Engineering retrospective. Analyzes commit history, work patterns, code quality metrics, session detection, streak tracking. Triggers: "/retro", "weekly retro", "what did we ship", "engineering retrospective".
From superomninpx claudepluginhub wilder1222/superomni --plugin superomniThis skill is limited to using the following tools:
SKILL.md.tmplSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
mkdir -p ~/.omni-skills/sessions
_PROACTIVE=$(~/.claude/skills/superomni/bin/config get proactive 2>/dev/null || echo "true")
_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
_TEL_START=$(date +%s)
echo "Branch: $_BRANCH | PROACTIVE: $_PROACTIVE"
If PROACTIVE is false: do NOT proactively suggest skills. Only run skills the
user explicitly invokes. If you would have auto-invoked, say:
"I think [skill-name] might help here — want me to run it?" and wait.
Report status using one of these at the end of every skill session:
Pipeline stage order: THINK → PLAN → REVIEW → BUILD → VERIFY → SHIP → REFLECT
REVIEW is the only human gate. All other stages auto-advance on DONE.
| Status | At REVIEW stage | At all other stages |
|---|---|---|
| DONE | STOP — present review summary, wait for user input (Y / N / revision notes) | Auto-advance — print [STAGE] DONE → advancing to [NEXT-STAGE] and immediately invoke next skill |
| DONE_WITH_CONCERNS | STOP — present concerns, wait for user decision | STOP — present concerns, wait for user decision |
| BLOCKED / NEEDS_CONTEXT | STOP — present blocker, wait for user | STOP — present blocker, wait for user |
When auto-advancing:
docs/superomni/[STAGE] DONE → advancing to [NEXT-STAGE] ([skill-name])When the user sends a follow-up message after a completed session, before doing anything else:
ls docs/superomni/specs/spec-*.md docs/superomni/plans/plan-*.md docs/superomni/ .superomni/ 2>/dev/null | head -20
git log --oneline -3 2>/dev/null
To find the latest spec or plan:
_LATEST_SPEC=$(ls docs/superomni/specs/spec-*.md 2>/dev/null | sort | tail -1)
_LATEST_PLAN=$(ls docs/superomni/plans/plan-*.md 2>/dev/null | sort | tail -1)
workflow skill for stage → skill mapping) and announce:
"Continuing in superomni mode — picking up at [stage] using [skill-name]."using-skills/SKILL.md.When asking the user a question, match the confirmation requirement to the complexity of the response:
| Question type | Confirmation rule |
|---|---|
| Single-choice — user picks one option (A/B/C, 1/2/3, Yes/No) | The user's selection IS the confirmation. Do NOT ask "Are you sure?" or require a second submission. |
| Free-text input — user types a value and presses Enter | The submitted text IS the confirmation. No secondary prompt needed. |
| Multi-choice — user selects multiple items from a list | After the user lists their selections, ask once: "Confirm these selections? (Y to proceed)" before acting. |
| Complex / open-ended discussion — back-and-forth clarification | Collect all input, then present a summary and ask: "Ready to proceed with the above? (Y/N)" before acting. |
Rule: never add a redundant confirmation layer on top of a single-choice or text-input answer.
Custom Input Option Rule: Whenever you present a predefined list of choices (A/B/C, numbered options, etc.), always append a final "Other" option that lets the user describe their own idea:
[last letter/number + 1]) Other — describe your own idea: ___________
When the user selects "Other" and provides their custom text, treat that text as the chosen option and proceed exactly as you would for any other selection. If the custom text is ambiguous, ask one clarifying question before proceeding.
Load context progressively — only what is needed for the current phase:
| Phase | Load these | Defer these |
|---|---|---|
| Planning | Latest docs/superomni/specs/spec-*.md, constraints, prior decisions | Full codebase, test files |
| Implementation | Latest docs/superomni/plans/plan-*.md, relevant source files | Unrelated modules, docs |
| Review/Debug | diff, failing test output, minimal repro | Full history, specs |
If context pressure is high: summarize prior phases into 3-5 bullet points, then discard raw content.
All skill artifacts are written to docs/superomni/ (relative to project root).
See the Document Output Convention in CLAUDE.md for the full directory map.
Agent failures are harness signals — not reasons to retry the same approach:
harness-engineering skill to update the harness before retrying.It is always OK to stop and say "this is too hard for me." Escalation is expected, not penalized.
After completing any skill session, run a 3-question self-check before writing the final status:
If any answer is NO, address it before reporting DONE. If it cannot be addressed, report DONE_WITH_CONCERNS and name the gap.
For a full performance evaluation spanning the entire sprint, use the self-improvement skill.
_TEL_END=$(date +%s)
_TEL_DUR=$(( _TEL_END - _TEL_START ))
~/.claude/skills/superomni/bin/analytics-log "SKILL_NAME" "$_TEL_DUR" "OUTCOME" 2>/dev/null || true
Nothing is sent to external servers. Data is stored only in ~/.omni-skills/analytics/.
