Skip to content

code-yeongyu/oh-my-openagent / packages/shared-skills/skills/ulw-research

ulw-research

Unverified

Runs maximum-saturation research with a cooperating team, claim-graph gating, and a cited, QA'd deliverable. Use when the user explicitly asks for research or a deep investigation, including any 'ulw' research wording.

FileKindSize
AGENTS.mdmarkdown9.2 KB
ATTRIBUTION.mdmarkdown2.4 KB
SKILL.mdskill md42.2 KB
references/deliverable-phase.mdmarkdown49.1 KB
references/fact-ledger-grammar.mdmarkdown6.8 KB
references/fact-ledger.mdmarkdown24.4 KB
references/fidelity-claim-kinds.mdmarkdown5.2 KB
references/markdown-blocks.mdmarkdown721 B
references/report-gates.mdmarkdown32.0 KB
references/report-visualization.mdmarkdown15.4 KB
references/research-collection.mdmarkdown26.8 KB
references/research-delivery.mdmarkdown14.3 KB
references/unit-rules.mdmarkdown16.3 KB
scripts/claim-kinds.mjsscript11.2 KB
scripts/claim-kinds.test.tsscript13.5 KB
scripts/claim-prefix.test.tsscript4.9 KB
scripts/claims-index.mjsscript5.3 KB
scripts/claims-index.test.tsscript5.7 KB
scripts/cli-support.mjsscript4.1 KB
scripts/cli-support.test.tsscript4.3 KB
scripts/contracts-validation.test.tsscript3.3 KB
scripts/contracts.mjsscript26.1 KB
scripts/contracts.test.tsscript7.9 KB
scripts/conversion-altered.test.tsscript11.0 KB
scripts/conversion-originals.test.tsscript22.7 KB
scripts/conversion-probe-classes.test.tsscript45.2 KB
scripts/conversion-probe.mjsscript13.5 KB
scripts/conversion-probe.test.tsscript11.6 KB
scripts/copy-returns-fidelity-policy.test.tsscript10.4 KB
scripts/copy-returns-polish.test.tsscript12.1 KB
scripts/copy-returns.test.tsscript10.6 KB
scripts/css-hiding.mjsscript9.1 KB
scripts/css-lite.mjsscript7.6 KB
scripts/css-lite.test.tsscript6.4 KB
scripts/delivery-barrier-meaning.test.tsscript12.3 KB
scripts/delivery-barrier.test.tsscript11.4 KB
scripts/design-spec.mjsscript7.2 KB
scripts/design-spec.test.tsscript6.7 KB
scripts/entities.mjsscript2.5 KB
scripts/entry-guard.mjsscript794 B
scripts/fact-commands-fill.mjsscript6.6 KB
scripts/fact-commands-meaning.mjsscript12.6 KB
scripts/fact-commands-polish.mjsscript10.3 KB
scripts/fact-commands-verify.mjsscript12.6 KB
scripts/fact-commands.mjsscript13.8 KB
scripts/fact-derive-2.test.tsscript7.2 KB
scripts/fact-derive.mjsscript4.9 KB
scripts/fact-derive.test.tsscript10.8 KB
scripts/fact-expr.mjsscript4.5 KB
scripts/fact-fill.mjsscript11.7 KB
scripts/fact-fill.test.tsscript10.7 KB
scripts/fact-ledger-grammar.test.tsscript11.8 KB
scripts/fact-ledger-kinds.mjsscript16.5 KB
scripts/fact-ledger-kinds.test.tsscript9.3 KB
scripts/fact-ledger-legacy.test.tsscript8.9 KB
scripts/fact-ledger-schema.mjsscript11.9 KB
scripts/fact-ledger-schema.test.tsscript1.5 KB
scripts/fact-ledger.mjsscript5.5 KB
scripts/fact-ledger.test.tsscript9.7 KB
scripts/fact-locate.mjsscript12.1 KB
scripts/fact-locate.test.tsscript7.2 KB
scripts/fact-pairs.mjsscript8.3 KB
scripts/fact-pairs.test.tsscript6.6 KB
scripts/fact-recompute.mjsscript4.8 KB
scripts/fact-unit-dimensions-2.test.tsscript8.4 KB
