hiivmind

This skill should be used when the user asks to "create a new skill", "scaffold skill", "build a skill", "new skill from scratch", "start a new skill", "add skill to plugin", "build from idea". Triggers on "create", "new", "build", "scaffold", "idea", "start skill", "add skill".

This skill should be used when the user asks to "validate workflow", "fix workflow", "upgrade schema", "refactor workflow", "check workflow errors", "restructure workflow", "migrate version", "lint workflow", "cleanup dead code", "extract subflow". Triggers on "validate", "fix", "upgrade", "refactor", "lint", "check", "migrate", "restructure", "schema", "cleanup", "broken workflow".

This skill should be used when the user asks to "assess a skill", "assess my plugin", "analyze coverage", "check skill health", "evaluate plugin", "skill inventory", "coverage report", "what's the state of my plugin", "where does this skill sit", "spectrum position", "is this skill appropriately formalized". Triggers on "assess", "evaluate", "coverage", "health", "inventory", "spectrum", "fit analysis".

This skill should be used when the user asks to "create gateway", "set up intent routing", "create intent mapping", "validate gateway", "add routing to plugin", "multi-skill routing", "update gateway". Triggers on "gateway", "intent routing", "intent mapping", "routing", "multi-skill", "3VL".

This skill should be used when the user asks to "create gateway", "add gateway command", "set up intent routing", "create plugin entrypoint", "generate gateway", "unified command for plugin", or needs to create a gateway command for a multi-skill plugin. Triggers on "create gateway", "gateway create", "add gateway", "plugin entrypoint", "intent routing", "unified command", "gateway setup".

This skill should be used when the user asks to "validate gateway", "check gateway routing", "verify gateway command", "lint gateway", "test gateway", or needs to verify a gateway command structure is complete and correct. Triggers on "validate gateway", "check gateway", "verify gateway", "lint gateway", "test gateway", "gateway errors".

This skill should be used when the user asks to "create intent mapping", "add intent detection", "generate intent-mapping.yaml", "define keyword routing", "set up 3VL matching", "create routing rules", or needs to create intent-mapping.yaml for a gateway. Triggers on "intent create", "create intent", "intent mapping", "keyword routing", "3VL setup", "routing rules", "intent detection".

This skill should be used when the user asks to "validate intent mapping", "check intent rules", "verify routing", "lint intent-mapping.yaml", "check 3VL logic", "find routing gaps", or needs to verify an intent-mapping.yaml is correct. Triggers on "validate intent", "check intent", "verify routing", "lint intent", "3VL validation", "routing gaps".

Add documentation source to corpus. Triggers: "add source", "add git repo", "include blog posts", "add local documents", "extend corpus with web pages", "add team docs", "add PDF to corpus", "import PDF book", "split PDF into chapters".

Create and manage cross-corpus concept bridges in registry-graph.yaml. Use when users want to link concepts across corpora, create query-routing aliases, or validate cross-corpus relationships. Triggers: "bridge", "cross-corpus", "link corpora", "registry graph", "alias", "bridge show", "bridge validate", "add alias".

Non-interactive (re)build of a corpus index for pipelines. Replays the decisions captured in config.build (segmentation, organization, skip_sections, embeddings, verify prefs) instead of prompting, regenerates index.yaml + the rendered markdown, optional graph and embeddings, and writes build-result.yaml (headless contract). Triggers: "headless build", "rebuild corpus headless", "build result file", scheduled rebuilds. Users normally want `build`.

This skill should be used when the user asks to "build corpus index", "create index from docs", "analyze documentation", "populate corpus index", or needs to build the initial index for a corpus that was just initialized. Triggers on "build my corpus", "index the documentation", "create the index.md", "finish setting up corpus", "hiivmind-corpus build", or when a corpus has placeholder index.md that says "Run hiivmind-corpus-build", or "create the index.yaml".

