Agent skill

Start Issue

by hmislk in hmislk/hmis

Full environment setup when starting work on a GitHub issue.

GPL-3.0Auto-check: notes

Install Start Issue

skills CLI
$ npx skills add hmislk/hmis --skill start-issue -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hmislk/hmis start-issue --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hmislk/hmis.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/start-issue .claude/skills/start-issue && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
start-issue
GitHub stars
236
Token cost
~1.5k tokens
SKILL.md length
559 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
GPL-3.0

At a glance

Full environment setup when starting work on a GitHub issue.

  • Works in 6 steps: Fetch Issue Title → Create Feature Branch from development → Set persistence.xml to Local JNDI → …
  • Beginning work on any new issue: start issue 20408
  • SKILL.md covers Arguments, Step 1 — Fetch Issue Title, Step 2 — Create Feature Branch… and Step 3 — Set persistence.xml…, plus 4 more sections
  • Calls gh and git

What it does

Start Issue is an agent skill from hmislk/hmis. Full environment setup when starting work on a GitHub issue. Creates a feature branch from origin/development, swaps persistence.xml to local JNDI settings, assigns the issue, and guides project board setup. Use when beginning work on any new issue: "start issue 20408", "/start-issue 20408", or "prepare env for issue 20408".

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with GitHub. The repository describes itself as: This is an Open Source Java EE based Hospital Information Management System. The licence is GPL-3.0.

When your agent uses it

  • Beginning work on any new issue: start issue 20408
  • /start-issue 20408
  • Prepare env for issue 20408

Example prompts

  • “start issue 20408”
  • “/start-issue 20408”
  • “prepare env for issue 20408”
  • “/start-issue”

Requirements

  • Pre-approved tools (allowed-tools): Bash, Read, Edit, Grep

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Fetch Issue Title
  2. Create Feature Branch from development
  3. Set persistence.xml to Local JNDI
  4. Assign Issue on GitHub
  5. Project Board (CareCode: HMIS Board)
  6. Summary

What it can do on your machine

Read from SKILL.md and the folder at commit d5d2020. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Edit
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Start Issue loads about 1.5k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 559 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Edit, Grep

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hmislk/hmis at commit d5d2020, republished under its GPL-3.0 licence (© hmislk). 559 words, ~1,493 tokens.

Download SKILL.mdSave it as .claude/skills/start-issue/SKILL.md (or your agent's skills folder).
name
start-issue
description
Full environment setup when starting work on a GitHub issue. Creates a feature branch from origin/development, swaps persistence.xml to local JNDI settings, assigns the issue, and guides project board setup. Use when beginning work on any new issue: "start issue 20408", "/start-issue 20408", or "prepare env for issue 20408".
allowed-tools
Bash, Read, Edit, Grep
disable-model-invocation
false
argument-hint
<issue-number> [short-description] [local-jndi-name]

Start Issue Workflow

Prepare the local development environment to fix a GitHub issue.

Arguments

  • $0 — Issue number (required, e.g. 20408)
  • $1 — Short kebab-case description (optional; derive from issue title if omitted)
  • $2 — Local JNDI datasource name (optional; read from persistence_for_local_testing.xml if omitted)

Step 1 — Fetch Issue Title

bash
gh issue view $0 --repo hmislk/hmis --json title,body --jq '.title'

Use the title to derive a short kebab-case description if $1 is not provided. Branch name format: $0-<short-description> (all lowercase, hyphens only).

Step 2 — Create Feature Branch from development

bash
git fetch origin
git checkout -b $0-<description> origin/development
git push -u origin $0-<description>

Rule: ALWAYS base on origin/development, never on master.

⚠️ Check current branch first. If git branch --show-current shows master, DO NOT proceed with uncommitted changes present — those changes will be carried onto the new branch and their ancestry will include master, causing PR conflicts. Instead, stash the changes (git stash), create the branch cleanly, then pop the stash (git stash pop).

Step 3 — Set persistence.xml to Local JNDI

Read the local JNDI name from: src/main/resources/META-INF/persistence_for_local_testing.xml

Look for the <jta-data-source> values — use those exact names.