scripts/fact-unit-dimensions.test.tsscript11.9 KB
scripts/fact-unit-rules.test.tsscript8.9 KB
scripts/fidelity-binding.mjsscript6.7 KB
scripts/fidelity-binding.test.tsscript4.0 KB
scripts/fidelity-brief.mjsscript6.4 KB
scripts/fidelity-brief.test.tsscript7.8 KB
scripts/fidelity-claims.mjsscript5.1 KB
scripts/fidelity-csv.mjsscript1.1 KB
scripts/fidelity-lexicon.mjsscript8.1 KB
scripts/fidelity-lexicon.test.tsscript6.0 KB
scripts/fidelity-originals.mjsscript9.9 KB
scripts/fidelity-policy.mjsscript10.1 KB
scripts/fidelity-records.mjsscript13.4 KB
scripts/fidelity-snapshot-readability.mjsscript2.2 KB
scripts/fidelity-sources.mjsscript4.3 KB
scripts/fidelity-state.mjsscript2.1 KB
scripts/fidelity-state.test.tsscript1.7 KB
scripts/fidelity-trace.mjsscript6.1 KB
scripts/fidelity-trace.test.tsscript3.3 KB
scripts/fidelity-value-unit.mjsscript13.3 KB
scripts/fidelity-values.mjsscript16.1 KB
scripts/fidelity-values.test.tsscript15.8 KB
scripts/format-extract-css.mjsscript5.1 KB
scripts/format-extract.mjsscript10.3 KB
scripts/format-extract.test.tsscript11.2 KB
scripts/gates-context.test.tsscript2.6 KB
scripts/gates-fidelity.mjsscript6.3 KB
scripts/gates-fidelity.test.tsscript3.3 KB
scripts/gates-figures.mjsscript9.9 KB
scripts/gates-layout.mjsscript6.6 KB
scripts/gates-layout.test.tsscript12.4 KB
scripts/gates-static-headings.test.tsscript961 B
scripts/gates-static.mjsscript8.1 KB
scripts/gates-static.test.tsscript14.9 KB
scripts/gates-structure.mjsscript4.7 KB
scripts/gates-text.mjsscript7.2 KB
scripts/glossary-vocabulary.test.tsscript1.7 KB
scripts/html-foreign-object.mjsscript2.8 KB
scripts/html-lite.mjsscript9.7 KB
scripts/html-lite.test.tsscript7.9 KB
scripts/html-markup.mjsscript7.0 KB
scripts/html-text-map.mjsscript4.8 KB
scripts/html-text-map.test.tsscript15.2 KB
scripts/layout-probe.mjsscript4.6 KB
scripts/layout-probe.test.tsscript4.2 KB
scripts/lexicon.mjsscript2.6 KB
scripts/lexicon.test.tsscript3.2 KB
scripts/markdown-closers.mjsscript4.9 KB
scripts/md-lite-boundaries.test.tsscript2.2 KB
scripts/md-lite.mjsscript7.8 KB
scripts/md-lite.test.tsscript10.3 KB
scripts/meaning-check.mjsscript9.7 KB
scripts/meaning-check.test.tsscript12.0 KB
scripts/number-grammar.mjsscript2.1 KB
scripts/number-grammar.test.tsscript1.8 KB
scripts/numerals.mjsscript12.0 KB
scripts/numerals.test.tsscript6.1 KB
scripts/outcome-start.mjsscript3.8 KB
scripts/outcome-start.test.tsscript5.0 KB
scripts/outcome.mjsscript10.5 KB
scripts/outcome.test.tsscript12.8 KB
scripts/page-source-locator.test.tsscript11.7 KB
scripts/particles-ko.mjsscript4.8 KB
scripts/particles-ko.test.tsscript4.3 KB
scripts/placeholder.mjsscript9.3 KB
scripts/placeholder.test.tsscript3.8 KB
scripts/polish-apply.mjsscript6.8 KB
scripts/polish-apply.test.tsscript19.7 KB
scripts/polish-diff.mjsscript1.7 KB
scripts/polish-diff.test.tsscript10.1 KB
scripts/polish-markup.test.tsscript14.0 KB
scripts/polish-partial.test.tsscript2.5 KB
scripts/polish-project.mjsscript5.8 KB
scripts/polish-rules.mjsscript9.8 KB
scripts/rational.mjsscript5.2 KB
scripts/rational.test.tsscript1.9 KB
