business-context-os

Single-task dispatcher for CLEAR Context OS scheduled maintenance. Runs from the daily scheduled task, reads schedule-config.json, determines which jobs are due today, runs them in sequence, appends to the diary, writes a consolidated morning digest, and surfaces any frequency-tuning suggestions. WHEN TO USE: - Invoked automatically each morning by the `bcos-{PROJECT}` scheduled task - User says "run today's maintenance now" (manual dispatch) - User says "run the [job-name] job" (runs one job on demand, skips others)

Strategic reflection skill. Step back from daily work to think about the bigger picture of your context architecture, identify gaps, and envision improvements.

Wiki zone manager for BCOS — the universal long-form and cross-cutting content destination per plugin-storage-contract.md Rule 2. Stores runbooks, SOPs, decision logs, how-tos, glossaries, post-mortems, FAQs, meeting notes, and plugin cross-cutting context (charters, transcripts, research, customer-call notes). Two ingest paths: Path B (local files, pasted text, inbox promotion — runbooks/scripts/SOPs/notes) and Path A (external URLs / GitHub / YouTube). Schema-validated frontmatter, banner citations, builds-on graph for references, two-tier refresh, supersedes chains. Schema-driven, CLEAR-governed, derived-artifact. Invoke with /wiki.

The single entry point for getting anything new into your context architecture. Takes any input (documents, URLs, YouTube, meeting notes, pasted content) and triages it: dump to _inbox, park in _planned, or integrate into active docs. WHEN TO USE: - "Here's a document — integrate it into my context" - "Save this for later" / "Dump these meeting notes" - "I have an idea — park it somewhere" - "Read this article — not sure if it's relevant" - "Our competitor just announced X — update positioning" - Any time new information needs to enter the context architecture - Raw material should become a wiki explainer rather than a canonical data point

First-run onboarding skill. Gets a new user from zero to a working context system. Claude asks one direct question upfront to pick the right scaffolding, then works from what the user shares — no long assessment ceremony beyond that. Creates a checklist that tracks setup progress across sessions and self-removes when done. WHEN TO USE: - "I want to set up my business context" - "Here's my website / pitch deck / LinkedIn" - "Scan my repo and show me what context exists" - "What do I do next?" (after install) - "Help me get started" - First time adopting CLEAR Context OS in any project

Cross-zone retrieval and task-driven bundle resolution for BCOS. /context search ranks docs across every zone in one shared schema; /context bundle (P5) returns a curated, freshness-flagged, source-of-truth-aware context bundle for a declared task. Mechanical-first; LLM is opt-in via --semantic / --resolve-conflicts / --verify-coverage flags only. Invoke with /context.

Creates implementation plans for ALL work scenarios. MANDATORY entry point for the PLAN phase. 8-step workflow: Intent -> Discovery -> Scenario -> Context -> Template -> Approach -> Session -> Approval 2 scenarios: AGENTING (ecosystem work), DOCUMENTATION (context creation & refinement)

Audits context architecture for CLEAR compliance, boundary enforcement, and consistency. WHEN TO USE: - User says "audit context for CLEAR" - User asks "check for duplication across data points" - User requests "find boundary violations in [area]" - Planning restructuring work - Before adding new data points (cleanup existing first) - Context quality improvement initiatives WHEN NOT TO USE: - Planning new features (use clear-planner instead) - Markdown syntax checking (use doc-lint instead) - Making changes directly (audit only, findings guide manual fixes)

Extracts structured context from conversation exports (Slack, meeting transcripts, chat logs) into _inbox for processing.

Natural-language editor for .claude/quality/schedule-config.json. Users talk about maintenance scheduling in everyday language ("run audit twice a week", "turn off deep daydream", "switch dispatcher to 08:30") — this skill parses intent, validates against the schema, shows a concrete diff, asks for confirmation, and writes the change. WHEN TO USE: - User wants to change how often a job runs - User wants to enable / disable a job - User wants to add or remove an auto-fix ID from the whitelist - User wants to change the dispatcher's daily time - User wants to reset config to defaults - User asks "what's my current maintenance schedule?" (read-only query mode) DO NOT USE: - For actually running jobs (that's the `schedule-dispatcher` skill) - For initial config creation when no `schedule-config.json` exists yet — `context-onboarding` Step 6 handles seeding from the template + creating the OS-level scheduled task. After Step 6 completes, this skill IS the right place to adjust cadences (e.g. "now turn audit-inbo

Manage the BCOS self-learning ladder: list learned rules, forget a rule, regenerate learned-rules.json from resolutions.jsonl. Mechanical-only — reads/writes derived artifacts; the actual learning happens via record_resolution.py at click time. Invoke with /learning.

Agent ecosystem expert for creating, maintaining, and auditing agents and skills. Prevents ecosystem drift and overlap.

Periodic maintenance of institutional knowledge. Analyzes lessons for staleness, overlaps, and gaps. Keeps lessons.json healthy.

Validates documentation quality: markdown syntax, cross-references, JSON structure. WHEN TO USE: - Validating markdown files for quality issues - Checking cross-references between documents - Validating JSON structure in ecosystem files - As part of FIXED END validation in any scenario WHEN NOT TO USE: - Content quality auditing (use context-audit for that) - Making content changes (findings guide manual fixes)

Bootstrap skill - enforces proactive skill discovery and invocation. Automatically check for applicable skills before any action. Always active.

Shared TodoWrite patterns for consistent progress tracking across all BCOS skills. This is a PATTERN LIBRARY, not an invocable skill. Skills copy these patterns inline. WHY INLINE, NOT INVOKED: If todo-utilities were invoked as a Task(), its TodoWrite calls would execute in an isolated context — invisible to the user. Patterns must run IN the parent skill's main context where TodoWrite is visible. WHEN TO REFERENCE: - Building a new skill that tracks multi-step progress - Adding agent delegation to an existing skill - Implementing approval gates or error recovery