research-word-etymology
Acerca de
Esta habilidad investiga el origen de las palabras rastreando raíces protolingüísticas, identificando cognados entre idiomas y documentando cambios semánticos con atestaciones históricas. Ayuda a los desarrolladores a investigar etimologías, comparar palabras relacionadas entre lenguajes y desmentir etimologías populares. Úsala cuando necesites analizar la historia de una palabra, trazar la evolución de su significado o validar orígenes lingüísticos.
Instalación rápida
Claude Code
Recomendadonpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/research-word-etymologyCopia y pega este comando en Claude Code para instalar esta habilidad
Documentación
Research Word Etymology
Trace a word's origin from its modern form back through attested historical stages and reconstructed proto-language roots, identify cognates in related languages, document semantic drift with dated evidence, and flag any folk etymologies.
适用场景
- Investigating the origin and historical development of a specific word
- Comparing cognate words across related languages to find a common ancestor
- Charting how a word's meaning has changed over centuries with attestation dates
- Evaluating whether a popular origin story is genuine or a folk etymology
- Building a structured etymology entry for documentation or scholarly reference
输入
- 必需: Target word (the modern form to research)
- 必需: Source language of the target word (default: English)
- 可选: Depth of reconstruction (default: earliest reconstructable root; alternative: stop at a specific historical stage)
- 可选: Cognate languages to include (default: major branches of the same family)
- 可选: Output format (default: structured entry; alternative: narrative prose)
步骤
第 1 步:Identify the Modern Form and First Attestation
Establish the current usage and earliest documented appearance of the target word.
-
Record the modern spelling, pronunciation (IPA if possible), and primary meaning(s) in the source language.
-
Search for the earliest attested use of the word in the source language. Consult etymological dictionaries (OED for English, TLFi for French, DWDS for German) and historical corpora via WebSearch:
Search: "[target word] etymology first attested" site:etymonline.com OR site:oed.com
-
Record the attestation date, the source text, and the meaning at first attestation. Note whether the modern meaning differs from the original.
-
If the word entered the source language via borrowing, identify the immediate donor language and approximate date of borrowing.
预期结果: A dated first attestation with the source text identified, the meaning at first use recorded, and the immediate donor language (if borrowed) established.
失败处理: If no attestation date is found in online sources, note this explicitly and proceed with the oldest available evidence. Mark the attestation as "date uncertain" and continue to Step 2.
第 2 步:Trace the Etymological Chain
Work backward from the modern form through documented historical stages to the earliest reconstructable root.
-
For each historical stage, record:
- The form (spelling/transcription)
- The language and approximate date range
- The meaning at that stage
- The phonological changes from the previous stage
-
Follow this chain through attested languages first, then into reconstructed proto-languages. Use standard notation: asterisk (*) for reconstructed forms, angle brackets for graphemes, slashes for phonemes.
-
For Indo-European languages, a typical chain looks like:
- Modern form (e.g., Modern English, post-1500)
- Middle period form (e.g., Middle English, 1100-1500)
- Old period form (e.g., Old English, 450-1100)
- Proto-language form (e.g., Proto-Germanic, reconstructed)
- Deep proto-language (e.g., PIE, reconstructed)
-
For borrowed words, trace through each donor language before reaching the ultimate origin. A Latin borrowing in English might go: Modern English < Old French < Latin < PIE.
-
At each stage, note relevant sound laws that explain the phonological changes (e.g., Grimm's Law for PIE-to-Germanic consonant shifts, the Great Vowel Shift for Middle-to-Modern English vowel changes).
预期结果: A complete chain from modern form to earliest reconstructable root, with each stage dated, the form and meaning recorded, and sound changes explained by named phonological rules where applicable.
失败处理: If the chain breaks at a particular stage (no further ancestor can be identified), mark that stage as the terminus with "origin beyond this point unknown" and proceed to Step 3 with what is available.
第 3 步:Identify Cognates Across Language Families
Find words in related languages that descend from the same proto-form.
-
From the deepest reconstructed root identified in Step 2, search for reflexes (descendant forms) in other branches of the language family.
-
For each cognate, record:
- The language and modern form
- The meaning (noting any semantic divergence from the target word)
- The regular sound correspondences that connect it to the proto-form
-
Group cognates by branch. For PIE, typical branches include: Germanic, Italic (Romance), Celtic, Hellenic, Balto-Slavic, Indo-Iranian, Armenian, Albanian, Tocharian, Anatolian.