scripts/raw-decode.mjsscript4.5 KB
scripts/raw-locator.mjsscript2.4 KB
scripts/raw-snapshot.test.tsscript7.3 KB
scripts/references-fences.test.tsscript1.2 KB
scripts/repair-tracker.mjsscript7.5 KB
scripts/repair-tracker.test.tsscript10.8 KB
scripts/report-tools-2.test.tsscript16.1 KB
scripts/report-tools-3.test.tsscript9.3 KB
scripts/report-tools-4.test.tsscript10.1 KB
scripts/report-tools-5.test.tsscript14.6 KB
scripts/report-tools-commands.mjsscript12.9 KB
scripts/report-tools.mjsscript2.6 KB
scripts/report-tools.test.tsscript12.1 KB
scripts/sentence-split.mjsscript3.0 KB
scripts/sentence-split.test.tsscript4.5 KB
scripts/snapshot-readability.test.tsscript7.0 KB
scripts/source-commands.mjsscript12.4 KB
scripts/source-integrity.test.tsscript18.1 KB
scripts/source-refresh.mjsscript5.2 KB
scripts/source-snapshot.mjsscript9.9 KB
scripts/source-snapshot.test.tsscript6.3 KB
scripts/source-view.mjsscript5.0 KB
scripts/sources-citation.mjsscript12.1 KB
scripts/sources-citation.test.tsscript14.8 KB
scripts/tests/contracts-support.tsscript3.5 KB
scripts/tests/delivery-barrier-session.tsscript3.3 KB
scripts/tests/derive-clock.tsscript341 B
scripts/tests/fact-derive-support.tsscript1.9 KB
scripts/tests/fact-unit-dimensions-support.tsscript1.5 KB
scripts/tests/fact-unit-rules-support.tsscript16.8 KB
scripts/tests/fidelity-values-support.tsscript1.6 KB
scripts/tests/fixtures/assets/figure-1.svgother141 B
scripts/tests/fixtures/bad-report.htmlother2.1 KB
scripts/tests/fixtures/boxes.jsonconfig3.2 KB
scripts/tests/fixtures/conversion-probe.htmlother485 B
scripts/tests/fixtures/design-spec.mdmarkdown458 B
scripts/tests/fixtures/fidelity-brief-locked.mdmarkdown571 B
scripts/tests/fixtures/fidelity-brief-pending.mdmarkdown574 B
scripts/tests/fixtures/fidelity/assets/share.csvother40 B
scripts/tests/fixtures/fidelity/claim-graph.mdmarkdown449 B
scripts/tests/fixtures/fidelity/gen-legacy-dev.mjsscript5.0 KB
scripts/tests/fixtures/fidelity/ledger-basic.jsonconfig5.1 KB
scripts/tests/fixtures/fidelity/ledger-legacy-dev.jsonconfig18.3 KB
scripts/tests/fixtures/fidelity/ledger-verify.jsonconfig9.1 KB
scripts/tests/fixtures/fidelity/polish-edits.jsonconfig303 B
scripts/tests/fixtures/fidelity/report-bad.htmlother821 B
scripts/tests/fixtures/fidelity/report-good.htmlother2.4 KB
scripts/tests/fixtures/fidelity/sources/S4.htmlother680 B
scripts/tests/fixtures/fidelity/sources/S4/acronyms.jsonconfig36 B
scripts/tests/fixtures/fidelity/sources/S4/meta.jsonconfig256 B
scripts/tests/fixtures/fidelity/sources/S4/sentences.jsonlother623 B
scripts/tests/fixtures/fidelity/sources/S4/text.txtmarkdown300 B
scripts/tests/fixtures/fidelity/sources/S5/acronyms.jsonconfig3 B
scripts/tests/fixtures/fidelity/sources/S5/meta.jsonconfig235 B
scripts/tests/fixtures/fidelity/sources/S5/sentences.jsonlother53 B
scripts/tests/fixtures/fidelity/sources/S5/text.txtmarkdown10 B
scripts/tests/fixtures/fidelity/sources/S9.txtmarkdown128 B
scripts/tests/fixtures/good-report.htmlother2.7 KB
scripts/tests/fixtures/reference-report.htmlother2.5 KB

