Skills for Real Engineers. Straight from my .agents directory.
os-big-picture
Agent skill fromkharmanskyi/open-steps
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.
How to install os-big-picture
npx skills add kharmanskyi/open-steps# or add only this skill to Claude Code: copy the folder
skills/os-big-picture/
# into
~/.claude/skills/os-big-picture/ (all projects)
.claude/skills/os-big-picture/ (one project)
1# os-big-picture23One file, `BIG-PICTURE.md`, where `os-whats-next` already looks for a backlog.4It answers "where are we now" - not a plan, nothing in it a promise. Write it5in the user's language; paths stay English.67**When to use it.** The user asks where the project stands, or there is no8`BIG-PICTURE.md` yet → the full pass: describe, census, signals, backlog. A9session report was just written → the fold-in: only the rows that session10touched. Both re-measure, because a session that moves no row is the one after11which the dates go quietly stale.1213## Step 1 - find the file, and never clobber it1415`BIG-PICTURE.md` in the project root, and it may already be somebody's own16work. Everything this skill writes lives between `<!-- open-steps:begin -->`17and `<!-- open-steps:end -->`; no markers → append at the end; no file → create18it, and add it to this clone's ignore list, never to `.gitignore`:1920```bash21f=BIG-PICTURE.md; e="$(git rev-parse --git-dir)/info/exclude"22git check-ignore -q "$f" || git ls-files --error-unmatch "$f" >/dev/null 2>&1 \23 || grep -qxF "$f" "$e" 2>/dev/null || printf '%s\n' "$f" >> "$e"24```2526Each of the three is a reason to leave it alone. Say in one line that you did27it; `git add -f BIG-PICTURE.md` shares it instead. Never read `Last worked on`28or `Signal` back out of the file - only `Stage` and the queue carry forward.2930## Step 2 - the census, measured by the script3132```bash33bash ${CLAUDE_SKILL_DIR}/scripts/census.sh .34```35…
Excerpt shown under the repository's MIT license.
More skills in open-steps
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
