Responses

Write the saved replies (macros) for "$ARGUMENTS" and record the policy they apply: what agents may offer, what needs approval and what is never promised.

Arguments. $ARGUMENTS may contain the project name and optional flags. Take the first token as <project> and treat --skip-checks as a flag; never include flags in file paths. All paths below use <project>. If --skip-checks is present, skip the prerequisite check and, before writing any artifact, append one line to .singularskills/log.jsonl: {"ts":"<ISO timestamp>","skill":"support-macros","workflow":"support","phase":4,"project":"<project>","event":"skipped","artifact":"04-macros.md","note":"<reason or \"none given\">"}.

Compute with code. Perform every calculation (totals, balances, ratios, variances, projections) with a script — Bash, Python or a spreadsheet formula written to a file — and include the computation alongside the result. Never do arithmetic mentally.

Prerequisites

Part of a workflow. This skill is phase 4 (Responses) of the Support Operations Cycle workflow (support); cross-domain workflows run it too. First check .singularskills/log.jsonl for an open run for this project: a run-started line with "project":"<project>" and no later run-finished line for the same workflow and project. If one exists, the conductor is running you: continue here. Otherwise, if the user asked to start, run, continue or resume a process or workflow rather than this one step, do not continue here: invoke the workflow skill with the workflow the user asked for, or support when they named none, followed by <project>; it runs this phase in order, asks before it writes and records the run. Otherwise continue here: a later phase runs on its own, behind its gate.

Run this skill's gate before writing: sh <this skill's folder>/scripts/gate.sh <project> <project root>, where <project root> is the folder that contains .singularskills/ (use . when you are already there). If it exits non-zero, stop and tell the user what it printed, unless --skip-checks was given (see Arguments). On a refusal, before you stop, append this line to .singularskills/log.jsonl (create the folder and file if missing): {"ts":"<ISO timestamp>","skill":"support-macros","workflow":"support","phase":4,"project":"<project>","event":"refused","artifact":"04-macros.md","note":"<what the gate printed>"}. Once the gate has passed, or under --skip-checks once you have appended the skipped line, append this line before you start work: {"ts":"<ISO timestamp>","skill":"support-macros","workflow":"support","phase":4,"project":"<project>","event":"started","artifact":"04-macros.md","note":""}.

Read .singularskills/support/<project>/02-taxonomy.md for the categories and priorities and .singularskills/support/<project>/03-knowledge.md for the articles macros link to.

Process

1. Find the voice: read .singularskills/branding/<project>/03-verbal.md if it exists and follow its voice and tone. Otherwise propose a short voice (three traits, with a do and a don't for each) and confirm it with the user before writing macros.

2. Record the policy. Ask the user, once and together with any other question, for:

   • what an agent may offer without approval (refunds up to an amount or a number of days, credits, extensions, replacements);
   • what needs approval, and from whom;
   • what is never promised (ship dates, fixes, legal positions, anything else). Write only what the user states. For anything unanswered, write no policy: agents promise nothing here and list it under Open questions.

3. Choose the macros: one for each of the most frequent contact reasons in the taxonomy (usually 10 to 20), plus one for each failure type the user names (a bug, a wrong charge, a late delivery, an outage).

4. Write each macro with:

   • Trigger — the category and the condition that make it the right reply
   • Reply — in the brand's voice, with placeholders in angle brackets (<first name>, <order date>)
   • Placeholders — what each one needs and where the agent finds it
   • Article — the knowledge-base article it links, from 03-knowledge.md, if any
   • Before sending — what the agent must check, naming the policy line the macro relies on

5. Apply service recovery: every macro for a failure passes the checklist in references/service-recovery.md. A macro whose reply offers anything (money, time, a replacement) quotes the policy line that allows it; with no such line, the reply offers nothing and says who will decide.

6. Write the artifact to .singularskills/support/<project>/04-macros.md with sections:

   • Voice — the voice the macros follow, and its source
   • Policies — may offer, needs approval, never promised
   • Macros — each with its trigger, reply, placeholders, article and pre-send checks

Output

The macros written to .singularskills/support/<project>/04-macros.md. Present a summary to the user highlighting:

• The number of macros and the contact reasons they cover
• The policy lines recorded, and every no policy gap
• Any macro that needed a policy the user has not given

Record the run. After you have written the artifact, append this line to .singularskills/log.jsonl (the started line of Prerequisites, with "event":"finished"): {"ts":"<ISO timestamp>","skill":"support-macros","workflow":"support","phase":4,"project":"<project>","event":"finished","artifact":"04-macros.md","note":""}.

Open the artifact with this frontmatter (agent is the agent you run in, or unknown; gate is passed when the gate ran clean and skipped under --skip-checks):

---
skill: support-macros
workflow: support
phase: 4
project: <project>
started: <ISO timestamp>
finished: <ISO timestamp>
agent: <the agent you run in, or "unknown">
gate: <passed|skipped>
---

End the artifact with ## Decisions and ## Open questions, in this shape:

## Decisions
- <what was chosen> — <why> — <what was rejected>

## Open questions
- <what the next phase or a reviewer must settle>