agentleFS
dmzoneilldmzoneill/skills/start-work/SKILL.md

start-work

Skill2 starsChanged 19 days agoApache-2.0View on GitHub

Begin or resume working on a Jira issue. Gets issue context, creates/checks out feature branch, shows MR feedback if exists, updates Jira status, searches related code, loads project gotchas. Use when user says "start work on AAP-X", "pick up issue", "begin work on AAP-12345".

17 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 0 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If no branch: generate AAP-XXXXX-slugified-summary

    line 43
  2. Very specific:

    If branch exists: git_checkout(repo, target=branch) then git_pull(repo, rebase=true)

    line 47
  3. Very specific:

    If new branch: git_checkout(repo, target="main") → git_pull → git_branch_create(repo, branch_name, checkout=true)

    line 48
  4. Very specific:

    If new work: skill_run("notify_team", '{"message": "🚀 Started work on AAP-X", "type": "info"}')

    line 57
  5. Very specific:

    If "issue does not exist": learn_tool_fix("jira_view_issue", "issue does not exist", "Wrong key", "Verify AAP-XXXXX format")

    line 62
  6. Very specific:

    If "no such host": learn_tool_fix("gitlab_mr_list", "no such host", "VPN not connected", "Run vpn_connect()")

    line 63

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Start Work on Jira Issue

Inputs

InputTypeDefaultPurpose
issue_keystringrequiredJira issue key (e.g., AAP-12345)
repostring""Repo path; if empty, resolved from issue key via config
repo_namestring-Config repo name (e.g., automation-analytics-backend)
auto_stashbooltrueStash uncommitted changes before checkout
slack_formatboolfalseUse Slack link format

Workflow

1. Bootstrap

  • persona_load("developer")
  • Resolve repo: use resolve_repo from scripts.common.repo_utils with issue_key, repo, repo_name
  • check_known_issues("", issue_text) — proactive check for related patterns

2. Validate

  • git_status(repo=resolved.path) — ensure valid git repo, no rebase/merge in progress
  • Validate issue key format: AAP-XXXXX via scripts.common.parsers.validate_jira_key
  • jira_view_issue(issue_key) — get issue; fail if not found

3. Knowledge & Search (optional, on_error: continue)

  • code_search(query=issue_summary, project=resolved.name, limit=5)
  • knowledge_query(project=resolved.name, section="gotchas")
  • knowledge_query(project=resolved.name, section="architecture.overview")
  • check_known_issues("", issue_text) — related error patterns

4. Branch & MR

  • git_fetch(repo=resolved.path, prune=true)
  • git_branch_list(repo=resolved.path, all_branches=true) — find branch matching issue key
  • If branch exists:
    • gitlab_mr_list(project=resolved.gitlab) — find MR for branch
    • gitlab_mr_view, gitlab_mr_comments, gitlab_ci_status — feedback
    • jira_view_issue — recent Jira updates
  • If no branch: generate AAP-XXXXX-slugified-summary

5. Stash & Checkout

  • If auto_stash: git_stash(repo, action="push", message="Auto-stash before switching")
  • If branch exists: git_checkout(repo, target=branch) then git_pull(repo, rebase=true)
  • If new branch: git_checkout(repo, target="main") → git_pull → git_branch_create(repo, branch_name, checkout=true)

6. Jira & Hygiene (new work only)

  • jira_transition(issue_key, "In Progress")
  • jira_assign(issue_key, assignee="currentUser")
  • skill_run("jira_hygiene", '{"issue_key": "...", "auto_fix": true}')

7. Memory & Notify

  • memory_session_log("Started/Resumed work on AAP-X", "Branch: X, Repo: Y")
  • If new work: skill_run("notify_team", '{"message": "🚀 Started work on AAP-X", "type": "info"}')
  • memory_append("state/current_work", "active_issues", item) — key, summary, status, branch, repo, started
  • memory_update("state/current_work", "last_updated", timestamp)

8. Failure Learning

  • If "issue does not exist": learn_tool_fix("jira_view_issue", "issue does not exist", "Wrong key", "Verify AAP-XXXXX format")
  • If "no such host": learn_tool_fix("gitlab_mr_list", "no such host", "VPN not connected", "Run vpn_connect()")

Key MCP Tools

  • persona_load, jira_view_issue, jira_transition, jira_assign
  • git_status, git_fetch, git_branch_list, git_checkout, git_pull, git_branch_create, git_stash
  • gitlab_mr_list, gitlab_mr_view, gitlab_mr_comments, gitlab_ci_status
  • code_search, knowledge_query, check_known_issues, learn_tool_fix
  • memory_session_log, memory_append, memory_update, skill_run

Branch Naming

Branch MUST start with AAP-XXXXX per .gitlab-ci.yml validate-mr. Pattern: ^aap-[0-9]{3,6}.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.