ketchup
Bring the user current on this chat since they last wrote, plainly, then lay out each pending call of theirs with what they need to make it without clicking…
Skill by kevherro
Chalk Labs
Need help deploying ketchup?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kevherro-ketchup
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 2, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ketchup
What's inside
- Skill name
ketchup- Description
- Bring the user current on this chat since they last wrote, plainly, then lay out each pending call of theirs with what they need to make it without clicking through. Use for /ketchup or "what did I miss here".
- License
- MIT
- Instructions
- 68 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Ketchup
Assume the user knows everything up to what they last typed, and
nothing since. Tool results, notifications, and child reports are not
their messages. Bring them current, then hand them every call that is
theirs.
Voice is **bro**'s: plain words, short sentences, like a teammate at
the desk. Describe outcomes for them, not your process. Leave out
hashes, paths, commands, and counts unless they need one to act. Name
each PR, branch, or child the way the user would.
For a catch-up across sessions or days, use **recall** instead.
## Gather
Read-only turn. Do not edit, start jobs, or post anything.
- Your own work since that message, child reports, and anyone
else's messages in this chat.
- The live state of every PR, CI run, and child this chat touched.
Verify every figure you plan to show against where it came from.
Say so when you correct one.
- Action items: calls only the user can make (a product choice, an
approval, something irreversible, access you lack). Include ones
raised earlier and still open. Work you can do yourself is not an
action item. Do not invent one to fill the reply.
For each item: link, what it changes for users, the evidence for
your pick, the risk, and your pick. Write `unknown` for a missing
fact. Omit a link you do not have.
## Write
1. One sentence: what waits on the user, or that nothing does. If
nothing happened and nothing waits, say that and stop.
2. What happened, pictures first, under about 100 words of text.
Embed screenshots or recordings the work produced. Add a diagram
only when a picture explains a change faster than words. Then one
bullet per thing the user asked for: the outcome and whether it
is done, running, failed, or unchecked. Each bullet must stay
true read alone. Never call something done that still waits on
the user. Name bugs found and fixed along the way. End with one
line on work you can still do yourself.
3. Action items, about 30 words each. Never drop or merge items to
save words; no count in place of a list, no link in place of an
item.
- One item, one call: a bullet with the call, your pick, user
impact, evidence, and risk.
- Many items, one call (merge these PRs): the call and pick once,
then a bullet per item, riskiest first.
- A choice between options: each option with what it gets and
what it costs, which is the risk.
Give risk even when low. Mention the cost of waiting only when it
is more than delay.
## Visuals
A visual is a screenshot, a recording, a Mermaid diagram, or a
chart. A table is not a visual. Draw how something connects, a
dependency chain with each state, a before and after, or options
side by side. Do not draw status lists or unconnected boxes. At most
six boxes, eight words each, in plain labels. Never draw a screen you
did not capture or a number you do not have. If the harness cannot
render images, say "no screenshot" and describe what changed on
screen in one line.From kevherro/mestack, MIT.
More from kevherro/mestack
- 0.567score
create-verification-skill
kevherro
Generate a project-local verify-<app> skill that drives this repo's real app the way a user does.
SkillAFreshness: AClaude Code +9 - 0.567score
mestack
kevherro
Kevin's harness-agnostic engineering dispatcher.
SkillAFreshness: AClaude Code +9 - 0.565score
create-formal-verification-skill
kevherro
Write a repo-local formal-<area> skill that machine-checks one high-stakes promise tests rarely exercise, using the verifier that fits the question.
SkillAFreshness: AClaude Code +9 - 0.565score
maintain-formal-verification-skill
kevherro
Re-sync a repo's formal-* checks with code that moved since their last confirmation: read those commits, update the model from the code, rerun, and classify…
SkillAFreshness: AClaude Code +9 - 0.563score
interrogate
kevherro
Adversarial review of a change by one child per configured reviewer.
SkillAFreshness: AClaude Code +9 - 0.561score
principle-attack-the-premise
kevherro
Two fixes on one belief failed the same check; test the belief before a third.
SkillAFreshness: AClaude Code +9 - 0.561score
help
kevherro
Print a table of the current mestack skills and a short description of each.
SkillAFreshness: AClaude Code +9 - 0.561score
benchmark-checklist
kevherro
Vet a performance measurement before you report or act on it: limiter, tuning, physical limits, errors, repeatability, relevance, and whether the work ran.
SkillAFreshness: AClaude Code +9 - 0.561score
correct
kevherro
Turn the mistakes agents repeat in this repo into ones they cannot make, preferring the strongest enforcement that fits.
SkillAFreshness: AClaude Code +9 - 0.556score
in-your-own-words
kevherro
Play back the user's goal and the problem behind it before any work.
SkillAFreshness: AClaude Code +9 - 0.521score
figure-it-out
kevherro
Design and run an auditable playbook when no narrower mestack playbook fits.
SkillBFreshness: BClaude Code +9 - 0.517score
nudge
kevherro
Recurring check-in in this session: ask whether to write a paste-ready team update.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kevherro/mestack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kevherro
- 0.567score
mestack
kevherro
Kevin's harness-agnostic engineering dispatcher.
SkillAFreshness: AClaude Code +9 - 0.567score
create-verification-skill
kevherro
Generate a project-local verify-<app> skill that drives this repo's real app the way a user does.
SkillAFreshness: AClaude Code +9 - 0.565score
create-formal-verification-skill
kevherro
Write a repo-local formal-<area> skill that machine-checks one high-stakes promise tests rarely exercise, using the verifier that fits the question.
SkillAFreshness: AClaude Code +9 - 0.565score
maintain-formal-verification-skill
kevherro
Re-sync a repo's formal-* checks with code that moved since their last confirmation: read those commits, update the model from the code, rerun, and classify…
SkillAFreshness: AClaude Code +9 - 0.563score
interrogate
kevherro
Adversarial review of a change by one child per configured reviewer.
SkillAFreshness: AClaude Code +9 - 0.561score
correct
kevherro
Turn the mistakes agents repeat in this repo into ones they cannot make, preferring the strongest enforcement that fits.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get ketchup running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
ketchup skill. Agent Mart. https://agentmart.dev/skills/kevherro-ketchup (last updated 2026-10-24)