メニュー
Task creation for issue trackers — structured descriptions, acceptance criteria, field categorization, and tracker linking. Invoke whenever task involves creating work items in any issue tracker — bugs, features, stories, tasks, or any tracked work from standalone requests or decomposition documents.
Design and iterate Claude Code skills: SKILL.md structure, description formulas, content architecture, and quality evaluation. Invoke whenever task involves any interaction with Claude Code skills — creating, reviewing, evaluating, debugging, or improving skills.
Project glossary for consistent domain terminology. Invoke whenever task involves creating, updating, or referencing a glossary, defining domain terms, establishing ubiquitous language, or when inconsistent naming causes confusion in code or planning artifacts.
Coding workflow covering discovery, planning, implementation, and verification. Invoke whenever task involves any interaction with code — writing, modifying, debugging, refactoring, or understanding codebases. Runs discovery protocol before language-specific skills engage.
Structured work handoff across context boundaries: triage decisions, constraints, and remaining work into a prompt-quality transfer document. Invoke whenever task involves handing off work — session restart, teammate delegation, async resumption, or any context boundary crossing.
Rust language conventions, idioms, error handling, concurrency (CPU-bound parallelism with threads/rayon and I/O-bound async with Tokio), the cargo/clippy/rustfmt toolchain, and rustdoc. Invoke whenever task involves any interaction with Rust code — writing, reviewing, refactoring, debugging, or understanding .rs files and Cargo projects.
Rust testing conventions and frameworks: built-in #[test], integration, and doctest layout plus the cargo-nextest runner and the proptest, insta, criterion, mockall, and rstest ecosystem. Invoke whenever task involves any interaction with Rust tests — writing, running, configuring, or debugging tests in .rs files and Cargo projects.
| name | task-creation |
| description | Task creation for issue trackers — structured descriptions, acceptance criteria, field categorization, and tracker linking. Invoke whenever task involves creating work items in any issue tracker — bugs, features, stories, tasks, or any tracked work from standalone requests or decomposition documents. |
Create well-formed tasks in an issue tracker. The input is either a decomposition document (from the pipeline) or a standalone request from a user. The output is a tracked task with enough context for an implementer to start work without asking questions.
From the pipeline: After frame produces a frame document with vertical slice phases, this skill handles creating
tasks from those phases in the issue tracker with proper fields, categorization, and linking.
Standalone: When a user requests a task directly — "create a bug for the pagination issue" or "add a task to upgrade the dependency." No decomposition document needed; gather context from the conversation.
This is an active discovery step — use available tools, don't rely on inference.
Write the title. The title is what people see in lists, boards, and notifications:
Write the description. Structure depends on task type, but every description needs:
Context — Why this task exists. Connect it to the larger effort. Link to the design document or technical design if one exists. One or two sentences.
What to do — The specific work. Concrete enough that the implementer knows the scope, abstract enough that they choose the approach. Describe the change, not the code.
Acceptance criteria — How to know it's done. See the dedicated section below.
References (optional) — Links to resources that already exist: design documents, technical designs, external specs, documentation URLs, mockups. Every item must be a real, verifiable resource — a file that exists on disk or a URL that resolves. Never include code paths, file paths to source code, or references to files that will be created during implementation. Code-level details belong in implementation, not task descriptions. Never reference other tasks in the same tracker — inter-task relationships are handled exclusively through native tracker links in Step 4. Omit this section entirely when there are no existing resources to link.
Every task needs a description. Extract intent, structure it, and link to the conversation if someone needs the raw thread — never copy-paste chat messages directly.
Set fields based on what you discovered in Step 1. Carry over estimates from the decomposition document if available. Only set fields that the tracker supports and the project uses — don't invent metadata.
## Task Draft
**Project:** [project name]
**Type:** [value from tracker]
**Title:** [title]
**Description:**
[full description with context, what to do, acceptance criteria, references]
**Fields:**
[list each field you plan to set with its value, based on project config]
After approval:
Acceptance criteria are the most important part of a task description after context. They transform vague intent ("make search faster") into verifiable conditions ("search returns results within 200ms for queries under 50 characters").
Testable — Each criterion has a clear pass/fail outcome. "User experience is improved" fails this test. "Page loads in under 2 seconds on 3G" passes.
Outcome-focused — Describe what the system does, not how it's built. "Search returns partial matches for inputs of 3+ characters" — not "implement a LIKE query with wildcard prefix."
Independent — Each criterion can be verified on its own. If criterion B can only be tested after criterion A, consider whether they're really one criterion.
Measurable — Quantify when possible. Response times, character limits, item counts, error rates. Numbers eliminate ambiguity. Replace vague conditions like "should be fast" or "user-friendly interface" with measurable thresholds.
Rule-oriented (checklist) — Best for most engineering tasks. Simple, scannable, directly translatable to test cases:
- [ ] Search field appears in the top navigation bar
- [ ] Search triggers on button click or Enter key
- [ ] Input accepts up to 200 characters
- [ ] Results display within 500ms for datasets under 10,000 records
- [ ] Empty query shows recent items instead of empty state
Scenario-oriented (Given/When/Then) — Best for complex user flows where preconditions and sequences matter:
Given the user is on the search page with an empty query
When they type 3 or more characters
Then results appear as a dropdown below the search field
Given the user has selected a filter
When they clear the search field
Then the filter remains applied and results update accordingly
Use rule-oriented by default. Switch to scenario-oriented when the behavior depends on specific preconditions or multi-step sequences.
