hellblazer/using-nx-skills
nx/skills/using-nx-skills/SKILL.md
Use when starting any conversation or task — establishes that nx skills must be checked before every response, including clarifying questions. If a skill plausibly applies, invoke it.
$ install --global
skillsauthnpx skillsauth add hellblazer/nexus using-nx-skillsInstall 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 26, 2026, 3:38 AM22.8s1 file scanned
SKILL.md
- name:
- using-nx-skills
- description:
- Use when starting any conversation or task — establishes that nx skills must be checked before every response, including clarifying questions. If a skill plausibly applies, invoke it.
- effort:
- low
Using nx Skills
If a skill plausibly applies, invoke it. False positives are cheap; misses cost time. Skills evolve — read the current version, don't rely on memory.
Plan Reuse
Before any multi-agent pipeline:
mcp__plugin_nx_nexus__plan_search(query="<task description>", limit=3)- If a match returns, present it as a starting structure
- If "No matching plans.", route normally
After a successful pipeline:
mcp__plugin_nx_nexus__plan_save(query="<task>", plan_json={"steps":[...],"tools_used":[...],"outcome_notes":"..."}, tags="<agents>")
Routing
Before code:
- About to implement →
/nx:brainstorming-gate(mandatory) - Multi-step →
/nx:create-plan - Needs design across modules →
/nx:architecturethen/nx:create-plan
Something broken:
- Failure / exception / unexpected behaviour →
/nx:debugimmediately - 2 failed fix attempts without
/nx:debug→ invoke now
Analyzing code:
- Structure / dependencies →
/nx:analyze-code - Why something behaves a certain way →
/nx:deep-analysis
Executing:
- Plan approved →
/nx:implement - Beads need enrichment →
/nx:enrich-plan
Quality gates:
- Code ready →
/nx:review-code - Plan ready →
/nx:plan-audit(validates against codebase) - Critique reasoning soundness →
/nx:substantive-critique - Tests written →
/nx:test-validate
Analytical questions (route through nx_answer):
- "how does…" / "tradeoffs…" / "compare…" / "why was this designed…" →
/nx:query - Design walks from concept to code →
/nx:research - Critique a change set →
/nx:review - Cross-corpus synthesis or ranking →
/nx:analyze - Why was this written this way →
/nx:debug - Documentation gaps →
/nx:document - 3+ validated findings to keep →
/nx:knowledge-tidy - PDF to index →
/nx:pdf-process
Direct search / query MCP calls are for keyword retrieval ("find X in collection Y"). Verb-shaped questions go through nx_answer.
RDR lifecycle: /nx:rdr-create → /nx:rdr-research → /nx:rdr-gate → /nx:rdr-accept → /nx:rdr-close. List/show: /nx:rdr-list, /nx:rdr-show NNN. Audit: /nx:rdr-audit.
Git: isolation → /nx:git-worktrees. Done → /nx:finishing-branch. Receiving review → /nx:receiving-review.
Catalog/linking: entries, links, tumblers, link-context seeding → /nx:catalog.
Reference (no agent dispatch): /nx:serena-code-nav, /nx:nexus, /nx:cli-controller, /nx:writing-nx-skills.
Essential MCP Tools (always available)
Sequential Thinking (mcp__plugin_nx_sequential-thinking__sequentialthinking): debugging hypotheses, design choices, plan evaluation. needsMoreThoughts: true to continue, isRevision: true to correct.
nx Storage Tiers (read widest → narrowest before any work):
- T3
nx search: permanent knowledge across all sessions/projects - T2
nx memory: project decisions, findings, session context - T1
nx scratch: this session's discoveries, shared across all agents
Write path: T1 (immediate, shared) → --persist to T2 (survives session) → /nx:knowledge-tidy to T3 (permanent, cross-project).
Common Mistakes
| Mistake | Correction |
|---------|------------|
| search for an analytical question | nx_answer via /nx:query or a verb skill |
| Test fails → try a different fix | /nx:debug |
| Implement without brainstorming-gate | brainstorming-gate first |
| Plan exists, start implementing | /nx:plan-audit first |
| Symbol callers via grep | /nx:serena-code-nav |
| Implement review feedback blindly | /nx:receiving-review first |
| Manual worktree setup | isolation: "worktree" on Agent tool, or /nx:git-worktrees |
Related Skills
hellblazer/review
development
VerifiedTrustedCommunity
Use when critiquing / auditing / reviewing a change set against decision history — tries the review plan library first (catalog lookup → decision-evolution traversal → extract → compare), falls through to /nx:query if nothing matches
1SKILL.mdUpdated Apr 17, 2026
hellblazer/research
documentation
VerifiedTrustedCommunity
Use when doing design / architecture / planning work that walks from prose (RDRs, docs, knowledge) into the modules implementing a concept
1SKILL.mdUpdated Apr 17, 2026
hellblazer/plan-promote
development
VerifiedTrustedCommunity
Use when surveying the plan library's runtime metrics to propose plans for promotion to a higher scope — advisory-only; dispatches the plan-promote-propose meta-seed (no lifecycle ops — those ship in RDR-079)
1SKILL.mdUpdated Apr 17, 2026
hellblazer/plan-inspect
business
VerifiedTrustedCommunity
Use when inspecting plan runtime metrics or enumerating dimension-registry usage — dispatches plan_match with dimensions={verb:plan-inspect}; strategy:default reports per-plan metrics, strategy:dimensions reports registry usage counts
1SKILL.mdUpdated Apr 17, 2026