skill-typst-research
- Repo stars 435
- Author updated Live
- Author repo nvim
- Domain
- Documentation
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @benbrastmckie · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: skill-typst-research
description: Research Typst documentation tasks. Invoke for Typst-language research. Thin wrapper that delega…
category: documentation
runtime: no special runtime
---
# skill-typst-research output preview
## PART A: Task fit
- Use case: Research Typst documentation tasks. Invoke for Typst-language research. Thin wrapper that delegates Typst research to typst-research-agent subagent. This skill activates when: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Trigger Conditions / Execution Flow / Stage 1: Input Validation” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Research Typst documentation tasks. Invoke for Typst-language research. Thin wrapper that delegates Typst research to typst-research-agent subagent. This skill activates when: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Trigger Conditions / Execution Flow / Stage 1: Input Validation” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Start with a small task and check whether the result follows “Trigger Conditions / Execution Flow / Stage 1: Input Validation”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: skill-typst-research
description: Research Typst documentation tasks. Invoke for Typst-language research. Thin wrapper that delega…
category: documentation
source: benbrastmckie/nvim
---
# skill-typst-research
## When to use
- Research Typst documentation tasks. Invoke for Typst-language research. Thin wrapper that delegates Typst research to…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Trigger Conditions / Execution Flow / Stage 1: Input Validation” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "skill-typst-research" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Trigger Conditions / Execution Flow / Stage 1: Input Validation
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, run shell commands | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Typst Research Skill
Thin wrapper that delegates Typst research to typst-research-agent subagent.
Trigger Conditions
This skill activates when:
- Task type is "typst"
- Research involves Typst documentation
- Typst-specific research is needed
Execution Flow
Stage 1: Input Validation
Validate task_number exists.
Stage 2: Preflight Status Update
Update status to "researching" BEFORE invoking subagent.
Stage 3: Prepare Delegation Context
Include task_context, focus_prompt, metadata_file_path.
Stage 4: Invoke Subagent
Use Agent tool with subagent_type: "typst-research-agent".
Stage 4b: Self-Execution Fallback
CRITICAL: If you performed the work above WITHOUT using the Agent tool (i.e., you read files,
wrote artifacts, or updated metadata directly instead of spawning a subagent), you MUST write a
.return-meta.json file now before proceeding to postflight. Use the schema from
return-metadata-file.md with the appropriate status value for this operation.
If you DID use the Agent tool, skip this stage -- the subagent already wrote the metadata.
Postflight (ALWAYS EXECUTE)
The following stages MUST execute after work is complete, whether the work was done by a subagent or inline (Stage 4b). Do NOT skip these stages for any reason.
Stage 5: Parse Subagent Return
Read the metadata file from specs/{N}_{SLUG}/.return-meta.json.
Stage 6: Update Task Status (Postflight)
Update state.json and TODO.md based on result.
Stage 7: Link Artifacts
Add research artifact to state.json. Update TODO.md per @.claude/context/patterns/artifact-linking-todo.md with field_name=**Research**, next_field=**Plan**.
Stage 8: Git Commit
Commit changes with session ID.
Stage 9: Return Brief Summary
Error Handling
Input Validation Errors
Return immediately if task not found.
Metadata File Missing
Keep status as "researching", report error.
Git Commit Failure
Non-blocking: Log failure but continue.
Return Format
Brief text summary (NOT JSON).
Decide Fit First
Design Intent
How To Use It
Boundaries And Review