CleanExpo/.claude/skills/research
.claude/skills/research/SKILL.md
# Research Skill **Name:** research **Triggers:** `/research`, "how does X work", "trace this flow", "explain the auth path", "where is X implemented" **Version:** 1.0.0 --- ## Purpose Answers codebase questions in an isolated subagent context so the main conversation never bloats with intermediate file reads. The parent session sees only the final 250-word summary — never the dozens of grep results, file fragments, and dead-end imports the subagent walked through to find the answer. This s
$ install --global
skillsauthnpx skillsauth add CleanExpo/CCW-CRM .claude/skills/researchInstall 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 16, 2026, 12:52 PM164.8s1 file scanned
SKILL.md
Research Skill
Name: research
Triggers: /research, "how does X work", "trace this flow", "explain the auth path", "where is X implemented"
Version: 1.0.0
Purpose
Answers codebase questions in an isolated subagent context so the main conversation never bloats with intermediate file reads. The parent session sees only the final 250-word summary — never the dozens of grep results, file fragments, and dead-end imports the subagent walked through to find the answer.
This skill is the first line of defence against context bloat. Use it whenever a question would otherwise require reading more than 2 files. The optimization audit found that 98.5% of tokens in long sessions are conversation re-reading; this skill cuts that at the source.
Commands
/research <question>
Dispatches an Explore subagent with the question. The subagent uses grep/glob to locate relevant code, reads only line ranges (never full files), traces imports, and stops as soon as it has the answer.
Returns to main context (≤250 words):
- Answer: 2-3 sentences directly answering the question
- Key files:
filepath:linereferences for the 3-5 most important locations - Gotcha: 1 non-obvious thing the user should know (edge case, hidden coupling, deprecated path)
Dispatch Target
Routes to the Explore subagent type. For deeper architectural questions (multi-layer trace, requires reading 5+ files), the Explore agent itself may delegate to existing project agents (spec-builder, truth-finder) — but those calls also stay isolated from the main context.
Process Rules (enforced inside the subagent)
- grep/glob first. Never read a file before locating the relevant lines.
- Line ranges only.
Readcalls must includeoffset+limitonce the section is known. - Stop early. As soon as the question is answered, return — do not "explore further" speculatively.
- Word budget. Output is hard-capped at 250 words. Trim verbose reasoning.
- No code generation. This skill is read-only research. For implementation use
/implementor/fix.
When NOT to use this skill
- The question is already answered in
docs/PROJECT_MAP.md— read that first - The user needs to MODIFY code — use
/fixor/implementinstead - Single-file lookup with a known path — just
Readit directly with offset/limit - Architecture-level design question requiring planning — use
/arch-plan
Related
.claude/skills/project-discovery/SKILL.md— runs the structural inventory this skill assumes exists.claude/agents/spec-builder/agent.md— for spec-level "what should this do" questions.claude/agents/truth-finder/agent.md— for verification of claims found during research
Related Skills
CleanExpo/youtube-uploader
content-media
VerifiedTrustedCommunity
Autonomously uploads CCW HeyGen demo videos to YouTube as Unlisted, collects video IDs, and patches DemoVideoBanner.tsx + video-registry.json. One-time OAuth setup required. Handles resume, retries, and ID propagation.
1SKILL.mdUpdated Apr 16, 2026
CleanExpo/unfreeze
data-ai
VerifiedTrustedCommunity
Clear the freeze boundary set by /freeze, allowing edits to all directories again. Use when you want to widen edit scope without ending the session. Use when asked to "unfreeze", "unlock edits", "remove freeze", or "allow all edits". (gstack)
1SKILL.mdUpdated Apr 16, 2026
CleanExpo/.claude/skills/spec-interview
tools
VerifiedTrustedCommunity
# Spec Interview Skill **Name:** spec-interview **Triggers:** `/spec-interview`, when requirements unclear **Version:** 1.0.0 --- ## Purpose Interviews user to gather complete requirements before planning. --- ## Interview Questions When requirements are unclear, ask: ### 1. Feature Clarity **Question:** "What is this feature supposed to do?" **Why:** Need clear objective ### 2. User Impact **Question:** "Who will use this and why?" **Why:** Understand user needs ### 3. Success Criteri
1SKILL.mdUpdated Apr 16, 2026
CleanExpo/ship
development
VerifiedTrustedCommunity
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is ready, asks about deploying, wants to push code up, or asks to create a PR. (gstack)
1SKILL.mdUpdated Apr 16, 2026