ordinary explanations without verification, end-of-session summaries, or code/test correctness checks.
testing
Design a CI/CD pipeline with quality gates, a <10-minute budget, feature-flag lifecycle, and an exit checklist. Use when adding a new CI pipeline, changing gate configuration, or planning a rollout for a new service. Complementary to kramme:pr:fix-ci (which fixes failures in an existing pipeline). Covers gate ordering, secrets storage, branch protection, rollback mechanism, and staged-rollout guardrails — not a rollout-execution runbook.
tools
--- name: kramme:visual:demo-reel description: Capture local demo evidence for observable product behavior: screenshots, before/after image sets, browser reels, terminal recordings, and short GIF/video proof. Use when shipping UI changes, CLI features, or any change where PR reviewers would benefit from visual or behavioral evidence. argument-hint: "[what to capture] [--url <url>|auto] [--tier static|before-after|browser-reel|terminal-recording]" disable-model-invocation: true user-invocable: tr