Goal: Understand what was shipped, patterns in how you work, and trends over time.
/retro — last 7 days (default)/retro 24h — last 24 hours/retro 14d — last 14 days/retro 30d — last 30 days/retro compare — compare this period vs prior period# Ensure we're up to date
DEFAULT_BRANCH=$(git remote show origin 2>/dev/null | grep "HEAD branch" | cut -d: -f2 | tr -d ' ' || echo "main")
git fetch origin "${DEFAULT_BRANCH}" --quiet 2>/dev/null || true
# Get author identity
AUTHOR_NAME=$(git config user.name)
AUTHOR_EMAIL=$(git config user.email)
echo "Retrospective for: ${AUTHOR_NAME} <${AUTHOR_EMAIL}>"
# Set period (adjust SINCE based on argument)
SINCE="7 days ago" # change based on /retro argument
# Commit log for the period
git log --oneline --since="${SINCE}" --author="${AUTHOR_EMAIL}" 2>/dev/null | head -100
# Detailed stats
git log --since="${SINCE}" --author="${AUTHOR_EMAIL}" \
--pretty=format:"%h|%ad|%s" --date=short \
--numstat 2>/dev/null | head -200
Calculate and display:
METRICS
════════════════════════════════════════
Period: [date range]
Commits: [N]
Net LOC: +[N] added / -[N] deleted
Files changed: [N unique files]
Active days: [N out of N days in period]
# Commit count
git log --oneline --since="${SINCE}" --author="${AUTHOR_EMAIL}" | wc -l
# LOC stats
git log --since="${SINCE}" --author="${AUTHOR_EMAIL}" \
--pretty=tformat: --numstat | \
awk '{ add += $1; del += $2 } END { printf "+%s / -%s\n", add, del }'
# Active days
git log --since="${SINCE}" --author="${AUTHOR_EMAIL}" \
--pretty=format:"%ad" --date=short | sort -u | wc -l
Identify work sessions (gap threshold: 45 minutes between commits = new session):
# Get commit timestamps in epoch seconds
git log --since="${SINCE}" --author="${AUTHOR_EMAIL}" \
--pretty=format:"%at" | sort -n
From timestamps, calculate:
Show when work happens (hourly histogram):
git log --since="${SINCE}" --author="${AUTHOR_EMAIL}" \
--pretty=format:"%ad" --date=format:"%H" | \
sort | uniq -c | sort -k2 -n
Display as a simple bar chart:
00 ██ (2)
09 ████████ (8)
10 ██████████████ (14)
...
Classify commits by conventional commit type:
git log --oneline --since="${SINCE}" --author="${AUTHOR_EMAIL}" | \
grep -oE "^[a-f0-9]+ (feat|fix|refactor|test|docs|chore|build|ci)" | \
awk '{print $2}' | sort | uniq -c | sort -rn
Commit types:
feat: [N] ([%])
fix: [N] ([%])
refactor: [N] ([%])
test: [N] ([%])
other: [N] ([%])
Top most-changed files in the period:
git log --since="${SINCE}" --author="${AUTHOR_EMAIL}" \
--pretty=tformat: --name-only | \
sort | uniq -c | sort -rn | head -10
Calculate consecutive active days:
# Get all active dates in the last 90 days
git log --since="90 days ago" --author="${AUTHOR_EMAIL}" \
--pretty=format:"%ad" --date=short | sort -u
Report:
Streak: [N] consecutive active days
Best streak: [N days] (dates)
Identify the most significant commit (by diff size or PR merge):
git log --since="${SINCE}" --author="${AUTHOR_EMAIL}" \
--pretty=format:"%h %s" --shortstat | head -30
RETRO_DIR=".context/retros"
mkdir -p "${RETRO_DIR}"
RETRO_FILE="${RETRO_DIR}/$(date +%Y-%m-%d).md"
Write the full report to the file and print a summary.
If /retro compare was invoked:
# Current period vs prior period
# Current: last 7 days
# Prior: 7-14 days ago
git log --since="14 days ago" --until="7 days ago" \
--author="${AUTHOR_EMAIL}" --oneline | wc -l
Show delta for each metric: ↑ 23% commits, ↓ 10% LOC, etc.
RETRO REPORT — [period]
════════════════════════════════════════
Commits: [N]
Net LOC: +[N] / -[N]
Active days: [N/7]
Sessions: [N] (~[avg]h each)
Streak: [N] days
Commit types: feat [N] | fix [N] | refactor [N] | test [N]
Ship of the week:
[commit message and impact]
Hottest files:
[file 1] — [N changes]
[file 2] — [N changes]
Peak hours: [hour range]
[if compare]
vs last period: commits [+/-N%] | LOC [+/-N%] | sessions [+/-N]
Saved to: [retro file path]
════════════════════════════════════════