About

Imported from yonatangross/orchestkit (src/skills/paired-probe/SKILL.md). Install upstream with npx skills add yonatangross/orchestkit --skill paired-probe. Copyright stays with the author.

paired-probe

Name: paired-probe
Author: yonatangross

A check that prints the same thing whether or not the fault is present has measured nothing. It still returns an answer, that answer looks like evidence, and it gets acted on. This skill makes the blindness fail loudly instead.

When to reach for it

Before reporting any of these, because all of them are verdicts:

"nothing found", "all clean", "no failures", "safe to delete"
a sweep, audit, or status roll-up over N items
a security or CI gate that just went green
any check that passed when you expected it to fail

And immediately whenever a result surprises you by passing. Surprise is the cheapest available signal that the instrument, not the world, is what changed.

The three gates

Gate	Question	Failure it catches
Differential	What does this print when the fault is ABSENT?	A probe that answers identically either way
Non-empty	How many items did it actually examine?	A sweep that measured zero and reported clean
Exit-aware	Did the probe itself run?	A swallowed error printing success

Could-not-observe is a third outcome, never folded into either verdict.

Usage

# Differential: stage the fault, then remove it. Both arms must differ.
scripts/paired-probe.sh --name "retired model pin fails the gate" \
  --present "printf 'model: claude-opus-4\n' > wf.yml && bash tests/ci/lint.sh" \
  --absent  "rm -f wf.yml && bash tests/ci/lint.sh"

# Single-shot, when the fault cannot be staged (a live sweep):
scripts/paired-probe.sh --name "worktrees examined" \
  --measure "git worktree list --porcelain | awk '/^worktree /{print \$2}'" \
  --min-count 1

Exit codes: 0 discriminates or met the count, 1 BLIND, 2 usage, 3 could-not-observe.

Why this exists

Four probes from a single session, 2026-08-21, each confidently wrong and none failing loudly. Three were caught by other people rather than by the check:

The probe	What it asked	Why it lied
"is this branch pushed?"	the local ref cache	unfetched and never-pushed print identically
"is the branch on origin?"	the remote branch list	a squash-merge DELETES the head branch, so landed work reads as lost
"does this worktree hold unique work?"	`diff main HEAD`	symmetric, so a stale tree flags `main` against itself
"any worktree at risk?"	a loop over a blocked temp file	the write failed, `\|\| true` swallowed it, the loop read zero items and printed "safe to prune"

Every one dies at gate 1 or 2 in seconds.

The rule that generalises

Ask what the instrument structurally cannot observe before trusting its silence. A tool reports on the channel it queried, not on reality: the local cache instead of the remote, the whole file instead of the frontmatter, the proxy instead of the origin. When the answer is a zero or an empty set, that is exactly when to check the channel, because zero is what a broken instrument returns too.

Related Skills

ork:verify grades finished work; this grades the check itself.
ork:quality-gates for escalation once a real defect is confirmed.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/yonatangross-orchestkit-paired-probe/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

yonatangross-orchestkit-paired-probe.ocm.jsonjson

{
  "ocm": "1",
  "id": "yonatangross-orchestkit-paired-probe",
  "kind": "skill",
  "name": "paired-probe",
  "description": "Refuse a verdict a probe did not earn. Runs a check where the fault IS present and where it is NOT, and blocks the answer when both arms print the same thing, because a check that cannot disagree with you has measured nothing. Also catches the zero-sample sweep that reads as \"clean\" and the swallowed error that reads as success. Use before reporting any status, audit, sweep, or \"nothing found\" result, and whenever a check surprises you by passing.",
  "publisher": "yonatangross",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "verification",
      "debugging",
      "quality-gates",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Refuse a verdict a probe did not earn. Runs a check where the fault IS present and where it is NOT, and blocks the answer when both arms print the same thing, because a check that cannot disagree with you has measured nothing. Also catches the zero-sample sweep that reads as \"clean\" and the swallowed error that reads as success. Use before reporting any status, audit, sweep, or \"nothing found\" result, and whenever a check surprises you by passing."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/yonatangross/orchestkit",
      "path": "src/skills/paired-probe/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/yonatangross/orchestkit/blob/HEAD/src/skills/paired-probe/SKILL.md",
      "key": "yonatangross/orchestkit/src/skills/paired-probe/SKILL.md"
    },
    "compatibility": "Claude Code 2.1.251+."
  },
  "instructions": "# paired-probe\n\n**A check that prints the same thing whether or not the fault is present has\nmeasured nothing.** It still returns an answer, that answer looks like evidence,\nand it gets acted on. This skill makes the blindness fail loudly instead.\n\n## When to reach for it\n\nBefore reporting any of these, because all of them are verdicts:\n\n- \"nothing found\", \"all clean\", \"no failures\", \"safe to delete\"\n- a sweep, audit, or status roll-up over N items\n- a security or CI gate that just went green\n- any check that passed when you expected it to fail\n\nAnd immediately whenever a result *surprises* yo",
  "cost": {
    "context_tokens": 786
  }
}

Fetch it by URL: GET /api/v1/registry/yonatangross-orchestkit-paired-probe/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.