Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
日本語の概要は準備中です。原文の説明を表示しています。
Use when creating, searching, updating, or managing GitHub issues via CLI. Triggers: "issue", "create issue", "gh issue", "task tracking", "context", "handoff", "resume task", "session context", "save progress", "active tasks", "in-progress", "my tasks", "open issues". Covers: gh commands, bulk operations, JSON/jq, search filters, issue-to-PR workflow, AI session context storage, task workflow with labels.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Efficient GitHub Issues management via gh CLI with AI session context storage.
| Task | Command |
|---|---|
| Create issue | gh issue create -t "Title" -b "Body" -l bug -a @me |
| Active tasks | gh issue list -l in-progress -s open |
| List open bugs | gh issue list -l bug -s open |
| View as JSON | gh issue view 123 --json number,title,body,labels,state |
| Close with comment | gh issue close 123 -c "Fixed in #456" |
| Edit labels | gh issue edit 123 --add-label priority:high |
| Start work | gh issue edit 45 --add-label in-progress |
| Create branch | gh issue develop 123 --checkout |
| Load context | gh issue view 45 --json comments --jq '.comments[] | select(.body | contains("AI-CONTEXT"))' |
Always use --json for parsing. Fields: number, title, body, state, labels, assignees, milestone, author, createdAt, updatedAt, comments, url.
gh issue view 123 --json number,title,labels,state
gh issue list --json number,title,labels --jq '.[] | select(.labels[].name == "bug")'
gh issue list -l bug --json number --jq '.[].number'
gh issue list --search "is:open author:username"
gh issue list --search "created:>=2026-01-01 created:<=2026-01-07"
gh issue list --search "label:bug label:priority:high"
gh issue list --search "is:open -label:wontfix"
gh issue list --search "milestone:v2.0"
gh issue edit 10 15 20 --add-label "priority:high"
gh issue close 10 15 20 -c "Duplicate of #5"
gh issue list -l needs-triage --json number --jq '.[].number' | \
xargs -I{} gh issue edit {} --add-label reviewed
gh issue develop 123 --checkout # Create branch from issue
git add . && git commit -m "fix: #123" # Commit with reference
gh pr create --fill # Create PR (auto-links)
gh issue close 123 -c "Fixed in PR #456" # Close when merged
gh api repos/:owner/:repo/milestones --jq '.[].title'
gh issue edit 123 -m "v2.0"
Store session context in GitHub issues for seamless task handoff.
# Get AI context from issue comments
gh issue view 45 --json comments --jq '
.comments[] | select(.body | contains("AI-CONTEXT:START")) | .body
'
# Get comment ID for updates
gh issue view 45 --json comments --jq '
.comments[] | select(.body | contains("AI-CONTEXT:START")) | .id
'
# Create new context comment
gh issue comment 45 --body-file .ai-context.md
# Update existing (replace COMMENT_ID)
gh api repos/:owner/:repo/issues/comments/COMMENT_ID \
--method PATCH -f body="$(cat .ai-context.md)"
See references/context-template.md for full template. Minimal version:
<!-- AI-CONTEXT:START -->
## Context | IN_PROGRESS
**Files:** `file.py:45`, `other.py:120`
**Done:** task1, task2
**Next:** next task
**Resume:** One-line summary for cold start
<!-- AI-CONTEXT:END -->
Manage issue lifecycle with labels.
| Label | Meaning |
|---|---|
backlog | In queue |
in-progress | Active work |
blocked | Blocked |
review | Needs review |
# My active issues
gh issue list -l in-progress -s open
# All my assigned issues
gh issue list --assignee @me -s open
# Issues with context
gh issue list -s open --json number,title,labels --jq '
.[] | select(.labels[].name == "in-progress") | "#\(.number): \(.title)"
'
# Mark as in-progress
gh issue edit 45 --add-label in-progress --remove-label backlog
# View issue + load context
gh issue view 45 --json number,title,body,comments --jq '{
number, title, body,
context: (.comments[] | select(.body | contains("AI-CONTEXT")) | .body) // "No context"
}'
# Mark as blocked
gh issue edit 45 --add-label blocked --remove-label in-progress
# Add blocking comment
gh issue comment 45 --body "Blocked: waiting for API access"
# Close with comment
gh issue close 45 -c "Done in commit abc123"
# Or close via PR (auto-closes if PR body contains "Fixes #45")
gh issue create -t "Simplify bot flow" -b "## Problem
Bot stopped converting. Current flow is complex.