-
Verify cognates by checking that the sound correspondences are regular (systematic across multiple word sets), not just superficial resemblance. False cognates (look-alikes from unrelated roots) should be explicitly flagged and excluded.
-
Format the cognate set as a comparison table:
Root: PIE *[root] "[meaning]"
├── Germanic: English [form], German [form], Old Norse [form]
├── Italic: Latin [form] > French [form], Spanish [form], Italian [form]
├── Hellenic: Greek [form]
├── Balto-Slavic: Russian [form], Lithuanian [form]
└── Indo-Iranian: Sanskrit [form], Persian [form]
预期结果: A cognate set with at least 3 branches represented (where the root has surviving reflexes), each cognate verified by regular sound correspondences, and any false cognates explicitly excluded with explanation.
失败处理: If the root has few surviving cognates (common for domain-specific or culturally bound vocabulary), document what exists and note the limited distribution. If the word has no cognates outside its immediate branch, state this and explain why (e.g., the word may be a substrate borrowing or an innovation within that branch).
第 4 步:Document Semantic Drift
Chart how the word's meaning has changed from the proto-root to the modern form.
-
At each stage of the etymological chain (from Step 2), record the primary meaning. Where multiple senses coexist, note them all.
-
Classify each meaning change according to standard categories:
- Narrowing (specialization): meaning becomes more specific (e.g., "deer" once meant any animal)
- Broadening (generalization): meaning becomes more general (e.g., "dog" once meant a specific breed)
- Amelioration: meaning becomes more positive (e.g., "knight" from servant to noble warrior)
- Pejoration: meaning becomes more negative (e.g., "villain" from farmworker to evildoer)
- Metaphor: meaning shifts via analogy (e.g., "mouse" from rodent to computer device)
- Metonymy: meaning shifts via association (e.g., "crown" from headwear to monarchy)
-
Provide the approximate date of each semantic shift where attestation evidence supports it.
-
Format the drift as a timeline:
Semantic drift: [word]
[date/period]: "[meaning]" ([source])
[date/period]: "[meaning]" — [drift type] ([source])
[date/period]: "[meaning]" — [drift type] ([source])
Present: "[meaning]"
预期结果: A dated semantic drift timeline with at least the original and modern meanings, each shift classified by type, and attestation sources cited.
失败处理: If intermediate stages lack clear attestation evidence, note the gap explicitly (e.g., "semantic shift from X to Y occurred between [date range] but the mechanism is not attested") and proceed with available evidence.
第 5 步:Flag Folk Etymologies
Identify and evaluate any popular but incorrect origin stories associated with the word.
- Search for common folk etymologies, backronyms, or urban legends about the word:
Search: "[target word] folk etymology" OR "[target word] myth origin" OR "[target word] false etymology"
-
For each folk etymology found, document:
- The claimed origin story
- Why it is linguistically unsupported (e.g., anachronistic, phonologically impossible, no attestation evidence)
- The likely reason the folk etymology became popular (satisfying narrative, apparent plausibility, memorable acronym)
-
If no folk etymologies exist for this word, state that explicitly rather than omitting the section.
-
Use clear verdict markers:
- Confirmed: Supported by linguistic evidence
- Probable: Well-supported but not conclusively proven
- Speculative: Possible but lacking sufficient evidence
- Folk etymology (unsupported): Popular but contradicted by evidence
- Backronym: Acronym invented after the word already existed
预期结果: Any folk etymologies identified and debunked with linguistic evidence, or an explicit statement that no folk etymologies are known for this word.
失败处理: If the status of a claimed etymology is genuinely uncertain (legitimate scholarly debate), present both sides with citations rather than forcing a verdict. Mark as "disputed" with the competing hypotheses.
第 6 步:Format the Structured Etymology Entry
Compile all findings into a standardized output format.
- Assemble the entry with the following structure:
## Etymology: [word]
**Modern form**: [word] ([language], [part of speech])
**Pronunciation**: /[IPA]/
**First attested**: [date], [source text/author]
### Etymological Chain
[Modern form] ([language], [date])
< [intermediate form] ([language], [date]) "[meaning]"
< [older form] ([language], [date]) "[meaning]"
< *[proto-form] ([proto-language]) "[reconstructed meaning]"
### Cognates
[Cognate table from Step 3]
### Semantic Drift
[Timeline from Step 4]
### Folk Etymologies
[Findings from Step 5, or "None known"]
### Sources
[Etymological dictionaries and corpora consulted]
### Confidence
[Overall confidence level: certain / probable / speculative / contested]
[Notes on any gaps or uncertainties in the analysis]
-
Review the entry for internal consistency: does the etymological chain match the cognate set? Does the semantic drift timeline align with the attestation dates?
