Skip to content
cccskills
FreePublished on GitHub

scope

Exploratory workflow for understanding problem spaces and drafting feature proposals, refactorings, or complex bug-fixes. Creates detailed tickets in your issue tracker without doing implementation work.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md5.5 KB
  • references/README.md4.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Scope - Problem Space Exploration & Ticket Creation

Helps you thoroughly understand a problem space through codebase exploration and iterative dialogue, then creates a well-specified ticket for future implementation.

This skill does NOT write code. It explores, questions, understands, and documents.

Workflow

1. Initial Discovery

Understand what the user wants to explore:

  • What feature are they considering?
  • What refactoring are they contemplating?
  • What bug needs detailed investigation?
  • Is this greenfield or modifying existing code?

Ask clarifying questions:

  • Scope and boundaries
  • Problem statement
  • Desired outcome (not implementation details yet)

Output: Clear understanding of what problem space to explore.

2. Codebase Exploration

Use exploration tools to understand context:

  • Spawn Explore agent (set thoroughness based on scope: "quick", "medium", "very thorough")
  • Use Grep to find relevant code patterns
  • Use Read to examine key files identified
  • Map out the current architecture/implementation

For third-party dependencies:

  • Use WebFetch to read API documentation
  • Clone relevant repositories to /tmp for examination if needed
  • Understand integration points and constraints

Exploration goals:

  • Where does this change fit in the architecture?
  • What existing code will be affected?
  • What patterns/conventions are already established?
  • What are the integration points?
  • What similar features exist that we can learn from?

Output: Comprehensive understanding of the relevant codebase areas.

3. Iterative Refinement

Use AskUserQuestion to refine understanding:

  • Present what you've learned from exploration
  • Ask about approaches (if multiple valid options exist)
  • Clarify edge cases and requirements
  • Discuss trade-offs between approaches
  • Validate assumptions about existing code

Loop until both Claude and user have:

  • Precise understanding of what to build
  • Clear rationale for approach chosen
  • Identified edge cases and constraints
  • Agreed on acceptance criteria

Important: This is collaborative design, not just requirements gathering. Challenge assumptions, propose alternatives, discuss trade-offs.

Output: Shared, precise understanding of the work to be done.

4. Ticket Synthesis

Draft ticket content adaptively based on type:

For feature proposals:

  • Problem statement (what problem does this solve?)
  • Proposed solution (high-level approach)
  • Acceptance criteria (specific, testable)
  • Technical notes (implementation considerations, affected components)
  • Security considerations (if the change introduces new attack surface, handles user input, touches auth/authz, or affects trust boundaries — note what controls will be needed. Consult the sec-blue-teamer agent if the implications are non-obvious.)
  • Out of scope (what explicitly won't be done)
  • Open questions (if any remain)

For refactorings:

  • Current state (what's problematic about existing code)
  • Desired state (what we want it to look like)
  • Motivation (why is this worth doing)
  • Approach (high-level refactoring strategy)
  • Risk assessment (what could go wrong)
  • Affected areas (files/modules that will change)

For complex bug fixes:

  • Bug description (observed behavior)
  • Root cause (from your exploration)
  • Proposed fix (high-level approach)
  • Why this happened (what allowed the bug)
  • Verification plan (how to confirm fix works)
  • Regression prevention (tests/checks to prevent recurrence)

Format guidelines:

  • Use markdown
  • Be specific, not vague
  • Include code references (file paths, line numbers, function names)
  • Link to relevant documentation or issues
  • Make it actionable (someone else should be able to implement from this)

Output: Draft ticket content for user review.

5. Review & Refine Ticket

Present draft to user:

  • Show complete ticket content
  • Highlight any areas of uncertainty
  • Ask if anything is missing or unclear

Iterate if needed:

  • Adjust based on feedback
  • Add missing details
  • Clarify ambiguous sections

Output: Approved ticket content ready to create.

6. Create Ticket

Detect the issue tracker and create the ticket per references/trackers.md (Detection Procedure + "Create" operation). Capture and present the resulting ticket URL.

Output: Created ticket with URL.

Skill Boundaries

This skill will:

  • Explore code extensively
  • Ask lots of questions
  • Synthesize understanding into tickets
  • Challenge your assumptions
  • Propose alternatives
  • Create issues in your issue tracker

This skill will NOT:

  • Write production code
  • Make commits
  • Run tests or linters
  • Modify files (except ticket creation)
  • Implement features

Notes

Exploration thoroughness:

  • Quick exploration: ~5 minutes, high-level understanding
  • Medium exploration: ~15 minutes, detailed component analysis
  • Very thorough: ~30 minutes, comprehensive system understanding

Ticket quality over speed:

  • Take time to understand deeply
  • Don't rush to ticket creation
  • Better to ask more questions than create vague tickets

Integration with /implement:

  • These skills are separate and complementary
  • /scope creates the ticket, /implement implements it
  • Ticket created by /scope can be handed to someone else or tackled later with /implement

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Bug-fixing workflow that coordinates diagnosis, test-driven reproduction, root-cause analysis, and targeted fixes. Use when the user wants to fix a bug with thorough investigation and regression testing.

The English summary is being prepared. Showing the original description.

chrisallenlane/claude-swe-workflows18Updated May 19, 2026

Proactive bug-hunting workflow. Assesses codebase risk through complexity, coverage, and structural analysis, then spawns focused investigators that write reproducing tests to validate suspected bugs. Thoroughness over speed. Advisory only — produces findings and proposes tickets; does not implement fixes.

The English summary is being prepared. Showing the original description.

chrisallenlane/claude-swe-workflows18Updated May 19, 2026

Iterative development workflow that coordinates implementation, refactoring, QA, and documentation agents to complete features systematically. Use when the user wants a full development workflow with quality checks.

The English summary is being prepared. Showing the original description.

chrisallenlane/claude-swe-workflows18Updated May 19, 2026

Multi-ticket batch workflow. Takes a batch of tickets, plans execution order, implements each via /implement in autonomous mode, runs cross-cutting quality passes, and presents results for final review.

The English summary is being prepared. Showing the original description.

chrisallenlane/claude-swe-workflows18Updated May 19, 2026

Full-lifecycle project workflow. Takes batched tickets, implements via /implement-batch, runs smoke tests, then executes a comprehensive quality pipeline (refactor, review-arch, review-test, tidy-docs, review-release). Maximizes autonomy with andon cord escape.

The English summary is being prepared. Showing the original description.

chrisallenlane/claude-swe-workflows18Updated May 19, 2026

Autonomous bug-elimination loop. Iteratively invokes /bug-hunt and /implement-batch until findings converge below an operator-specified severity floor. At termination, runs /review-test scoped to the run's new reproducing tests and fixes quality issues above the floor. Auto-approves /bug-hunt and /review-test ticket proposals; pulls the andon cord on contested findings, repeated implementation failure, hard-cap exhaustion, or breaking-change proposals. Optional /refactor finisher.

The English summary is being prepared. Showing the original description.

chrisallenlane/claude-swe-workflows18Updated May 19, 2026

See all skills by chrisallenlane

Report a problem with this skill