Then update src/main/resources/META-INF/persistence.xml:

  • Replace ${JDBC_DATASOURCE} → the local main JNDI (e.g. jdbc/ruhunu)
  • Replace ${JDBC_AUDIT_DATASOURCE} → the local audit JNDI (e.g. jdbc/ruhunuAudit)

Do NOT commit this change. It stays local only. Before any push, revert to placeholders. Remember these JNDI names — after every push they must be restored immediately so the developer can test without any manual step.

Step 4 — Assign Issue on GitHub

bash
gh issue edit $0 --repo hmislk/hmis --add-assignee buddhika75

If the command fails with a scope error, inform the user that they need to run:

! gh auth refresh -s project

Step 5 — Project Board (CareCode: HMIS Board)

Make sure the issue is on project #11, set Status = In Progress, then read the status back. All three steps are mandatory: the update call's success response returns only the item ID, not the new value, so it is not proof that the change was saved. Issue #24105 was reported as "In Progress" from that response alone, but the board still showed Backlog.

The issue is often already on the board: the "Item added to project" automation puts new issues in Backlog. addProjectV2ItemById handles both cases. If the issue is already on the board, it returns the existing item instead of adding a duplicate.

Show full SKILL.md (212 more words)Show less
bash
# 1. Issue node ID
ISSUE_NODE=$(gh api repos/hmislk/hmis/issues/$0 --jq '.node_id')

# 2. Add to project #11, or get the existing item, and capture the item ID
ITEM_ID=$(gh api graphql -f query='
mutation($p:ID!,$c:ID!){ addProjectV2ItemById(input:{projectId:$p,contentId:$c}){ item{ id } } }' \
  -f p=PVT_kwDOAHw-zs4ApMln -f c="$ISSUE_NODE" --jq '.data.addProjectV2ItemById.item.id')

# 3. Set Status = In Progress
gh api graphql -f query='
mutation($p:ID!,$i:ID!){ updateProjectV2ItemFieldValue(input:{
  projectId:$p, itemId:$i,
  fieldId:"PVTSSF_lADOAHw-zs4ApMlnzggpN3k",
  value:{singleSelectOptionId:"47fc9ee4"} }){ projectV2Item{ id } } }' \
  -f p=PVT_kwDOAHw-zs4ApMln -f i="$ITEM_ID"

# 4. READ BACK: this output is the only thing that may be reported as the board status
gh api graphql -f query='
query($i:ID!){ node(id:$i){ ... on ProjectV2Item{
  fieldValueByName(name:"Status"){ ... on ProjectV2ItemFieldSingleSelectValue{ name updatedAt } } } } }' \
  -f i="$ITEM_ID" --jq '.data.node.fieldValueByName'

IDs, verified 2026-10-01: project PVT_kwDOAHw-zs4ApMln, Status field PVTSSF_lADOAHw-zs4ApMlnzggpN3k, "In Progress" option 47fc9ee4. If a mutation fails with an unknown or invalid ID error, re-query them: gh api graphql -f query='query{organization(login:"hmislk"){projectV2(number:11){id field(name:"Status"){... on ProjectV2SingleSelectField{id options{id name}}}}}}'

If step 4 does not print "name":"In Progress", do not retry silently and do not report success. Tell the user that the automated status change did not stick, show what the board actually holds, and ask them to set it manually at https://github.com/orgs/hmislk/projects/11.

If the token lacks the project scope (error: INSUFFICIENT_SCOPES), tell the user:

Action required: Your GitHub token lacks the project scope for board automation. Please add the issue to the board manually: https://github.com/orgs/hmislk/projects/11 Set Status = In Progress.

To enable automation in future, run: ! gh auth refresh -s project

Step 6 — Summary

Report what was done:

  • Branch name created and pushed
  • persistence.xml local JNDI set to (name)
  • Issue assigned to buddhika75
  • Project board status: quote the value read back in Step 5 step 4, or say that a manual change is needed. Never report the status from the update call's success response alone.

Remind the user: persistence.xml must be reverted to ${JDBC_DATASOURCE} before any git push. Check it directly (or let commit-code catch it — it verifies persistence.xml when staged).

Reference

See start-issue-workflow.md for full details.

© hmislk, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/start-issue of hmislk/hmis.

Open the folder on GitHubat commit d5d2020

Compare with similar skills

Start Issue next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Start Issue compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Start Issue this skillhmislk/hmis236—~1.5kAutomated safety check: NotesGPL-3.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Diagnosing Superpowers Sessionsobra/superpowers296k3 repos~1.7kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow83k5 repos~1.3kAutomated safety check: PassMIT
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
Update V8 Versionopeninterpreter/openinterpreter69k2 repos~845Automated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    296k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed
  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    83k GitHub starsUsed in 5 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • Update V8 Version

    openinterpreter/openinterpreter

    Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

    69k GitHub starsUsed in 2 repos~845 tokens
    DevOps & CloudAuto-check passed
  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.8k tokensUpdated today
    Research & ScienceAuto-check: notes

More from hmislk/hmis

All 33 skills in this repo
  • API Usage

    hmislk/hmis

    Reference for calling existing HMIS REST APIs. An agent skill from hmislk/hmis.

    236 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Application configuration options reference for the HMIS project.

    236 GitHub stars~474 tokensUpdated today
    Auto-check passed
  • Caveman

    hmislk/hmis

    Ultra-compressed communication mode. An agent skill from hmislk/hmis.

    236 GitHub starsUsed in 21 repos~946 tokens
    Auto-check passed
  • Database Guide

    hmislk/hmis

    MySQL database development guide for the HMIS project. An agent skill from hmislk/hmis.

    236 GitHub stars~664 tokensUpdated today
    Auto-check passed
  • Demo Video

    hmislk/hmis

    A skill your agent uses when asked to make a demo, training, how-to or tutorial video with sound or voice-over showing an HMIS function or configuration (e.g.

    236 GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Deploy QA

    hmislk/hmis

    Sync development into QA/testing environment branches (QA1-QA4, local RH staging) via PR + merge on GitHub.

    236 GitHub stars~2.1k tokensUpdated today
    Auto-check: notes

Works with

Questions about Start Issue

What does Start Issue do?

Full environment setup when starting work on a GitHub issue. Start Issue is an agent skill from hmislk/hmis. Full environment setup when starting work on a GitHub issue.

When should I use Start Issue?

Start Issue fits situations like: beginning work on any new issue: start issue 20408; /start-issue 20408; prepare env for issue 20408.

How do I install Start Issue in Claude Code?

Run `npx skills add hmislk/hmis --skill start-issue -a claude-code`. Or copy the skill folder (.claude/skills/start-issue in hmislk/hmis) into .claude/skills/start-issue in your project. Claude Code loads it when a task matches its description.

How do I install Start Issue in Codex?

Run `npx skills add hmislk/hmis --skill start-issue -a codex`. Or copy the skill folder (.claude/skills/start-issue in hmislk/hmis) into .agents/skills/start-issue in your project. Codex loads it when a task matches its description.

Can I use Start Issue in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hmislk/hmis --skill start-issue -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/start-issue, .gemini/skills/start-issue, .github/skills/start-issue and .opencode/skills/start-issue in your project.

What does Start Issue need to run?

Going by SKILL.md and its folder, Start Issue needs the command-line tools its instructions call (gh and git). Its frontmatter pre-approves these tools: Bash, Read, Edit, Grep.

Does Start Issue access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Start Issue safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Start Issue use?

Start Issue is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Start Issue use?

About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Start Issue?

Skills that share tags, products or a category with Start Issue: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Diagnosing Superpowers Sessions (obra/superpowers, 296k stars), GitHub Deep Research (bytedance/deer-flow, 83k stars) and Greploop (onyx-dot-app/onyx, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Start Issue?

hmislk (a GitHub organization) maintains it in hmislk/hmis, which has 236 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 8, 2026.

Source: hmislk/hmis on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.