agentsclimarketplace
Sign in

Support macros

Skill shinzoxD/knackbox/skills/productivity/support-macros

Draft customer support replies and macros with correct tone, escalation judgment, and no over-promising. Use whenever the user pastes a support ticket, asks for a help-desk reply, canned macro, refund wording, or whether to escalate a customer issue.From its SKILL.md

Install
npx -y skills add shinzoxD/knackbox --skill support-macros

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.0 KB, 339 tokens by cl100k_base, as published. Nobody here has run it

Support Macros

Support writing is empathy plus accuracy. Never invent policy. Escalate when risk, abuse, data loss, or legal exposure appears.

Workflow

  1. Restate customer problem and emotion in one line (internal).
  2. Identify facts you have vs need; list clarifying questions if blocked.
  3. Apply user-provided policy only — do not invent refund/SLA rules.
  4. Choose path: resolve, workaround, escalate, or security/privacy path.
  5. Draft reply: empathy → answer/action → next step → close.
  6. Offer a shorter macro variant when useful.

Output format

## Ticket read
**Issue:** …
**Tone to match:** …
**Path:** resolve | workaround | escalate

## Customer reply
…

## Internal notes
- macros tags, escalation reason, fields to update

## If policy missing
Questions to ask the user/policy owner before sending.

Rules

  1. Never invent pricing, refunds, legal commitments, or timelines not given.
  2. Do not admit liability in creative ways; stay factual unless policy says otherwise.
  3. Security reports: do not ask for passwords; use secure channels.
  4. Abusive tickets: firm boundaries without matching hostility.
  5. Personal data: minimize echoing sensitive data back.
  6. One clear CTA (what happens next / what we need).

Edge cases

  • Angry churn risk: acknowledge impact, own the fix path, avoid fake discounts.
  • Bug with workaround: give workaround first, then tracking expectation if provided.
  • Cannot reproduce: request artifacts without blaming the customer.

What ships with it: 1 file

1.4 KB alongside SKILL.md

benchmarks/

Gives 0 of the 12 instructions most customer support skills give in 339 tokens

Counted across 123 of the 124 authors here whose files we hold, read 2026-08-07

  • Call RUBE_SEARCH_TOOLS first to get current schemasin 12 of 123, across 4 files
  • Confirm connection status is ACTIVE before running workflowsin 12 of 123, across 4 files
  • Stop and ask for clarification if required inputs are missingin 9 of 123, across 2 files
  • Call RUBE_MANAGE_CONNECTIONS with the helpdesk toolkitin 9 of 123, across 2 files
  • Use both timestamp and ID for cursor navigationin 8 of 123, across 1 file
  • Implement backoff on 429 responsesin 8 of 123, across 1 file
  • Parse response data defensively with fallback patternsin 8 of 123, across 1 file
  • Use this skill only when the task clearly matches the scopein 8 of 123, across 1 file
  • Pass a JSON file as the positional argumentin 7 of 123, across 1 file
  • Specify output format with the --format flagin 7 of 123, across 1 file
  • Run health, churn, and expansion scripts togetherin 7 of 123, across 1 file
  • Verify output files contain expected records before continuingin 7 of 123, across 1 file

Said here and by no other author read

  • restate customer problem and emotion in one line
  • list clarifying questions if blocked
  • apply user-provided policy only
  • choose a resolution path
  • draft reply using empathy, action, next step, and close
  • offer a shorter macro variant when useful

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.