## Reference
Simple flow example from competitor.
## Tasks
- [ ] Analyze current flow
- [ ] Create new diagram
- [ ] Implement"
# 1. View issue with context
gh issue view 45 --json number,title,body,comments --jq '{
number, title, body,
context: (.comments[] | select(.body | contains("AI-CONTEXT")) | .body) // "No context"
}'
# 2. Create branch
gh issue develop 45 --checkout
# 3. Work...
# Create context file
cat > .ai-context.md << 'EOF'
<!-- AI-CONTEXT:START -->
## AI Session Context
_Last updated: 2026-01-07 16:00_
### Status
**IN_PROGRESS**
### Progress
- [x] Analyzed current flow
- [ ] Create new diagram
### Key Files
- `handlers/start.py:45-78` — start handler
- `data/courses.yaml` — config
### Next Steps
1. Draw simplified flow
2. Implement changes
### Resume Context
Simplifying bot flow. Analyzed current state. Next: create diagram.
<!-- AI-CONTEXT:END -->
EOF
# Save to issue
gh issue comment 45 --body-file .ai-context.md
# Load context
CONTEXT=$(gh issue view 45 --json comments --jq '
.comments[] | select(.body | contains("AI-CONTEXT")) | .body
' 2>/dev/null)
echo "$CONTEXT"
# Continue from where you left off...
| Mistake | Fix |
|---|---|
Missing --json | Always --json field1,field2 |
| Loop instead of multi-arg | gh issue edit 1 2 3 |
Using grep on output | Use --jq |
Forgot -s all for closed | Default is open only |
{owner}/{repo} in API | Use :owner/:repo |
| Duplicate context comments | Update existing, don't create new |
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
日本語の概要は準備中です。原文の説明を表示しています。
Audits the agent rules in the current folder (AGENTS.md, nested AGENTS.md files) and the skill descriptions the agent sees at start, then reports what to cut, move or rewrite and edits only after the user says yes. Use on «аудит правил», «проверь AGENTS.md», «почему агент не слушается правил», «проверь скиллы».
日本語の概要は準備中です。原文の説明を表示しています。
Робот агента Personal Corp. Агент делает себе голову робота из набора деталей, хранит её в штабе в stack/avatars.json и кладёт в штаб страницу avatar/robot.html, где робот стоит за партой своего штаба и вокруг видны отделы, без сервера и интернета. На уроке по ссылке входа с экрана урока робот входит в живой класс и горит маячком, пока агент работает. Триггеры /avatar, /avatar <ссылка входа>, сделай себе аватар, покажи своего робота, приди на урок.
日本語の概要は準備中です。原文の説明を表示しています。
Use when choosing between engines or models for an agent pipeline and the answer must come from measurement on your own data, not from marketing pages: speech recognition for meeting recordings, the model that turns a transcript into notes, the critic model that checks it. Runs every variant in an isolated container, measures time, cost per hour of input (USD and RUB, with price source and date) and quality (WER/CER and course terms for ASR; code checks plus a judge of a different model for LLM steps), writes results.json/csv and one static analytics page. Triggers on "бенчмарк", "сравни движки", "сколько стоит час записи", "какую модель взять для пайплайна", "benchmark the pipeline", "compare ASR engines".
日本語の概要は準備中です。原文の説明を表示しています。
Use when user asks for Claude Code usage stats, weekly analytics, project activity summary, or wants to see what projects were worked on. Triggers on "аналитика", "статистика claude", "cc stats", "weekly report", "что делал"
日本語の概要は準備中です。原文の説明を表示しています。
Use when needing strategic project analysis from multiple independent expert perspectives. Triggers on business decisions, growth strategy, product direction, competitive analysis, or any situation where diverse C-level opinions reduce blind spots
日本語の概要は準備中です。原文の説明を表示しています。