-
Add a confidence assessment for the overall etymology, noting any weak links in the chain.
预期结果: A complete, internally consistent etymology entry with all sections filled, sources cited, and confidence levels marked.
失败处理: If any section could not be completed (e.g., no cognates found, no folk etymologies known), include the section with an explicit "not applicable" or "insufficient evidence" note rather than omitting it.
验证清单
- Modern form and first attestation are recorded with a date and source
- Etymological chain traces at least two historical stages (or notes why fewer exist)
- Reconstructed forms use standard notation (asterisk prefix)
- Cognate set includes words from at least two language branches (where available)
- Sound correspondences cited are regular (not ad hoc resemblances)
- Semantic drift timeline has dated entries with classified shift types
- Folk etymologies are addressed (either debunked or noted as absent)
- Sources are cited (dictionary names, corpus names, or URLs)
- Confidence level is explicitly stated
- Entry is internally consistent (chain, cognates, and drift align)
常见问题
- Surface resemblance mistaken for cognacy: Words that look similar across languages are not necessarily related (e.g., English "much" and Spanish "mucho" are from different roots). Always verify with regular sound correspondences, not visual similarity.
- Confusing borrowing with inheritance: A word present in two related languages may have been borrowed from one to the other rather than inherited from a common ancestor. Check the phonological form against expected sound-law outcomes to distinguish the two.
- Treating reconstructed forms as attested: PIE roots and other proto-forms are scholarly hypotheses, not historical documents. Always mark them with asterisks and note that they are reconstructed.
- Accepting folk etymologies uncritically: Popular origin stories are often more memorable than correct etymologies. Always check for attestation evidence and phonological plausibility before accepting a claimed origin.
- Ignoring semantic drift: A word's modern meaning may be very different from its original meaning. Tracing only the form without tracking the meaning can produce misleading results.
- Stopping too early: Many online sources give only one or two stages of a word's history. Push back to the deepest available reconstruction for a complete picture.
相关技能
manage-memory— Document etymology research findings for persistent reference across sessionsargumentation— Build and evaluate arguments about contested etymologies
Repositorio GitHub
Habilidades relacionadas
evaluating-llms-harness
PruebasEsta Skill de Claude ejecuta el benchmark lm-evaluation-harness para evaluar modelos de lenguaje en más de 60 tareas académicas estandarizadas como MMLU y GSM8K. Está diseñada para que los desarrolladores comparen la calidad de los modelos, realicen seguimiento del progreso del entrenamiento o reporten resultados académicos. La herramienta admite varios backends, incluidos modelos de HuggingFace y vLLM.
cloudflare-cron-triggers
PruebasEsta habilidad proporciona conocimiento integral para implementar Cron Triggers de Cloudflare y programar Workers mediante expresiones cron. Cubre la configuración de tareas periódicas, trabajos de mantenimiento y flujos de trabajo automatizados, manejando problemas comunes como expresiones cron inválidas y inconvenientes de zonas horarias. Los desarrolladores pueden utilizarla para configurar manejadores programados, probar activadores cron e integrar con Workflows y Green Compute.
webapp-testing
PruebasEsta habilidad de Claude proporciona un kit de herramientas basado en Playwright para probar aplicaciones web locales mediante scripts de Python. Permite verificación de frontend, depuración de interfaz de usuario, captura de pantallas y visualización de registros, mientras gestiona los ciclos de vida del servidor. Úsela para tareas de automatización de navegadores, pero ejecute los scripts directamente en lugar de leer su código fuente para evitar contaminación del contexto.
finishing-a-development-branch
PruebasEsta habilidad ayuda a los desarrolladores a completar el trabajo terminado verificando que las pruebas pasen y luego presentando opciones estructuradas de integración. Guía el flujo de trabajo para fusionar, crear PRs o limpiar ramas después de que se completa la implementación. Úsala cuando tu código esté listo y probado para finalizar sistemáticamente el proceso de desarrollo.