scripts/meaning-check.mjs

View on GitHub
// meaning-check.mjs - ingest the meaning readers' verdicts over fact-pairs output.
//
// ingestVerdicts reads verdict files written by separate reader lanes (cheap and strong tiers),
// keeps a drift verdict only when its pair exists, its tier and drift_kind are in the closed sets,
// and both its fragment (from the sentence) and source_fragment (from the quote or statement) are
// non-empty substrings after whitespace normalization; every other verdict is dropped and logged.
// Both tiers naming the same drift_kind (not "other") on a pair is meaning_drift_confirmed (major,
// never integrity); one tier is meaning_drift_warn (minor). Each flagged pair yields one
// calibration line; a dispute is recorded there and never removes the defect. Coverage is
// fail-closed: every pair no reader judged, and every force_strong pair no strong reader judged,
// is listed in `unverified`, so a gate can tell a clean check apart from a pair nobody read.
// No model, no fetch.

import { appendFileSync, readFileSync } from "node:fs"

import { DEFECT_CODES } from "./contracts.mjs"

export const DRIFT_KINDS = Object.freeze([
  "subject_changed",
  "scope_widened",
  "hedge_dropped",
  "certainty_added",
  "causality_added",
  "direction_flipped",
  "population_changed",
  "evidence_grade_raised",
  "other",
])
export const MODEL_TIERS = Object.freeze(["cheap", "strong"])
export const VERDICTS = Object.freeze(["drift", "ok"])
export const isDriftKind = (kind) => DRIFT_KINDS.includes(kind)
/** The machine-read verdict contract a reader lane receives with pairs.json; built from the registries above. */
export const VERDICT_SCHEMA = Object.freeze({
  model_tier: MODEL_TIERS,
  verdict: VERDICTS,
  drift_kind: DRIFT_KINDS,
  required: Object.freeze(["pair_id", "verdict"]),
  drift_required: Object.freeze(["drift_kind", "fragment", "source_fragment"]),
})

/** NFC, every whitespace run collapsed to one space, trimmed. */
const squash = (text) =>
  String(text ?? "")
    .normalize("NFC")
    .replace(/\s+/gu, " ")
    .trim()

/** Read a verdict file, mapping an unreadable path or invalid JSON to a short typed error. */
function parseFile(path) {
  let text
  try {
    text = readFileSync(path, "utf8")
  } catch {
    throw new TypeError(`${path}: cannot read the verdict file`)
  }
  try {
    return JSON.parse(text)
  } catch {
    throw new TypeError(`${path}: the verdict file is not valid JSON`)
  }
}

function verdictsOf(input) {
  const label = typeof input === "string" ? input : "<inline>"
  const parsed = typeof input === "string" ? parseFile(input) : input
  const list = Array.isArray(parsed) ? parsed : parsed?.verdicts
  if (!Array.isArray(list))
    throw new TypeError(`${label}: a verdict file is an array of verdicts or { verdicts: [...] }`)
  const tier = Array.isArray(parsed) ? undefined : parsed.model_tier
  return list.map((verdict) => ({
    verdict: tier === undefined || verdict?.model_tier !== undefined ? verdict : { ...verdict, model_tier: tier },
    file: label,
  }))
}

