create-work-items
Create and classify typed work items (epic, story, feature, bug, finding, work-item) in the configured tracking backend.
Skill by intelligentcode-ai
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/intelligentcode-ai-create-work-items
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/create-work-items
What's inside
- Skill name
create-work-items- Description
- Create and classify typed work items (epic, story, feature, bug, finding, work-item) in the configured tracking backend. Use when users ask to create/capture work or when actionable findings/comments are discovered from review, PR feedback, QA, regressions, or defect reports.
- License
- MIT
- Instructions
- 141 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Create Work Items
Create typed work items and publish them to the active tracking backend.
## Triggering
Use this skill when the request requires creating or normalizing tracked work items.
Use this skill when prompts include:
- create tickets, issues, work items, findings, or backlog entries
- capture actionable findings/comments from review, PR feedback, QA, regression, or defect reports
- convert discovered implementation tasks into typed work items before planning/execution
Do not use this skill for:
- explanation-only prompts (no request to create tracked work)
- current backlog status only
- implementation-only prompts when existing planned items already cover the work
## Acceptance Tests
| Test ID | Type | Prompt / Condition | Expected Result |
| --- | --- | --- | --- |
| CWI-T1 | Positive trigger | "Create work items for these 4 review findings" | skill triggers |
| CWI-T2 | Positive trigger | "Capture these PR comments as bugs and findings" | skill triggers |
| CWI-T3 | Negative trigger | "Explain why the tests failed" | skill does not trigger |
| CWI-T4 | Negative trigger | "Show current backlog status only" | skill does not trigger |
| CWI-T5 | Behavior | skill triggered for actionable findings/comments | creates typed items with required fields and backend-aware output summary |
## Canonical Actionable Findings Definition
Treat these as actionable findings/comments:
- review findings
- PR comments requesting code/documentation changes
- QA findings
- regressions
- explicit defect reports
Do not create items for non-actionable commentary (questions, explanations, praise, status updates).
## When To Use
- User asks to create tickets/issues/work items
- New work is discovered during implementation or review
- Requirements must be captured before planning/execution
## Item Types
Supported item types:
- `epic`
- `story`
- `feature`
- `bug`
- `finding`
- `work-item`
## Backend Selection
Use canonical config-first backend routing:
1. `.agent/tracking.config.json`
2. `${ICA_HOME}/tracking.config.json`
3. `$HOME/.codex/tracking.config.json` or `$HOME/.claude/tracking.config.json`
4. Auto-detect GitHub
5. Fallback to `.agent/queue/`
## Configuration Bootstrap (MANDATORY)
Before creating items, ensure a persisted tracking configuration exists and is used:
1. If `.agent/tracking.config.json` exists, use it.
2. If project config is missing, ask explicitly:
- "Use system tracking config for this project, or create a project-specific backend config?"
3. If the selected config file does not exist, ask for backend default (`github` or `file-based`) and create it.
4. Persist at least:
```json
{
"issue_tracking": { "enabled": true, "provider": "github" },
"tdd": { "enabled": false }
}
```
5. Use the persisted provider for this run (do not silently switch providers).
6. If user asks to change backend later, update the same config file and confirm the new active provider.
## TDD Confirmation Gate (MANDATORY)
If TDD skill is active (locally or globally), ask explicitly for this scope:
- "TDD is active. Apply TDD for this work scope? (yes/no)"
Persistence rule:
- If `tdd.enabled` is missing on first TDD-related invocation, ask for the default and persist it in the selected config file.
- Scope-level answer overrides stored default for the current run.
## Required Fields
Each created item should include:
- title
- type
- priority (`p0` to `p3` or local equivalent)
- description / acceptance notes
- optional parent
If fields are missing, ask focused clarification (short, bounded), then proceed.
## TDD Decomposition Rule (MANDATORY)
If TDD is being performed for the requested scope, you MUST create explicit work items for:
- `RED` - write/update failing test first
- `GREEN` - implement minimal code to make RED pass
- `REFACTOR` - cleanup and improve design with tests still green
These are required work items, not optional notes.
Required dependency order:
- `GREEN` blocked by `RED`
- `REFACTOR` blocked by `GREEN`
For GitHub backend:
- create these as separate child issues (typically `type/work-item`)
- use clear titles like `[RED] ...`, `[GREEN] ...`, `[REFACTOR] ...`
- create and verify native parent-child linksFrom intelligentcode-ai/skills, MIT.
More from intelligentcode-ai/skills
- 0.437score
github-state-tracker
intelligentcode-ai
Retrieve, normalize, and report GitHub issue state continuously with prioritization and parent-child awareness.
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
github-issues-planning
intelligentcode-ai
Plan and structure GitHub Issues work for epics, stories, bugs, findings, and work-items with consistent labels, priorities, and parent-child links.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
architect
intelligentcode-ai
Activate when user needs architectural decisions, system design, technology selection, or design reviews.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
devops-engineer
intelligentcode-ai
Activate when user needs CI/CD or deployment work - pipeline design, deployment automation, release management.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
backend-tester
intelligentcode-ai
Activate when user needs API or backend testing - REST/GraphQL validation, integration tests, database verification.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
developer
intelligentcode-ai
Activate when user asks to code, build, implement, create, fix bugs, refactor, or write software.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
agent-browser
intelligentcode-ai
Use when you need to reproduce or debug web UI flows (especially auth/OIDC) via the Agent Browser CLI, capture snapshots/screenshots, and extract redirect…
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
database-engineer
intelligentcode-ai
Activate when user needs database work - schema design, query optimization, migrations, data modeling.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
ai-engineer
intelligentcode-ai
Activate when user needs AI/ML work - model integration, behavioral frameworks, intelligent automation.
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
branch-protection
intelligentcode-ai
Activate when performing git operations.
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
autonomy
intelligentcode-ai
Activate when a subagent completes work and needs continuation check.
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
file-placement
intelligentcode-ai
Activate when creating any summary, report, or output file.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Feb 16, 2026 (8 months ago)
- Last release
- Feb 16, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/intelligentcode-ai/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from intelligentcode-ai
- 0.437score
github-state-tracker
intelligentcode-ai
Retrieve, normalize, and report GitHub issue state continuously with prioritization and parent-child awareness.
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
github-issues-planning
intelligentcode-ai
Plan and structure GitHub Issues work for epics, stories, bugs, findings, and work-items with consistent labels, priorities, and parent-child links.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
developer
intelligentcode-ai
Activate when user asks to code, build, implement, create, fix bugs, refactor, or write software.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
architect
intelligentcode-ai
Activate when user needs architectural decisions, system design, technology selection, or design reviews.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
agent-browser
intelligentcode-ai
Use when you need to reproduce or debug web UI flows (especially auth/OIDC) via the Agent Browser CLI, capture snapshots/screenshots, and extract redirect…
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
ai-engineer
intelligentcode-ai
Activate when user needs AI/ML work - model integration, behavioral frameworks, intelligent automation.
SkillDFreshness: D★ 1Claude Code +9
Cite this page
create-work-items skill. Agent Mart. https://agentmart.dev/skills/intelligentcode-ai-create-work-items (last updated 2026-10-24)