This skill should be used when the user asks "what corpora do I have installed?", "list my documentation corpora", "find installed corpus plugins", "what hiivmind-corpus plugins are available?", "check the docs", "search the documentation", "what do the docs say", "look up in corpus", or needs to discover installed documentation corpus skills. Also use when a generic documentation query doesn't specify which corpus to search.

This skill should be used when the user asks to "add more detail to corpus", "enhance corpus coverage", "expand section in index", "need more depth on [topic]", "corpus is too shallow", "add entries for [topic]", or wants deeper coverage of specific topics in an existing corpus. Triggers on "enhance [topic] section", "more detail on [feature]", "expand the index", "add depth to corpus", or "hiivmind-corpus enhance".

Headless (non-interactive) enrichment of stale index entries. Re-scans changed source files to regenerate entry metadata (title, summary, tags, keywords, category), assigns concepts from the existing graph.yaml, verifies summaries against content, clears stale flags, re-renders, and re-embeds. Run after hiivmind-corpus-refresh-headless in automated pipelines, or standalone to repair a corpus with accumulated stale entries. Requires a v2 index (index.yaml).

View, validate, and edit a corpus concept graph (graph.yaml). Triggers: "graph", "show graph", "validate graph", "concept graph", "view concepts", "graph.yaml", "show relationships", "add concept", "add relationship".

Headless multi-repo governance audit. Fetches per-repo API data, evaluates the 11-check catalog deterministically via evaluate_checks.py honoring team dismissals, writes healthcheck-result.yaml (kind: healthcheck) and updates the committed healthcheck.yaml governance record. Zero prompts; explicit inputs only. Use when: a scheduled fleet audit runs, an orchestrator needs repo grades. Trigger phrases: "headless healthcheck", "fleet healthcheck", "scheduled governance audit".

Headless config sync. Refreshes workspace config sections against GitHub without prompting, replaying the section selection recorded by interactive gh-refresh (automation.refresh_sections) or an explicit sections input. Writes refresh-result.yaml (kind: refresh). Zero prompts; explicit inputs only. Use when: a scheduled run found refresh_needed, an orchestrator syncs catalogs before a fleet audit. Trigger phrases: "headless refresh", "scheduled config sync".

Headless workspace status pre-check for schedulers and orchestrators. Computes per-section config freshness and API rate limit, writes status-result.yaml (kind: status) per the headless result contract. Zero prompts; explicit inputs only — never discovers a workspace. Use when: a scheduled run must decide whether a refresh is warranted, an orchestrator gates on refresh_needed. Trigger phrases: "headless status", "status headless", "scheduled status check".

Run a v2 workflow non-interactively under its headless policy. ASKs are recorded, withheld mutations become proposed_actions, notable items become typed findings; writes workflow-run-result.yaml (kind: workflow-run). Zero prompts; explicit inputs only. Use when: a scheduler runs a workflow unattended, an orchestrator needs a workflow's findings as data. Trigger phrases: "headless workflow run", "run workflow headless", "scheduled workflow".

Handle session wake-up when the heartbeat hook detects pending work. Processes triggered workflows, runs auto workflows immediately, and presents non-auto workflows for user approval. Use this when: session starts with pending workflows, heartbeat detected changes, stale config needs attention, GitHub state changed since last session. Trigger phrases: "heartbeat", "wake up", "session start", "what changed", "pending workflows", "check for changes", "session summary", "what happened", "github changes since last session", "morning briefing", "status update", "run heartbeat", "check heartbeat", "poll github".

Manage event-driven workflows for GitHub automation. List, enable, disable, run, create, and check status of workflows that trigger on session start, after operations, or on demand. Use this when: managing automation rules, configuring what happens on session start, enabling/disabling workflows, running workflows manually, creating custom workflows, checking workflow status. Trigger phrases: "list workflows", "enable workflow", "disable workflow", "run workflow", "create workflow", "workflow status", "show automations", "manage automations", "configure automation", "what workflows are active", "turn on workflow", "turn off workflow", "automation settings", "heartbeat config", "event triggers", "workflow list", "my workflows".