Too vague: "Works correctly" or "handles edge cases" — what does correctly mean? Which edge cases? Every criterion needs a clear pass/fail outcome.
Too prescriptive: "Use a Redis cache with TTL of 300 seconds" — that's implementation, not acceptance. Say "repeated queries return cached results" and let the implementer choose the mechanism.
Missing negative cases: Only describing the happy path. Include: what happens with invalid input, empty states, error conditions, permission boundaries.
Different types of work call for different description structures. These patterns can be combined.
For broken functionality. The reader needs to understand what's wrong, how to see it, and what should happen instead.
Reproduce the bug before drafting — read the reported steps, trace the code, run the failing path. A confirmed reproduction yields precise Steps to Reproduce and a real Actual Behavior; a failed or partial reproduction is the signal to gather more detail first, not a reason to file a vague task.
## Context
[What feature is affected and how it relates to the system]
## Problem
[What's broken — observable symptoms, not root cause speculation]
## Steps to Reproduce
1. [Step one]
2. [Step two]
3. [Step three]
## Expected Behavior
[What should happen]
## Actual Behavior
[What happens instead]
## Acceptance Criteria
- [ ] [Verifiable fix condition]
- [ ] [Regression prevention]
Include screenshots, error messages, or log excerpts when they clarify the problem. Omit when the description is self-explanatory.
For building or changing functionality. The standard pattern — most tasks from a decomposition document follow this structure.
## Context
[Why this task exists, link to design/technical design]
## What to Do
- [Specific work items]
## Acceptance Criteria
- [ ] [Verifiable conditions]
## References
- [Links to existing design docs, specs, documentation URLs, mockups — never code paths or other tasks]
For work where the outcome is understanding, not code. Debugging, research, feasibility analysis.
## Context
[What prompted the investigation]
## Symptoms / Evidence
[What was observed — logs, error messages, metrics, user reports]
## Goal
[What answer or decision this investigation should produce]
## Acceptance Criteria
- [ ] Root cause identified and documented
- [ ] Recommended fix or next steps proposed
For code improvements that don't change behavior. The reader needs to understand what's being restructured and why, despite no user-visible change.
## Context
[What motivates the refactoring — upcoming feature, tech debt, performance]
## What to Do
- [Specific restructuring work]
## Constraints
- [Behavior must not change]
- [Backward compatibility requirements]
## Acceptance Criteria
- [ ] Existing tests pass without modification
- [ ] [Specific structural improvements verifiable in code review]
User request: "Create a bug for the search — it returns 500 when the query has special characters like & or %"
Step 1 (Gather Context): Query the tracker for the project's field configuration. Discover available types (Bug, Task, Story), required fields (Priority, State), and valid values.
Step 2 (Draft):
## Task Draft
**Project:** SEARCH
**Type:** Bug
**Priority:** High
**Title:** Fix 500 error on search queries containing special characters
**Description:**
## Context
The search API returns HTTP 500 when queries contain URL-significant characters (& , %, =). This
affects all clients using the search endpoint.
## Problem
Special characters in the search query are passed to the backend unescaped, causing the query parser
to fail with an unhandled exception.
## Steps to Reproduce
1. Open the search page
2. Enter a query containing `&` or `%` (e.g., "R&D budget")
3. Submit the search
## Expected Behavior
Search returns results matching the literal query text.
## Actual Behavior
HTTP 500 response. No results displayed.
## Acceptance Criteria
- [ ] Search queries containing &, %, =, and + return correct results
- [ ] Invalid UTF-8 sequences return HTTP 400 with a descriptive error message
- [ ] Existing search functionality is unaffected (run search test suite)
Step 3 (Present): Show draft to user, wait for approval.
Step 4 (Create): Create in tracker, set fields, link to parent epic via native tracker link if applicable, report task ID and URL.
Two rules from the tasks skill apply equally here:
Descriptions are plans, not reports. Write every description as if the work has not started. "Add pagination to the search results" — not "Added pagination" or "Pagination was implemented." The implementer reads this fresh. Tell them what to do, not what was done.
No implementation in descriptions. Describe WHAT should change and what "done" looks like. No production code, no function signatures, no class names to create. Pseudocode is acceptable for complex logic. Configuration samples are acceptable when configuration is the deliverable. Describe the capability needed, not the code to write.
When creating: Apply all rules silently. Follow the workflow steps, discover project configuration before drafting, write titles in imperative mood, structure descriptions with Context/What to do/Acceptance criteria/References, and use native tracker links for all inter-task relationships. Do not narrate which rules you are following.
When reviewing: Evaluate existing tasks against the Quality Checklist. For each violation, cite the specific rule, quote the problematic section, and show the fix inline. Common review findings:
When all tasks are created:
Before creating a task in the tracker: