.agents/skills/cross-link-skills/SKILL.md
Repair and verify cross-references between SKILL.md files after a skill is created, renamed, removed, or restructured. Ensures every skill that calls another skill references the correct name, and every skill that is called has accurate "Called by" context. Load after universal-skill-creator creates a skill, after improve-skills completes a cycle, after a skill is renamed or removed, or when the user asks to fix cross-references, sync skill links, repair broken skill references, or update skill cross-links.
npx skillsauth add dvy1987/agent-loom cross-link-skillsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are a cross-reference repair engine for agent skills. After any structural change — skill created, renamed, removed, or rewired — you scan every SKILL.md file, detect stale or missing cross-references, and fix them. You only touch cross-reference strings — never workflow logic, hard rules, examples, or prose.
Only edit cross-reference strings. Allowed edits: skill name strings, Called by: / Calls: lines, → routing arrows, frontmatter description references to other skill names. Nothing else.
Never rewrite workflow steps, hard rules, examples, or prose.
Always scan ALL skills. Read every .agents/skills/*/SKILL.md to build the full registry before making any edits.
Run validate-skills on every SKILL.md you edited. Must still score ≥10/14 after your edits.
Read every .agents/skills/*/SKILL.md. For each skill, extract:
name (from frontmatter)invoke, call, load, →, backtick-quoted skill names)Store as an in-memory registry of {name, calls[], calledBy[]}.
Compare the registry against the trigger event:
Renamed skill (old-name → new-name):
old-name. Every hit is stale — replace with new-name.Removed skill:
New skill:
Rewired skill (changed what it calls):
For each stale or missing reference found in Step 2:
Run validate-skills on every SKILL.md that was edited. If any skill drops below 10/14 after the edit, undo that edit and flag it for manual review.
Deliver the cross-link report (see Impact Report below).
sources field — skill names in sources are metadata, not cross-references. Leave them alone.Stale references found: 13 process-decomposer/SKILL.md: 2 references → fixed setup-evaluation/SKILL.md: 4 references → fixed project-orchestrator/SKILL.md: 2 references → fixed create-agent-prompt/SKILL.md: 2 references → fixed skill-finder/SKILL.md: 1 reference → fixed tool-finder/SKILL.md: 1 reference → fixed ROUTING.md: 1 reference → fixed (not a SKILL.md, flagged for library-skill)
Validation: all 6 edited skills still ≥10/14 ✓
</output>
</example>
<example>
<input>New skill cross-link-skills was just created. Run cross-link repair.</input>
<output>
Cross-link repair triggered by: new skill (cross-link-skills)
Skills scanned: 36
New skill calls: validate-skills New skill called by: universal-skill-creator, improve-skills universal-skill-creator/SKILL.md: reference present ✓ improve-skills/SKILL.md: reference present ✓
Stale references: 0 Missing references: 0 No edits needed. </output> </example> </examples>
Cross-link repair complete: YYYY-MM-DD
Trigger: [created | renamed | removed | rewired] — [skill name(s)]
Skills scanned: N
Stale references found: N
References fixed: N
References flagged for manual review: N
SKILL.md files edited: [list]
Validation: all edited skills ≥10/14 [✓ | list failures]
development
Run a fast, read-only health check across all skills in the library and produce a structured quality report — without modifying anything. Load when the user asks to validate skills, check skill health, audit the library, run a skill quality check, or when improve-skills needs a pre-flight before starting its cycle. Also triggers on "what's wrong with my skills", "check all skills", "skill health report", "are my skills ok", or "pre-flight check". Called automatically by improve-skills before any improvement work begins, and by universal-skill-creator after every new skill is created. Never modifies any file — only reads and reports.
tools
Design, build, validate, and ship production-grade agent skills that work across OpenAI Codex, Ampcode, Factory.ai Droids, Google Gemini, Warp, Bolt.new, Replit, GitHub Copilot, Claude Code, VS Code, Cursor, and any agentskills.io compliant platform. Load when the user asks to create a skill, build a custom skill, write a SKILL.md, package instructions as a reusable agent capability, convert a workflow into a skill, improve or audit an existing SKILL.md, generate a meta-skill, make a cross-platform skill, turn a repeated task into automation, or design agent skills that target multiple AI coding tools simultaneously. Also load for skill stacking, skill scoping, skill discovery, parameterized skills, skill publishing to GitHub or skills.sh, or when the user says skill creator, skill architect, or skill engineer.
tools
Identify the right tool for a process step. Load when a user or skill needs to check tool availability, confirm CLI compatibility, or determine if an MCP server is needed. Triggers on "what tool", "do I need an MCP", "is [tool] available", "which tool handles", "tool lookup", "check tool availability", "find a tool for". Called by process-decomposer and agent-builder when assigning tools to steps.
development
Apply the Red-Green-Refactor cycle to software development. Load when the user asks to write code using TDD, create unit tests, implement a feature with test coverage, refactor code, or ensure software quality through automated testing. Also triggers on "test-driven development", "write tests first", "TDD this feature", "Red-Green-Refactor", "ensure 100% test coverage", or any request to build software with a test-first approach. Supports unit, integration, and end-to-end testing strategies.