Sync cached workspace config with current GitHub state. This skill should be used when: config is stale, "ID not found" errors occur, project fields changed, new projects created, options renamed, or after making changes in GitHub UI. Trigger phrases: "refresh config", "sync workspace", "update cache", "ID not found", "field not found", "stale config", "refresh projects", "config out of date", "resync GitHub", "fix stale config", "revalidate github IDs", "config refresh", "github settings changed", "reload github config", "update github cache", "sync github state". Supports selective refresh of sections: workspace, projects, views, repo_settings, automations, relationships, teams.

Execute GitHub operations with automatic context enrichment from cached workspace. Use this for ANY GitHub operation, not just complex ones. Simple operations like creating issues are enriched with project linking, milestone resolution, and field assignments. Direct `gh issue create` misses these benefits. This skill should be used when: creating issues, closing issues, merging PRs, setting milestones, adding labels, updating project status, protecting branches, triggering workflows, creating releases, managing secrets. Trigger phrases: "create issue", "close issue #", "merge PR", "set milestone on", "add label to", "update project status", "add to project board", "protect branch", "trigger workflow", "create release", "set secret", "list PRs", "merge pull request", "remove label", "create milestone", "archive project item", "rerun workflow", "cancel action", "github issue", "github pr", "github milestone", "make a new issue", "open pull request", "start workflow", "new issue for", "assign to milestone", "mov

This skill should be used when the user asks to "post on solvr", "create a problem", "create a question", "ask a question", "propose an idea", "new post", "submit a problem", "new idea", or needs to create content on the Solvr knowledge base. Triggers on "post", "create", "new problem", "new question", "new idea", "ask", "propose", "submit problem".

This skill should be used when the user asks to "vote", "upvote", "downvote", "comment", "bookmark", "evolve idea", "accept answer", "report content", "engage with post", or needs to interact with existing Solvr content. Triggers on "vote", "upvote", "downvote", "comment", "bookmark", "evolve", "accept", "report", "engage".

This skill should be used when the user asks to "browse solvr", "show feed", "trending", "stuck problems", "unanswered questions", "latest posts", "explore solvr", "what's new", "browse problems", "browse questions", "browse ideas", or needs to discover content on Solvr. Triggers on "feed", "trending", "stuck", "unanswered", "browse", "explore", "latest", "what's new".

This skill should be used when the user asks to "view profile", "update profile", "my notifications", "manage api keys", "register agent", "claim agent", "my posts", "my contributions", or needs to manage their Solvr account. Triggers on "profile", "me", "notifications", "api key", "api keys", "claim", "register agent", "my posts", "my contributions".

This skill should be used when the user asks to "search solvr", "find on solvr", "lookup", "query solvr", "how to", "search problems", "search questions", "search ideas", "find solutions", or needs to search the Solvr knowledge base. Triggers on "search", "find", "lookup", "query", "how to", "look up", "search for".

This skill should be used when the user asks to "solve a problem", "provide an approach", "answer a question", "respond to an idea", "tackle", "submit approach", "submit answer", "write an answer", "help solve", or needs to compose and submit a solution to a Solvr post. Triggers on "solve", "approach", "answer", "respond", "tackle", "submit answer", "submit approach", "help solve", "write answer".

Unified entry point for AI Persona OS — setup wizard, in-chat commands, context protection, monitoring, and learning system. Say 'persona setup' to start, 'persona status' for dashboard, or 'persona help' for all commands.

Context protection and checkpointing system for AI Persona OS (Never-Forget Protocol). Monitors context window usage and automatically saves progress at critical thresholds to prevent context loss. Enables 95% recovery from interruptions. Triggers: checkpoint, save context, preserve, resume, context protection, never-forget, recovery, context loss, emergency checkpoint, survival mode, flush context, session recovery, decision tracking, action items, resume point, proactive save, forced checkpoint, natural break, risky operation, context threshold, vigilant mode, active checkpoint, emergency flush, critical save, context percentage, checkpoint frequency, workspace memory, permanent facts, recovery protocol, session continuity, progress preservation.

