Os Big Picture
ALWAYS invoke this skill when the user asks where the project as a whole stands -...
Install
npx skills add kharmanskyi/open-steps --skill os-big-picture -g -a claude-code -y- Repository
- kharmanskyi/open-steps1.3k
- Category
- Git and review
- Updated
- 1mo ago
- License
- MIT
- Context cost
- Mediumabout 1,634 tokens
- Runs scripts
- Yes, review before use
What it does
ALWAYS invoke this skill when the user asks where the project as a whole stands - "where are we", "what's the big picture", "what have we built", "what is in this project", "map the project", "what does this thing even do", "what is stale", "what can we delete", "update the roadmap" - in any language, and whenever a session report has just been written. It keeps one file, BIG-PICTURE.md: what the product is, every feature with how far it got, which parts nobody has touched, and what is queued next. Age and wiring are measured from git; how far a feature got comes from the reports or says "not checked". Where a tracker is connected it offers to open the queue as tickets, after a yes and never before. Never invents work, never deletes code.
os-big-picture
One file, BIG-PICTURE.md, where os-whats-next already looks for a backlog.
It answers "where are we now" - not a plan, nothing in it a promise. Write it
in the user's language; paths stay English.
When to use it. The user asks where the project stands, or there is no
BIG-PICTURE.md yet → the full pass: describe, census, signals, backlog. A
session report was just written → the fold-in: only the rows that session
touched. Both re-measure, because a session that moves no row is the one after
which the dates go quietly stale.
Step 1 - find the file, and never clobber it
BIG-PICTURE.md in the project root, and it may already be somebody's own
work. Everything this skill writes lives between <!-- open-steps:begin -->
and <!-- open-steps:end -->; no markers → append at the end; no file → create
it, and add it to this clone's ignore list, never to .gitignore:
f=BIG-PICTURE.md; e="$(git rev-parse --git-dir)/info/exclude"
git check-ignore -q "$f" || git ls-files --error-unmatch "$f" >/dev/null 2>&1 \
|| grep -qxF "$f" "$e" 2>/dev/null || printf '%s\n' "$f" >> "$e"
Each of the three is a reason to leave it alone. Say in one line that you did
it; git add -f BIG-PICTURE.md shares it instead. Never read Last worked on
or Signal back out of the file - only Stage and the queue carry forward.
Step 2 - the census, measured by the script
bash ${CLAUDE_SKILL_DIR}/scripts/census.sh .
Where your tool does not set ${CLAUDE_SKILL_DIR}, run it from the project
root as bash <this skill's folder>/scripts/census.sh .. If it cannot run at
all, say so and mark every measured column "not checked"; never estimate them.
An AGE line, then one measured PART row per part: path, last worked on,
commits in six months, whether anything outside reaches it, the signal.
