Streamlines starting work on GitHub issues by fetching metadata and automating relevant skill activation.
Install
mkdir -p .claude/skills/issue && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12328" && unzip -o skill.zip -d .claude/skills/issue && rm skill.zipInstalls to .claude/skills/issue
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Start working on a GitHub issue. Fetches the issue details and automatically activates the relevant development skills based on issue labels. Use when the user says "work on issue #N", "start issue N", or invokes /issue <number>. Requires a GitHub issue number as argument.Key capabilities
- →Fetch GitHub issue details using gh CLI
- →Activate component skills based on issue labels
- →Suggest creating or switching to a feature branch
- →Fetch and parse implementation progress from issue comments
- →Update implementation progress in issue comments
- →Present a summary of the issue with progress details
How it works
The skill fetches GitHub issue details, activates relevant component skills based on labels, manages feature branch creation, and tracks/updates implementation progress within issue comments.
Inputs & outputs
When to use issue
- →Start work on a new feature
- →Automate workflow setup for bug fixes
- →Synchronize implementation progress from GitHub comments
About this skill
Work on GitHub Issue
You have been asked to start working on a GitHub issue. Follow these steps:
Step 1 — Fetch the issue
Run this command to get the issue details (replace <number> with the argument):
gh issue view <number> --json number,title,body,state,labels,assignees
If the command fails, inform the user and stop.
Step 2 — Activate component skills based on labels
Inspect the labels array from the response. For each label whose name
matches a component tag, invoke the corresponding skill using the Skill tool:
| Label name | Skill to invoke |
|---|---|
component: api | api-dev |
component: plugin | plugin-dev |
Invoke all matching skills. If neither label is present, skip this step (the user may activate skills manually if needed).
Step 3 — Create the feature branch (if needed)
Check the current git branch. If you are NOT already on a branch that
references this issue number (e.g., feature/<number>-*), ask the user
whether they want to create or switch to one.
Step 4 — Fetch implementation progress from comments
Check the issue comments for an existing implementation progress todo list:
gh api repos/{owner}/{repo}/issues/<number>/comments --jq '.[] | select(.body | contains("## Implementation progress")) | {id: .id, body: .body}'
If found:
- Parse the todo list (lines matching
- [x]and- [ ]) - Present it to the user as the current status, clearly separating done and remaining items
- Throughout the session, update the comment when tasks are completed:
gh api repos/{owner}/{repo}/issues/<number>/comments/<comment_id> \
-X PATCH -f body='<updated body with checkboxes toggled>'
If not found, skip this step — the user may add one later.
Step 5 — Present the issue summary
After activating the skills, present the issue to the user in this format:
## Issue #<number>: <title>
**State:** <state>
**Labels:** <comma-separated label names>
**Assignees:** <comma-separated assignee logins, or "none">
<issue body, rendered as markdown>
If an implementation progress comment was found in Step 4, append:
### Implementation progress
**Done:**
- item 1
- item 2
**Remaining:**
- item 3
- item 4
Then ask the user how they would like to proceed with the implementation.
When not to use it
- →When a GitHub issue number is not provided
- →When the gh CLI command fails to fetch issue details
- →When the user does not want to work on a GitHub issue
Limitations
- →Requires a GitHub issue number as argument
- →Requires gh CLI to be installed and authenticated
- →Only activates skills for 'component: api' and 'component: plugin' labels
How it compares
This skill simplify the process of starting work on a GitHub issue by automating information retrieval, skill activation, and progress tracking, which is more integrated than manual steps.
Compared to similar skills
issue side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| issue (this skill) | 0 | 4mo | Review | Intermediate |
| jira | 11 | 6mo | No flags | Beginner |
| triaging-issues | 5 | 2mo | Review | Intermediate |
| landing | 0 | 3mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
jira
davila7
Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.
triaging-issues
pytorch
Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.
landing
hoangsonww
End-of-session ritual. Close finished beads, file new ones for remaining work, run verify, commit in logical groupings, push. Work is not complete until git push succeeds.
ck
wanzicong
Claude Code 的每个项目持久化记忆。在会话启动时自动加载项目上下文,通过 git 活动追踪会话,并写入原生记忆。命令运行确定性的 Node.js 脚本——行为在不同模型版本间保持一致。
project-state-init
luck7x
初始化 Codex 项目“项目记忆/状态管理”套件到当前项目根目录:复制 `AGENTS.md` 与 `.codex/skills/*`(handoff / handoff-resume / ops-sync 等)并可选生成 `.codex/state` 骨架。用于新项目快速启用长期项目工作流(ops-sync、handoff、审计)。
gsd-ns-manage
rafaelribeiro96
config workspace | workstreams thread update ship inbox