Runtime in-chat commands for AI Persona OS. Routes 11 commands to appropriate actions - status dashboard with health indicators, show persona (display SOUL.md identity), show memory (display MEMORY.md contents), health check (run diagnostics script), security audit (run security validation), show config (validate configuration), help (command reference), checkpoint (save context snapshot), advisor on/off (toggle proactive mode), switch preset (change persona configuration). Recognizes natural language variants like "how's my system" for status, "what's my persona" for show persona. Keywords: status, dashboard, show persona, show memory, health check, security audit, show config, help, checkpoint, advisor, switch preset, commands, diagnostics, validate, proactive mode

Ambient monitoring and health pulse for AI Persona OS sessions. Monitors context window usage, provides proactive suggestions when advisor mode is enabled, detects session starts to resume previous work, performs silent memory maintenance (pruning old entries, archiving logs), and surfaces health status when needed. Trigger keywords: heartbeat, monitor, pulse, context check, health, session start, memory maintenance, ambient, housekeeping, status check, session resume, context health.

Captures, reviews, and promotes learnings, errors, and feature requests in the AI Persona OS. Logs structured entries to ~/workspace/.learnings/ (LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md), scans for patterns weekly, promotes repeated learnings (3+ occurrences) to MEMORY.md, and implements 4 growth feedback loops: Curiosity (knowledge gaps → questions → pattern tracking), Pattern Recognition (repeated requests → automation proposals), Capability Expansion (limitations → research → tooling), and Outcome Tracking (decisions → follow-up → lessons). Supports continuous improvement through structured learning capture, mistake analysis, error tracking, pattern detection, and growth-oriented behavioral loops. Trigger keywords: learn, mistake, error, review, promote, growth, learning, capture, pattern, improvement, feature request.

First-run setup wizard for AI Persona OS. Guides users through initial workspace configuration with preset selection (coding assistant, executive assistant, marketing assistant, or custom persona). Detects existing installations, gathers personalization context, builds workspace structure with templates, and configures SOUL.md, USER.md, and MEMORY.md files. Triggered by keywords setup, install, preset, get started, first run, fresh install, initialize, wizard, onboard, configure workspace, initial setup, persona configuration.

Interview-driven enrichment of a career hub. Given a category (foundations | roles | projects | capabilities) or a menu if no argument, reads existing stubs, drafts from known content, and asks the user only gap questions. Edits files in place, bumps last_updated, flips status from draft to active when substantively complete. Offers .private.md confidential siblings when candid content surfaces. Logs deferrals to g.backlog/ as one file per item.

Scaffold an empty, compliant career hub in the current working directory. Produces the mandated 7-category structure (a.foundations through g.backlog), PRINCIPLES.md, README.md index, and stub files with frontmatter and TODO markers. Use when starting a new career-facts repository. Refuses if cwd already contains a hub or is non-empty with unrelated content.

Comprehensive CV/resume optimization for the dual-AI hiring landscape. Reformat and rewrite CVs to pass both ATS (Applicant Tracking System) screening and employer fraud detection while maintaining authentic, verifiable claims. Use when creating a new CV, optimizing an existing resume, preparing for job applications, addressing employment gaps, or struggling with resume rejections. Produces both a reformatted CV and a detailed strategy document explaining all changes and reasoning.

Render a draft target artefact from career-hub content. Built-in targets — cv, linkedin, github-profile. Extensible via target spec files in targets/. Applies visibility filter (public-only by default, never confidential). Drafts into f.pipeline/<target>-draft.md inside the hub — user copy-pastes out to the destination surface. Prints a cross-surface consistency posting checklist.

