Scans the wiki vault and adds missing [[wikilinks]] between pages that are related but not yet connected. Use this skill when the operator says "link my pages", "find missing links", "cross-reference the wiki", "connect my wiki", "add wikilinks", or after any large ingest to weave new pages into the existing knowledge graph. Also trigger when orphaned pages need connecting or when wiki-lint reports fragmented tag clusters. This is a write-heavy skill — it modifies page files to insert links, unlike wiki-lint which only reports.
Scans .claude/skills/ to discover which skills exist in this workspace and selects the best match for a described task. Invoke whenever an operator asks "is there a skill for X", "what skill should I use to do Y", "does a skill exist for Z", or before authoring a new skill to prevent duplicates. Returns ranked matches with descriptions and invocation names so the operator can immediately use the right skill or confirm no match exists before proceeding to skill-creator.
Scaffolds a new conformant skill under .claude/skills/, including the folder, SKILL.md frontmatter (name, description, model pin), body structure, and optional references/ directory. Invoke after find-skills confirms no existing skill covers the need, or when an operator asks to "create a skill for X", "add a skill that does Y", or "build a skill to automate Z". Also handles registering the new skill's model pin in docs/conventions/skill-model-pins.md as a mandatory part of creation.
Summarises a fetched web source into structured, cited notes suitable for a research brief. Extracts key claims, attributes each to the source URL, and flags unsupported or hedged assertions. Designed for use inside the Researcher Worker of research swarms.
Audits a swarm directory against the 7-point conformance checklist in swarms/PROTOCOL.md and emits a structured gap report. Invoked when an operator wants to verify a swarm before promotion, during Gate 3 of a new swarm scaffold, or whenever a swarm's conformance status is in question.
Scaffolds a new conformant multi-agent swarm under swarms/ against swarms/PROTOCOL.md, producing CLAUDE.md, agents/ (orchestrator, worker, validator stubs), role-registry.md, a validation-contract stub, and a builds/ directory so the result passes all 7 protocol conformance checks. Invoke when an operator asks to "create a new swarm for X", "set up a multi-agent workflow to do Y", or "scaffold a swarm that handles Z". Use only when the task genuinely requires multiple roles, multiple sessions, or adversarial validation — if it fits in one context window, use a composite skill instead.
Enforces and normalizes tags across the wiki against the controlled vocabulary in wiki/schema/tag-taxonomy.md. Use this skill when the operator says "fix my tags", "normalize tags", "tag audit", "clean up tags", "tag taxonomy", or "my tags are a mess". Also use when creating or updating wiki pages and the right tags are unclear. Operates in three modes: Audit (report current state), Normalize (apply fixes), and Classify (tag a single new page). Always reads the taxonomy file before assigning any tags.
Distills a raw source file from wiki/raw/ into a structured wiki page under wiki/wiki/, following the schema in wiki/schema/. Use this skill when the operator wants to add new knowledge to the wiki — "ingest this doc", "add this to the wiki", "process this source", "promote my drafts", or whenever a file lands in wiki/raw/ and needs to become a queryable wiki page. Handles documents (markdown, text, PDF) and structured data (JSON, CSV). Does not replace wiki-update, which refreshes an existing page against a changed source.
Audits the wiki vault for structural health problems and auto-fixes deterministic issues. Use this skill when the operator wants to check the wiki for issues — "audit my wiki", "wiki health check", "find broken links", "fix my frontmatter", "what needs fixing", "clean up the wiki", or before any major query session or ingest. Reports orphans, broken wikilinks, missing or invalid frontmatter, schema violations, stale content, and tag inconsistencies. Auto-fixes deterministic issues; reports judgment-bearing issues for operator review. Runs cross-linker on fragmented tag clusters at the end of every run.
Reports the current state of the wiki vault — page counts, category breakdown, hub pages, orphans, stale entries, and a delta showing what has changed since the last ingest. Use this skill when the operator asks "what's the status", "wiki dashboard", "how many pages", "what's stale", "what's been ingested", "show me the delta", or "wiki health overview". Also surfaces structural insights (top hubs, fragmented clusters, bridge pages) when the operator asks "wiki insights", "what's central", or "show me the hubs". Read-only: this skill reports and recommends; it does not modify any files.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.
nexuschainsSkill