grill-with-docs · haowjy, claude — Claude Code skill: what it does, how to install
grill-with-docs challenges concepts and decisions by grounding every critical inquiry strictly in local repository documents.
Apache-2.0 556 installs ★ 601 updated 2026-10-25
npx skills add haowjy/creative-writing-skills --skill grill-with-docs -a claude-codeWhat grill-with-docs does
This skill triggers /creative-writing-skills:grill alongside /creative-writing-skills:knowledge-layers. It forces the model to examine internal project vocabulary, active work artifacts, recorded decisions, and repository docs before fetching external data.
Context retrieval stays disciplined. Rather than dumping the entire file tree into context, the agent launches a bounded @explorer. It delegates transcript searches to @session-miner only when details exist exclusively in session logs. Any lasting terminology or consensus that emerges must be written back into the project docs.
What it helps with
- interrogate proposals against existing repository documentation
- verify terminology against project vocabulary before making changes
- delegate context retrieval to a bounded
@explorersubagent - document fresh decisions and definitions directly into project files
Example prompts for the agent
- Grill this proposed architecture update strictly against our repository docs
- Run grill-with-docs on the new feature spec using existing project decisions
- Challenge our migration approach and verify all terms against the glossary
How to install grill-with-docs
1Skills CLI (Vercel)
npx skills add haowjy/creative-writing-skills --skill grill-with-docs -a claude-code2Manually: put the files in place
~/.claude/skills/grill-with-docs/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/grill-with-docs/
1Skills CLI (Vercel)
npx skills add haowjy/creative-writing-skills --skill grill-with-docs -a codex2Manually: put the files in place
.agents/skills/grill-with-docs/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add haowjy/creative-writing-skills --skill grill-with-docs -a cursor2Manually: put the files in place
.cursor/skills/grill-with-docs/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install haowjy/creative-writing-skills plugin/claude/skills/grill-with-docs2Manually: put the files in place
.github/skills/grill-with-docs/SKILL.md1Skills CLI (Vercel)
npx skills add haowjy/creative-writing-skills --skill grill-with-docs -a gemini-cli2Platform CLI
gemini skills install https://github.com/haowjy/creative-writing-skills --path plugin/claude/skills/grill-with-docsManually: put the files in place
.devin/skills/grill-with-docs/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add haowjy/creative-writing-skills --skill grill-with-docs -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about grill-with-docs
How to install grill-with-docs in Claude Code?
Run npx skills add haowjy/creative-writing-skills --skill grill-with-docs -a claude-code. The skill will be placed at ~/.claude/skills/grill-with-docs/SKILL.md.
What does grill-with-docs do?
It interrogates project plans and assumptions by grounding every critique in existing repository artifacts and decisions.
How does it handle missing documentation?
It dispatches an @explorer subagent for targeted reading and calls @session-miner only when data resides in chat transcripts.
Source text
SKILL.md · Apache-2.0
--- name: grill-with-docs description: | Use when grilling should be grounded primarily in project artifacts. Loads `/grill`, checks project vocabulary and prior decisions first, and spawns bounded explorers when the answer should come from docs. metadata: type: reference --- # Grill With Docs Load `/creative-writing-skills:grill` if it isn't already loaded. Load `/creative-writing-skills:knowledge-layers` if it isn't already loaded. Use this when the challenge should be grounded primarily in project artifacts. Check repo docs, existing prompts, prior decisions, active work artifacts, and project vocabulary before reaching for external sources. When the answer should come from project materials beyond what is already in context, spawn a bounded `@explorer` instead of bulk-reading the tree yourself. Use `@session-miner` only when the missing context lives in transcripts rather than artifacts. If the conversation produces durable terminology or decisions, update the right documentation surface.
© haowjy · Apache-2.0 · haowjy/creative-writing-skills
Similar skills
All skills for Agent setup: memory, context, orchestration →grill-with-docs by other authors comes first.