--- name: output-standards description: | Use this skill when defining or enforcing output formatting standards for agent responses in WrongStack. Triggers: user says "next steps format", "output standard", "response format", "final message format", "standardize next steps". version: 1.0.0 --- # Output Standards — WrongStack Standardizes the format of agent output, particularly the `next_steps` section in final messages. This ensures system-level parsing and automation can reliably extract structured data from agent responses. ## Rules 1. **Only the leader agent's final message SHOULD include ``** — subagents report findings only. If nothing is pending, omit the tag entirely; do not append a loose "next steps" or goodwill-style follow-up line. 2. **Any suggested next prompt MUST be inside `...`** — never emit parseable-looking prose such as "Next steps:", "next suggests", "Suggested next:", or "Let me know if you want..." when you intend `/next` to work. 3. **`` is for prompt options only** — every item is the exact natural-language message that can be submitted back to the agent through the current TUI or WebUI prompt input. It asks the agent to perform work; it is not a checklist of work the user must do. Human-only actions (e.g., "open DevTools yourself", "manually check the browser console") belong outside the tag as informational text. 4. **Tags must be exact and properly closed** — `...` with no attributes on either tag. In particular, never emit ``. 5. **No markdown inside tags** — plain text only, one item per line. 6. **Items are agent-directed prompt inputs** — imperative wording is valid when it tells the agent what to do. Write the complete message the user would send, not an instruction addressed to the user. 7. **Only item 1 may be marked `auto="true"`** — at most one item may carry the marker, and its input must be complete enough to submit directly. 8. **Keep concise** — max 5 items unless the task genuinely requires more. 9. **Skip `` whenever the live `ctx.todos` list still has open items** — any `pending` or `in_progress` todo means the in-flight task list is not done, and surfacing new prompt options would race the todo loop (YOLO+auto could pick the top suggestion and pivot away from the unfinished work; `/next 1` would replace the next todo with an arbitrary prompt). Finish the todo list first, re-arm the tag on the turn where the last todo flips to `completed`. The runtime enforces the same gate, so emitting it mid-task is parsed-and-discarded — the rule exists to keep the output focused, not to override runtime behavior. ## Output Format ``` [... task results ...] 1. Run the focused parser tests and fix any failures 2. Review the current diff and implement any necessary corrections Informational text for human-only actions (outside the tag, no tag wrapper). ``` ### Format Requirements | Element | Rule | Example | |---------|------|---------| | Opening tag | `` on its own line | `` | | Numbered items | `1. ` prefix, one agent-directed prompt per line | `1. Fix the auth bug in core/session.ts and add a regression test` | | Closing tag | `` on its own line | `` | | `auto="true"` item | Optional on item 1 only; include the full input content | `1. fix in core/auth.ts:42 auto="true"` | ### ✅ Correct Examples ``` Bug Hunt complete. Found 3 critical issues. 1. Fix the shell injection in packages/cli/src/slash-commands/dev.ts:15 2. Replace Math.random() with randomUUID() in the affected files 3. Run the type checker and fix any errors Open browser DevTools → Network tab to verify the WebSocket connection is established before testing. ``` ``` Audit complete. Found bash command timeout pattern in iterations 14–20. 1. Run the session tests and type checker, then fix any failures Review iterations 14–20 in the session log to characterize the loop. ``` ### ❌ Incorrect Examples ``` Task done. Next steps: 1) fix bug 2) run tests # ❌ No tags — not parseable ``` ``` - Fix the bug in auth.ts # ❌ Dash, not number - Run tests # ❌ Wrong bullet character ``` ``` 1. **Fix the bug** — use execFile instead # ❌ Markdown inside tags 2. Run `pnpm test` # ❌ Markdown formatting not allowed inside tags ``` ``` Next steps: 1. Fix auth.ts # ❌ Missing opening/closing tags ``` ``` 1. Open the browser console and check for errors # ❌ Human-only action, not a prompt ``` ## `auto="true"` Format When the first item should be auto-submitted, append `auto="true"` to that item. Never put it on the `` tag or on items 2+: ``` 1. Run the type checker and fix any errors auto="true" 2. Fix the shell injection in packages/cli/src/slash-commands/dev.ts:15 and add a regression test ``` The text before `auto="true"` is the exact prompt the user would type. There can be at most one auto item and it must be item 1. Items without `auto="true"` are suggestions the user can select manually. ## Subagent Requirements When a **leader agent** synthesizes output from **subagents**, the leader MUST: 1. Collect findings from subagents (they return results, not ``) 2. Based on findings, produce a unified `` section with prompt options 3. Remove duplicates (dedupe by file path + action) 4. Re-prioritize if needed (critical > high > medium > low) 5. Human-only findings (e.g., "check the browser console") go outside the tag 6. Keep the unified list within the 5-item guideline, but no hard cap When a **subagent** completes its task, it MUST: 1. **NOT include ``** in its output — report findings only 2. Report what it found/achieved in a structured, self-contained format 3. Let the leader decide what next steps follow from the findings ## Anti-patterns - **Don't put human-only actions in ``** — those belong outside the tag as plain text - **Don't address instructions to the user** — agent-directed imperatives are valid because the selected text is submitted back to the agent verbatim - **Don't use markdown inside ``** — plain text only - **Don't skip the tag when there are prompt options** — the tag enables the `/next` workflow - **Don't use dashes or asterisks** — use `1.`, `2.`, `3.` numbering - **Don't be vague** — "fix bugs" is useless, "fix auth/session.ts:42" is a valid prompt - **Don't exceed 5 items without reason** — if >5, it's probably not a single task - **Don't write declarations of intent** — "we should refactor X" is not a prompt; "refactor core/config.ts" is - **Don't assign manual work to the user** — "manually check if X is correct yourself" is not a valid next prompt; when tools permit it, use an agent-directed prompt such as "Use the browser tools to verify X and fix any issue you find" - **Don't include `` in subagent output** — subagents report findings, leaders produce next steps ## Skills in scope - `bug-hunter` — inherits output-standards for bug reports - `security-scanner` — inherits output-standards for security findings - `refactor-planner` — inherits output-standards for refactoring plans - `architect` — inherits output-standards for architecture analysis - `tech-stack` — inherits output-standards for dependency reports