nsheaps/word-vomit
plugins/word-vomit/skills/word-vomit/SKILL.md
Use when the user wants to dump unstructured thoughts, ideas, or notes that need to be organized. Triggers: "brain dump", "word vomit", "let me think out loud", "process my notes", "organize my thoughts", "dump my ideas".
$ install --global
skillsauthnpx skillsauth add nsheaps/ai-mktpl word-vomitInstall 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: Apr 22, 2026, 4:18 PM24.6s1 file scanned
SKILL.md
- name:
- word-vomit
- description:
- |
- Triggers:
- brain dump", "word vomit", "let me think out loud", "process my notes", "organize my thoughts", "dump my ideas".
Word Vomit Workflow
Process unstructured user thoughts into organized, actionable items.
Quick Start
- User writes thoughts to a scratch file or sends them as a message
- This skill guides you through categorization and filing
Workflow
Step 1: Capture
If the user hasn't already written their thoughts to a file, save them to:
.claude/scratch/word-vomit-<date>.md
Add the marker at the top of the file:
<!-- word-vomit -->
# Brain Dump — <date>
- thought 1
- thought 2
...
Step 2: Process
For each item in the file:
- Parse: Split into discrete thoughts (one per bullet or paragraph)
- Categorize using this table:
| Category | Destination | Labels |
| ----------------- | ---------------------------- | ------------- |
| Bug | GitHub issue | bug |
| Task | GitHub issue or TaskCreate | none |
| Feature idea | GitHub issue | enhancement |
| Research question | GitHub issue | research |
| Decision needed | Present to user with options | none |
| Observation/note | Append to relevant doc | none |
| Reminder | TaskCreate with context | none |
| Duplicate | Link to existing issue | none |
- Deduplicate: Search existing issues with
gh issue listbefore creating new ones - File: Create issues, tasks, or doc entries as appropriate
Step 3: Update Source
After filing each item, update the original file:
# Before
- fix the auth endpoint returning 500
# After
- ~~fix the auth endpoint returning 500~~ → [nsheaps/agent-team#42](https://github.com/nsheaps/agent-team/issues/42)
Rules:
- Strikethrough original text with
~~text~~ - Add link to filed item
- Never delete original text
- If input was a message (not file), include mapping in summary
Step 4: Summarize
Provide a structured summary:
## Processed Items
| # | Original | Category | Filed As | Priority |
| --- | --------------- | -------- | --------------- | -------- |
| 1 | "fix auth 500" | Bug | nsheaps/repo#42 | p1 |
| 2 | "add dark mode" | Feature | nsheaps/repo#43 | p3 |
## Decisions Needed
- Redis vs Memcached — need user input on requirements
Quality Standards
- Zero drops: Every item must appear in the output
- No fabrication: Never invent details
- Deduplication: Always check for existing issues first
- Traceability: Every filed item links back to original thought
- Correct routing: Items go to the right repo with the right labels
Tips
- For large dumps (15+ items), process in batches
- If an item spans multiple categories, split it
- Vague items get filed with
needs-clarificationlabel - Default ambiguous items to "Task" category
Related Skills
nsheaps/claude-code
tools
VerifiedTrustedCommunity
Reference material for Claude Code internals — the on-disk layout under ~/.claude and project-scope .claude, the plugin cache, session-env propagation, and the full hook lifecycle. Auto-recall when working on Claude-Code-related tasks: writing or debugging hooks, authoring plugins, inspecting session state, troubleshooting why an env var is or isn't visible to a Bash tool call, or when paths under ~/.claude or ~/.claude/plugins/ come up.
3SKILL.mdUpdated May 6, 2026
nsheaps/github-app-token
development
VerifiedTrustedCommunity
Manage GitHub App installation tokens in Claude Code sessions. Use when tokens expire, auth errors occur in long-running sessions, or when setting up GitHub App credentials for agent teams. <example>my github token expired</example> <example>refresh the github app token</example> <example>check token status</example> <example>set up github app authentication for this session</example>
3SKILL.mdUpdated Apr 22, 2026
nsheaps/auto-config
tools
VerifiedTrustedCommunity
Auto-detect project formatting tools and configure edit-utils settings
3SKILL.mdUpdated Apr 22, 2026
nsheaps/op
tools
VerifiedTrustedCommunity
Use this skill when the user asks about 1Password, secrets management, retrieving credentials, using op CLI, service accounts, secret references, vault operations, or any task involving the 1Password CLI (op). Also use when needing to inject secrets into environment variables, read passwords or API keys from 1Password, or manage 1Password items from the command line.
3SKILL.mdUpdated Apr 22, 2026