/** The reason a verdict is dropped, or null when it is accepted. */
function dropReason(verdict, pair) {
  if (verdict === null || typeof verdict !== "object") return "malformed_verdict"
  if (!pair) return "unknown_pair"
  if (!VERDICTS.includes(verdict.verdict)) return "invalid_verdict"
  if (!MODEL_TIERS.includes(verdict.model_tier)) return "invalid_model_tier"
  if (verdict.verdict === "ok") return null
  if (!isDriftKind(verdict.drift_kind)) return "unknown_drift_kind"
  const [fragment, sourceFragment] = [squash(verdict.fragment), squash(verdict.source_fragment)]
  if (fragment === "" || sourceFragment === "") return "empty_fragment"
  if (!squash(pair.sentence).includes(fragment)) return "fragment_not_found"
  const source = pair.kind === "claim" ? pair.statement : pair.quote
  if (!squash(source).includes(sourceFragment)) return "source_fragment_not_found"
  return null
}

function defect(code, pair, driftKind, tiers, verdicts) {
  const entry = DEFECT_CODES[code]
  // The fragment must come from the verdict whose drift_kind is being reported, not from whichever
  // verdict happened to arrive first on the pair.
  const first = verdicts.find((verdict) => verdict.drift_kind === driftKind) ?? verdicts[0]
  return {
    code,
    severity: entry.severity,
    integrity: entry.integrity,
    pair_id: pair.pair_id,
    sentence_key: pair.sentence_key ?? null,
    drift_kind: driftKind,
    tiers,
    fragment: first.fragment,
    source_fragment: first.source_fragment,
    selector: null,
    line: null,
    message: `${pair.pair_id}: ${tiers.join(" and ")} reader${tiers.length > 1 ? "s" : ""} found ${driftKind} at "${squash(first.fragment)}"`,
    hint: entry.hint,
  }
}

/** One meaning_unverified defect per coverage gap, so blocksDelivery sees an unread pair through the registry. */
export function unverifiedDefects(unverified) {
  const entry = DEFECT_CODES.meaning_unverified
  return unverified.map((gap) => ({
    code: "meaning_unverified",
    severity: entry.severity,
    integrity: entry.integrity,
    pair_id: gap.pair_id,
    reason: gap.reason,
    selector: null,
    line: null,
    message: `${gap.pair_id}: ${gap.reason === "no_strong_verdict" ? "no strong reader judged this force_strong pair" : "no reader judged this pair"}`,
    hint: entry.hint,
  }))
}

/** Pairs with no accepted verdict, and force_strong pairs with no accepted strong verdict, in pair order. */
function coverageGaps(list, accepted) {
  const tiersByPair = new Map()
  for (const verdict of accepted) {
    tiersByPair.set(verdict.pair_id, (tiersByPair.get(verdict.pair_id) ?? new Set()).add(verdict.model_tier))
  }
  const gaps = []
  for (const pair of list) {
    const tiers = tiersByPair.get(pair.pair_id)
    if (tiers === undefined || tiers.size === 0) gaps.push({ pair_id: pair.pair_id, reason: "no_verdict" })
    else if (pair.force_strong === true && !tiers.has("strong"))
      gaps.push({ pair_id: pair.pair_id, reason: "no_strong_verdict" })
  }
  return gaps
}

/** Group accepted drift verdicts per pair, then per tier. */
function flaggedPairs(accepted) {
  const byPair = new Map()
  for (const verdict of accepted) {
    if (verdict.verdict !== "drift") continue
    const tiers = byPair.get(verdict.pair_id) ?? new Map()
    tiers.set(verdict.model_tier, [...(tiers.get(verdict.model_tier) ?? []), verdict])
    byPair.set(verdict.pair_id, tiers)
  }
  return byPair
}

