thkt/brush
skills/brush/SKILL.md
Enrich a vague prompt by routing to the best skill or injecting relevant rules and constraints. Use when prompt is rough or missing perspective. Examples: "find bugs", "refactor this", "add feature X", プロンプト補完, ブラッシュアップ. Do NOT use when the prompt is already detailed.
$ install --global
skillsauthnpx skillsauth add thkt/dotclaude brushInstall 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 20, 2026, 9:28 AM13.8s1 file scanned
SKILL.md
- name:
- brush
- description:
- >
- allowed-tools:
- Read, Glob, Grep, LS
- model:
- opus
- argument-hint:
- [rough prompt]
- user-invocable:
- true
/brush
Route a vague prompt to the best skill, or enrich it with relevant rules and constraints when no skill fits.
Input
$1: rough prompt (required). If empty, output usage example and exit.
Execution
| Step | Action | Detail |
| --- | --- | --- |
| 1 | Classify | Identify task type from $1: refactor / bug-fix / feature / review / investigation / other |
| 2 | Scan skills | Glob ~/.claude/skills/*/SKILL.md; read descriptions of 3–5 candidates that match the task type |
| 3 | Route or enrich | See decision below |
| 4 | Output | See format below |
Decision
Route (skill found)
A skill is a clear match when its "Use when" description covers the task.
Output the routing recommendation. Include any gap — what the skill does NOT cover — if the original prompt had scope the skill won't handle.
Enrich (no skill match)
Rules from ~/.claude/rules/ are already loaded in context. Select the
relevant ones and make them explicit in the rewritten prompt.
| Category | Inject when | | --- | --- | | PRINCIPLES.md (Occam, DRY, YAGNI) | Refactoring, architecture decisions | | CODE_THRESHOLDS.md | Any code quality ask | | CODE_STRUCTURE.md | Structural or organization questions | | SECURITY.md | Auth, input handling, API endpoints | | PRE_TASK_CHECK.md | Broad implementation requests |
Only inject rules that are directly relevant. Do not add length for thoroughness.
Output Format
Route case
→ /skill-name [suggested args]
Covers: [what the skill handles from the original prompt]
Gap: [what it does not cover, if any]
Enrich case
Original:
> [verbatim input]
Enriched:
> [rewritten prompt]
Added:
- [rule or principle]: [what was injected and why]
Related Skills
thkt/use-cli-herdr
tools
VerifiedTrustedCommunity
Delegate implementation to codex (coder) via the herdr-agentchat plugin and drive a two-pane conversation to completion.
11SKILL.mdUpdated Jul 27, 2026
thkt/scribe
development
VerifiedTrustedCommunity
Extract recurring patterns from past closed PRs/issues and the research findings in workspace/research/, verify them against the latest code, and propose them to docs/wiki/ via PR.
11SKILL.mdUpdated Jul 20, 2026
thkt/dr
development
VerifiedTrustedCommunity
Create Decision Records (DR) in MADR v4 format with auto-numbering.
11SKILL.mdUpdated Jul 15, 2026
thkt/shake
development
VerifiedTrustedCommunity
Detect flaky tests by shaking them — repeated runs under varied order, parallelism, and seed — plus a static smell scan that flags latent flakiness in tests that currently pass. Classify each target as confirmed-flaky, latent-flaky, or stable and fix the root cause without weakening the test. Do NOT use to fix a confirmed single bug (use /fix) or for static-only code review (use /audit).
11SKILL.mdUpdated Jul 13, 2026