Whetstone · 20 skills · CC BY 4.0
Agent skills honed on real work. Each one is a short, self-contained rule set distilled from one concrete failure — written so an AI coding agent (or a human) can apply the lesson without the original context.
What makes a whetstone skill
01 / From a real failure
Every skill names the sanitized case it was distilled from — a check that passed against a stand-in, a merge that dropped a field, a green test that could never fail. No hypotheticals.
02 / Client-agnostic
No project or company detail survives. The lesson is stripped to its mechanism so it transfers to your codebase, your stack, your next incident.
03 / Fails loudly
Each ends in a pre-flight checklist that fails loudly when a box is unchecked — a gate on "done," not a suggestion you can wave through.
If it reads like a blog post, it doesn't belong. If it reads like a checklist
a tired engineer would thank you for at 3am, it does.
The collection
Each links to its SKILL.md — the full rule set, the sanitized case, and the pre-flight check.
verify-through-the-real-path ↗
Before claiming something works, is done, safe, or fast — verify through the actual trigger, real data, and representative conditions, not a stand-in.
prove-the-test-can-fail ↗
After writing a test, or before trusting a green one — make it fail on purpose once, and confirm new branches are reachable by the mocks.
measure-the-delta-not-the-absolute ↗
Judging whether your change is clean on a red or noisy baseline — prove it by stash-and-compare, not by which files appear in the failure list.
test-fixture-realism ↗
Writing tests against a shared store or fabricated fixtures — make fixtures mirror data reality and assertions unable to pass trivially.
know-your-aggregate-command-scope ↗
Before citing a test / lint / type-check / build script as proof — confirm what it actually runs, how it forwards args, and whether it caches.
running-long-background-jobs ↗
Launching or verifying a long-running / detached job, or reconciling a batch against a corpus other processes also write to.
03 skills
01 skill
Anatomy of a skill
One folder, one SKILL.md. Plain Markdown, so any agent that can load a system prompt can use it — the plugin auto-discovery is the only Claude Code-specific part.
The description carries the trigger phrases, so a skill-aware agent surfaces the right skill when the situation matches.
One paragraph. The whole lesson, stated once, before any elaboration.
Each rule paired with the sanitized real case it came from — the scar that earned it.
The checklist that gates "done" and fails loudly when a box is unchecked.
--- name: verify-through-the-real-path description: > Use before claiming something works, is done, is safe, or is fast — verify through the actual trigger, real data... --- # Verify Through the Real Path ## The core rule A convenient stand-in is not the thing you claimed works. Verify through the actual trigger, real data... ## Checks - Real trigger, not a direct call. ... - Smoke test = throughput floor. ... ## Pre-flight check - [ ] Fired through the real trigger? - [ ] Real data, representative load? - [ ] Observed the end effect?
Put an edge on it
Two ways in. The plugin gives you auto-discovery; the manual copy is just folders.
Recommended
Add the marketplace, then install the plugin — all 20 skills come with it. Run both inside Claude Code.
Copy> /plugin marketplace add iamakbarsha1/whetstone
Copy> /plugin install whetstone@whetstone-skills
Any agent
Each skill is a self-contained folder in the Claude Code skill layout. Copy one, or all of them.
Copy$ cp -R skills/verify-through-the-real-path ~/.claude/skills/
Copy$ cp -R skills/* ~/.claude/skills/