/** The drift_kind both tiers named (never "other"), or null. */
function agreedKind(tiers) {
  const [cheap, strong] = MODEL_TIERS.map((tier) => tiers.get(tier) ?? [])
  return (
    cheap
      .map((verdict) => verdict.drift_kind)
      .find((kind) => kind !== "other" && strong.some((verdict) => verdict.drift_kind === kind)) ?? null
  )
}

/**
 * @param {object[] | { pairs: object[] }} pairs extractPairs(...) output
 * @param {(string | object[] | { verdicts: object[], model_tier?: string })[]} verdictFiles paths, or parsed verdict lists
 * @param {{ dispute?: { pair_id: string, reason: string }, calibrationPath?: string }} [options]
 *   calibrationPath: append each calibration line to this JSONL file (fidelity-calibration.jsonl)
 * @returns {{ defects: object[], dropped: object[], unverified: { pair_id: string, reason: string }[], calibrationLines: string[] }}
 *   unverified lists, in pair order, every pair no reader judged (`no_verdict`) and every
 *   force_strong pair no strong reader judged (`no_strong_verdict`); a verdict that was dropped
 *   does not count as read. A consumer MUST treat a non-empty list as blocking: the pairs were
 *   never checked, so an empty `defects` list does not mean the report is clean.
 * @throws {TypeError} when pairs is neither an array nor `{ pairs: [...] }` (fail closed: a missing
 *   pairs input never reads as a fully verified report)
 */
export function ingestVerdicts(pairs, verdictFiles, options = {}) {
  const list = Array.isArray(pairs) ? pairs : pairs?.pairs
  if (!Array.isArray(list)) throw new TypeError("pairs: expected an array of pairs or { pairs: [...] }")
  const byId = new Map(list.map((pair) => [pair.pair_id, pair]))
  const accepted = []
  const dropped = []
  for (const input of verdictFiles) {
    for (const { verdict, file } of verdictsOf(input)) {
      const reason = dropReason(verdict, byId.get(verdict?.pair_id))
      if (reason === null) accepted.push(verdict)
      else dropped.push({ file, pair_id: verdict?.pair_id ?? null, model_tier: verdict?.model_tier ?? null, reason })
    }
  }
  const dispute = options.dispute ?? null
  const defects = []
  const calibrationLines = []
  const flagged = flaggedPairs(accepted)
  for (const pair of list) {
    const tiers = flagged.get(pair.pair_id)
    if (!tiers) continue
    const tierNames = MODEL_TIERS.filter((tier) => tiers.has(tier))
    const agreed = agreedKind(tiers)
    const verdicts = MODEL_TIERS.flatMap((tier) => tiers.get(tier) ?? [])
    const kind = agreed ?? verdicts[0].drift_kind
    const confirmed = agreed !== null
    defects.push(defect(confirmed ? "meaning_drift_confirmed" : "meaning_drift_warn", pair, kind, tierNames, verdicts))
    const disputed = dispute !== null && dispute.pair_id === pair.pair_id
    calibrationLines.push(
      JSON.stringify({
        kind: pair.kind,
        pair_id: pair.pair_id,
        tiers: tierNames,
        drift_kind: kind,
        confirmed,
        disputed,
        reason: disputed ? String(dispute.reason ?? "") : null,
      }),
    )
  }
  const unverified = coverageGaps(list, accepted)
  if (dispute !== null && !flagged.has(dispute.pair_id)) {
    dropped.push({ file: "<dispute>", pair_id: dispute.pair_id, model_tier: null, reason: "dispute_not_flagged" })
  }
  if (options.calibrationPath && calibrationLines.length > 0)
    appendFileSync(options.calibrationPath, `${calibrationLines.join("\n")}\n`)
  return { defects, dropped, unverified, calibrationLines }
}
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall