agentleFS
HyunKNHyunKN/harness-kit/skills/issue-driven-workflow/SKILL.md

issue-driven-workflow

Skill0 starsChanged 7 months agoMITView on GitHub

Use when a project follows an issue-first workflow and implementation should be tracked through docs/issues before, during, and after coding. Trigger for non-trivial bug fixes, features, refactors, or reliability work once the problem is already clear enough to execute. Do not use this skill as a substitute for early problem framing or detailed task decomposition when those are still missing.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run non-trivial implementation through an issue document so problem, scope, risks, validation, and next steps stay explicit.

    line 8
  2. Very specific:

    If the request is still vague, hand off to spec-writing first.

    line 12
  3. Distinctive:

    Create or update an issue doc before coding.

    line 13
  4. Distinctive:

    Keep the issue state in sync with actual work.

    line 14
  5. Distinctive:

    Use troubleshooting notes, decision records, and review notes when the work produces reusable evidence beyond the issue itself.

    line 19
  6. Distinctive:

    Always remind what was just completed and what remains.

    line 20
  7. Very specific:

    Keep the issue doc focused on execution state.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Issue Driven Workflow

Run non-trivial implementation through an issue document so problem, scope, risks, validation, and next steps stay explicit.

Default flow

  1. If the request is still vague, hand off to spec-writing first.
  2. Create or update an issue doc before coding.
  3. Keep the issue state in sync with actual work.
  4. Record affected files, linked docs, and validation commands.
  5. After completion, update:
    • docs/issues/current_backlog.md
    • docs/status/implemented_features.md when real functionality changed
  6. Use troubleshooting notes, decision records, and review notes when the work produces reusable evidence beyond the issue itself.
  7. Always remind what was just completed and what remains.

Good fit

  • feature work
  • bug fixes with more than one file
  • reliability or UX cleanup
  • refactors with validation requirements

Avoid for

  • tiny spelling fixes
  • trivial one-line changes with no real scope

Resources

  • See references/issue-lifecycle.md for the recommended issue lifecycle.
  • Pair with spec-writing when scope is loose and planning-workflow when the issue is too large to execute directly.
  • Keep the issue doc focused on execution state; move durable rationale to decision-recording and mechanism explanations to technical-learning-note.

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.