bhaveshpabnani/humungousaur/llm-wiki
Claude Code and agent skill by bhaveshpabnani/humungousaur
- community
Checking that the SKILL.md file is still in the repository.
Native Humungousaur skill for LLM Wiki. Use when a task calls for llm wiki workflows, readiness checks, artifacts, or approval-gated local/provider actions.
Install
npx vskill@latest install bhaveshpabnani/humungousaur/llm-wikiSKILL.md
LLM Wiki
This is a Humungousaur-native skill. It is authored inside this repository and uses only Humungousaur-owned tools, approval gates, artifacts, and optional dependency records.
When To Use
Use this skill when the user asks for llm wiki planning, execution, verification, troubleshooting, or artifact creation inside Humungousaur.
Tool Map
tool_searchtool_describecapability_surfacewrite_notenative_security_policytool_output_storellm_wiki_build_prepareweb_searchweb_extractresearch_web_pagesx_searchprovider_registryexecute_codecredential_file_policy
Workflow
- Clarify the user's concrete llm wiki objective, target environment, credentials already configured, and expected artifact or action.
- Use
tool_searchorcapability_surfaceto find the native Humungousaur tools for the domain before choosing a path. - Run safe inspection/readiness steps first and write bounded notes or artifacts under the workspace or data directory.
- Collect sources with web/research tools, store evidence, and separate verified facts from hypotheses.
- For security or OSINT work, use defensive scope, authorization notes, and credential-file policy records before running active checks.
- Summarize what ran, what was skipped, what remains blocked, and the exact files or records created.
Safety And Boundaries
- Do not import, execute, or vendor upstream assistant code for this skill.
- Do not store raw secrets; store only environment variable names, secret references, or readiness booleans.
- Use approvals for writes, sends, purchases, desktop control, process launches, provider calls, and destructive operations.
- Do not run network scans, exploit tooling, cloud jobs, or GPU workloads without explicit authorization and scope.
Verification
- Record concrete evidence paths or tool outputs before claiming completion.
- Prefer dry-run or prepared artifacts when credentials, hardware, licenses, or live services are missing.
- If a provider-specific runtime is not configured, report the missing credential or binary by name and stop before live execution.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/software-engineering/llm-wiki/SKILL.md
Popularity
- Repository stars
- 8
- 7-day trend score
- 16
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/bhaveshpabnani/humungousaur/llm-wiki)