Agent skill
issue-from-plan
Create a GitHub issue from an approved plan before implementation
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/issue-from-plan
SKILL.md
Create a GitHub issue from the approved plan. Distill — do not dump the full plan.
Issue content:
- Title: short imperative summary (under 70 chars)
- Body:
- Problem/goal (one sentence)
- Action items (only the surviving TODOs, as a checklist)
- Key decisions (non-obvious choices, one line each)
Omit rejected candidates, false positives, and exploration steps. Include investigation notes section only if of high documentation value or if it is needed context for coding agent.
After creating the issue, report the issue number and URL. The subsequent PR must reference Closes #N.
Then, if not in a worktree already, create a new worktree using the EnterWorktree tool and proceed with executing the plan inside it.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?