Menu
Guidelines on creating issues on GitHub
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Render a document, a diagram, or a report as HTML for human visualisation.
Use when writing prose meant to read by humans: PR descriptions, docs, blog drafts, emails, design memos
Run a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed. MANDATORY TRIGGERS: 'premortem this', 'premortem my', 'run a premortem', 'what could kill this', 'future-proof this', 'stress test this plan', 'what am i missing here', 'find the blind spots'. STRONG TRIGGERS: 'what could go wrong', 'am i missing anything', 'poke holes in this', 'where will this break', 'devil's advocate this'. Do NOT trigger on simple feedback requests, or factual questions. DO trigger when someone has a plan or commitment where the cost of being wrong is high.
Schedule a prompt to fire back at yourself at a future time or on a recurring cron pattern. Use when the user says "remind me", "every N minutes/hours/days", "at HH:MM tomorrow", "check X periodically", or otherwise asks for any time-based action. Triggered by the `schedule` tool plus the `/schedule` command for listing and deletion.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get roasted on their design, or mentions "brainstorm".
Pick one open task and implement it end-to-end as a unit of work. Use when the user asks to pick a task.
| name | issue |
| description | Guidelines on creating issues on GitHub |
| disable-model-invocation | true |
| argument-hint | The context & scope of the issue |
CRITICAL: under no circumstances are you to open issues automatically. This skill only outputs text for a human to review and post themselves.
If the session context doesn't contain enough information to accurately describe the issue:
Ground yourself in facts rather than guessing from training data.
Research existing issues, PRs, and discussions related to the task. If there is already a direct match, stop and point the user to it.
If there are no matches, collect relevant issues, PRs, and discussion IDs to add as links.
If the issue to report is a bug that can be isolated, use the repro skill to create
a minimal reproduction repository first, that we can link to in the issue body.
If the "can be isolated" property is unclear, ask the user if they want to create a reproduction.
You MUST use the prose skill for guidelines on contents (tone, verbosity).
This is important: maintainers' attention is limited, and submitting AI slop is disrespectful.
You MUST read the target repo's CONTRIBUTING.md, issue templates, or other reference docs on contributions, and use their guidelines to drive the shape of the output.
When you have collected all you need, write the issue text to a temporary file and open it in Sublime Text.
