mohitagw15856/glossary-builder
skills/glossary-builder/SKILL.md
Build a translation/terminology glossary so a product's key terms render consistently everywhere. Use when asked to create a glossary, a termbase, a do-not-translate list, or to keep terminology consistent across translators/locales. Produces a glossary — each source term with its approved translation per locale, part of speech, definition/context, and do-not-translate flags — ready for a CAT tool or style guide.
$ install --global
skillsauthnpx skillsauth add mohitagw15856/pm-claude-skills glossary-builderInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 30, 2026, 7:17 AM221.9s1 file scanned
SKILL.md
- name:
- glossary-builder
- description:
- Build a translation/terminology glossary so a product's key terms render consistently everywhere. Use when asked to create a glossary, a termbase, a do-not-translate list, or to keep terminology consistent across translators/locales. Produces a glossary — each source term with its approved translation per locale, part of speech, definition/context, and do-not-translate flags — ready for a CAT tool or style guide.
Glossary Builder Skill
Inconsistent terminology is the most visible localization failure — when "dashboard" is translated three ways across one product, it looks amateur and confuses users. A glossary (termbase) fixes the key terms once, so every translator and every locale uses the approved rendering. This skill builds it: extract the terms that matter, define them in context, and set the approved translation (or do-not-translate flag).
Required Inputs
Ask for these only if they aren't already provided:
- The source material / domain — product UI, docs, or a term list; and the field (so definitions are right).
- Target locale(s) — which languages need approved translations.
- Existing decisions — any brand terms, product names, or prior translations to lock in.
- Do-not-translate candidates — brand/product names, trademarks, code/API terms.
Output Format
Glossary: [product/domain]
A termbase table — one row per term:
| Source term | Part of speech | Definition / context | Do-not-translate? | [Locale 1] | [Locale 2] | |---|---|---|---|---|---| | Dashboard | noun | the main metrics screen | no | 仪表板 | Tableau de bord | | Acme Cloud | proper noun | product name | yes (keep verbatim) | Acme Cloud | Acme Cloud | | sync (verb) | verb | to reconcile data both ways | no | 同步 | synchroniser |
Guidance included:
- Definitions/context — so a translator knows which meaning (e.g. "ticket" = support case, not event admission), preventing the classic wrong-sense error.
- Do-not-translate list — brand/product names, trademarks, code identifiers, UI elements that must stay in English.
- Part of speech / forms — flag terms where the form matters (verb vs. noun "filter").
- Consistency notes — preferred vs. avoided synonyms in the source itself ("use 'sign in', not 'log in'").
Output note: structured for import into a CAT tool (Trados/memoQ/Crowdin) or to sit in the localization style guide. Mark any translation that needs native review as (draft — confirm).
Quality Checks
- [ ] Each term has a definition/context so translators pick the right sense
- [ ] Do-not-translate terms (brand, product, code) are clearly flagged
- [ ] An approved translation is given per target locale (or marked draft for review)
- [ ] Part of speech / ambiguous forms are disambiguated
- [ ] Source-side consistency (preferred synonyms) is noted
- [ ] Structured for a CAT tool / style-guide import
Anti-Patterns
- [ ] Do not list terms without context — "ticket" or "filter" with no definition guarantees wrong-sense translations
- [ ] Do not omit the do-not-translate flags — that's how brand/product names get mangled across locales
- [ ] Do not present machine translations as approved — mark them draft for native review
- [ ] Do not ignore source consistency — if the source mixes "sign in/log in," the glossary should pick one
- [ ] Do not forget part of speech — a term that's both noun and verb often needs two entries
Based On
Terminology-management practice — termbases, do-not-translate lists, context definitions, CAT-tool glossary structure.
Related Skills
mohitagw15856/win-loss-analysis
business
VerifiedTrustedCommunity
Analyze why deals are won and lost and turn it into an action plan. Use when asked to run a win/loss analysis, review closed-won and closed-lost deals, understand why the team is losing to a competitor, or summarize sales feedback into patterns. Produces a structured win/loss report with themes, win/loss rates by segment and competitor, representative quotes, and prioritized actions for product, marketing, and sales.
1,117SKILL.mdUpdated Jul 2, 2026
mohitagw15856/which-skill
development
VerifiedTrustedCommunity
Route a fuzzy request to the right skill in this library. Use when the user is unsure which skill fits, asks 'which skill should I use for X', describes a task without naming a skill, or when a request could plausibly match several skills. Produces a best-fit recommendation with the inputs to gather, a runner-up with the tie-breaker, and a workflow recipe when the job spans multiple skills.
1,117SKILL.mdUpdated Jul 2, 2026
mohitagw15856/vuln-triage
testing
VerifiedTrustedCommunity
Triage a vulnerability or scanner finding — assess real severity, exploitability, and how urgently to fix. Use when asked to triage a CVE, prioritize scanner/pentest findings, assess a vuln's risk, or decide what to patch first. Produces a triage verdict: CVSS-informed severity adjusted for your context, exploitability, real risk, a fix/mitigation, and an SLA — so you fix what matters, not just what's red.
1,117SKILL.mdUpdated Jul 2, 2026
mohitagw15856/voice-of-customer-program
development
VerifiedTrustedCommunity
Stand up a Voice of Customer (VoC) program that turns feedback into action. Use when asked to build a VoC program, design a customer feedback loop, consolidate feedback sources, or set up a closed-loop feedback process. Produces a VoC program design — objectives, feedback sources and channels, a taxonomy, collection and analysis cadence, closed-loop routing, ownership, and success metrics.
1,117SKILL.mdUpdated Jul 2, 2026