Find and analyze Claude Code skills in a directory. Reports skill names, descriptions, and compatibility status for other surfaces. Trigger phrases: "find skills", "list skills", "what skills are in", "discover skills", "analyze plugin".

Export a Claude Code skill as a ZIP file for upload to claude.ai web interface. Analyzes the skill, bundles dependencies, transforms frontmatter, and creates a self-contained ZIP. Trigger phrases: "export for claude.ai", "create ZIP", "export skill", "download skill".

Gateway skill for transforming and transporting Claude Code skills to other Claude surfaces. Routes to appropriate skill based on intent: export-zip for claude.ai, upload-api for Messages API. Trigger phrases: "export skill", "upload skill", "sync skill", "publish skill", "arcana".

Upload a Claude Code skill to the Anthropic Skills API for workspace-wide availability. Analyzes the skill, bundles dependencies, transforms frontmatter, validates, and uploads. Tracks uploads for future updates. Trigger phrases: "upload to API", "publish skill", "sync to API", "upload skill".

This skill should be used when the user asks to "analyze this progression", "analyze these chords", "what key is this in", "what function does this chord have", "analyze my song", "what's the Roman numeral for", "explain this chord sequence", "break down this progression", "harmonic analysis of", or provides a chord sequence like "C Am F G" for analysis. Returns songwriter-friendly analysis with chord roles, voice leading, and Nine Harmonic Cells classification. Theory terms provided optionally in [Theory] tags.

This skill should be used when the user asks to "find chromatic bass patterns", "show me bridge techniques", "deceptive cadence examples", "McCartney patterns", "how did Beatles do", "modal interchange examples", "search corpus for", "find patterns like", "show me examples of", "what patterns exist for", "browse the pattern database", or mentions specific techniques (chromatic bass, borrowed chords, modal interchange, deceptive moves). Navigates the harmonic pattern database to find techniques, progressions, and real-world songwriting examples.

This skill should be used when the user asks "where should I go next", "suggest a bridge", "what chord comes after", "how do I get to the chorus", "I'm stuck on this progression", "give me options for", "what would work here", "suggest chords for bridge/chorus/verse", "what should come next", "I need a pre-chorus", "help me write a bridge", or expresses being stuck or needing harmonic direction. Co-writing assistant that suggests next moves based on context using guitarist-friendly language. Theory provided optionally in [Theory] tags.

Create a release branch, bump version, update changelog, and open a PR to main. Automates the documented release workflow in RELEASING.md. Use this skill when: preparing a production release, creating a release branch, cutting a release, shipping a new version. Trigger phrases: "prepare release", "cut release", "release branch", "ship version", "create release", "start release", "new release", "release to main", "production release", "prepare for release".

Analyze PR changes and prepare semantic version bumps with changelog entries. Use this skill when: preparing a branch for PR creation, bumping version before merge, finalizing a PR for release, checking if version was bumped, verifying changelog entries. Trigger phrases: "bump version", "version bump", "prepare release", "prepare PR", "finalize PR", "check version", "verify bump", "semver", "changelog", "what version should this be", "ready to merge", "pre-merge check", "update version", "draft changelog", "release prep", "version check", "bump and PR".

Build or refresh a documentation-ready profile of a large software package before writing docs. Use when documentation needs to cover many modules, subpackages, public APIs, backend architecture, maintainers, users, contributors, or marketing audiences; when raw code is too large or uneven for direct LLM documentation; or when incremental documentation updates must track the last profiled git commit hash.

Use when you need to assess or uplift a plugin for multi-platform portability. Gauges intent upfront (diagnostic or uplift, which platforms, uplift target), then runs shared detection, inventory, and condition-driven scoring across all platforms. For uplift, generates missing artifacts with fixes: annotations linked to rubric conditions. Supports incremental uplift for viable+ platforms. Platforms: Claude Code, Cursor, Gemini CLI, Codex, Antigravity, OpenClaw.