vc-context-discovery
vc-context-discovery is the canonical context-loading entry point for every agent session. It discovers and surfaces all nested files under process folders, extracts frontmatter metadata, and routes context by domain using keyword matching. Use the auto-discovery script or keyword-first routing to load exactly the docs your task needs.
vc-context-discovery loads all relevant context files and feature artifacts at the start of every agent session.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-06-21
vc-context-discovery loads all relevant context files and feature artifacts at the start of every agent session. vc-context-discovery is the canonical context-loading entry point for every agent session. It discovers and surfaces all nested files under process folders, extracts frontmatter metadata, and routes context by domain using keyword matching. Use the auto-discovery script or keyword-first routing to load exactly the docs your task needs.
Use it when
- vc-context-discovery scans feature folders recursively to surface nested files with full paths and frontmatter metadata.
- vc-context-discovery includes the discover-context.mjs script as the canonical auto-discovery entry point.
Verify before relying
Read SKILL.md below before installing (6 files). Open directory: indexed for reading, not audited.
Install
withkynam/vibecode-pro-max-kit/vc-context-discovery · repository language: JavaScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I load all relevant context at the start of my session?
vc-context-discovery is your entry point for bootstrapping agent sessions with context. It discovers all nested files across feature folders, extracts YAML frontmatter metadata, and auto-routes docs by domain and task vocabulary. Run the discovery script at session start to populate your full context baseline before executing tasks.
How can I discover all relevant files for this feature?
vc-context-discovery scans feature folders recursively to surface nested files with full paths and frontmatter metadata. Use keyword matching against frontmatter schemas to filter by domain and task vocabulary. The tool maintains drift-proof routing tables so your context stays aligned with feature structure as it evolves.
What is the discover-context.mjs script?
vc-context-discovery includes the discover-context.mjs script as the canonical auto-discovery entry point. It loads all context, plan, and report files from your repo, extracts their frontmatter, and generates routing tables keyed by domain. Run it once per session to ensure every agent has the complete context artifact set needed for its task.
How does vc-context-discovery route context by domain?
vc-context-discovery uses keyword matching against frontmatter schemas to route context files by domain and task vocabulary. It generates and maintains drift-proof routing tables that map keywords to file paths, letting you load exactly the docs your current task needs without manual filtering or path hunting.
Can vc-context-discovery find nested files in feature folders?
Yes. vc-context-discovery discovers all nested files across feature folders with full paths and frontmatter metadata. It extracts YAML frontmatter from context, plan, and report files, then surfaces that metadata for routing and filtering. This ensures no relevant nested file is missed during session bootstrap.
What context do I need for this task with vc-context-discovery?
vc-context-discovery answers that by scanning your repo's frontmatter and matching task vocabulary against domain keywords. Load the discovery script at session start, then query the routing tables it generates. The tool surfaces only the context files relevant to your task's domain, eliminating noise and keeping your session lean.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
vc-context-discovery
> Output style: Follow process/development-protocols/communication-standards.md — answer-first, plain language, no unexplained jargon, TL;DR on long responses.
Discover and load all relevant context for the current task. This skill lists feature group nested files with full paths and loads process/context/ files by domain routing table. It is the canonical context-loading entrypoint for every agent session.
When To Invoke
At the start of every agent session (research, innovate, plan, validate, execute, update-process, fast-mode). Also at the start of any skill that needs repo context before operating.
Frontmatter Schemas
Document the canonical schemas for three file types
(truncated - see the full file via the links below)
File tree — 6 files
.claude/skills/vc-context-discovery/SKILL.md
.claude/skills/vc-context-discovery/scripts/discover-context.mjs
.claude/skills/vc-context-discovery/scripts/discover-skills.mjs
.claude/skills/vc-context-discovery/scripts/fixtures/validate-context-discovery-output/fail.md
.claude/skills/vc-context-discovery/scripts/fixtures/validate-context-discovery-output/pass.md
.claude/skills/vc-context-discovery/scripts/validate-context-discovery-output.mjs
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Load all relevant context files and feature artifacts at the start of an agent session”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
This skill scaffolds multi-phase programs by generating an umbrella orchestration plan, Program Goal Charter, per-phase plan stubs, and a session-goal block. It enforces a 7-step inner loop (Research → Innovate → Plan-Supplement → PVL → Execute → EVL → Update-Process) with validation gates between phases, ensuring each phase is ready before the next begins. Use it when work naturally breaks into 3+ dependent phases across multiple packages or services.
vc-setup guides you through configuring an agent development harness tailored to your project. It detects your tech stack, asks clarifying questions to understand your codebase, then scaffolds the necessary directory structure and context files—always requesting approval before making changes. Works equally well on new projects and those with existing configurations.
vc-audit-plans scans your active plan inventory to flag stale, completed, or obsolete artifacts and recommend archival or cleanup actions. It validates plan status against your codebase, detects misplaced task artifacts, and surfaces a summary table with classifications and next steps. Use it for periodic maintenance, post-burst reconciliation, or when plan cleanup has drifted.
vc-audit-context validates your project's context layer, routing tables, and shared-skill discovery across agents. Run built-in validators to catch missing context files, broken skill references, and protocol misalignment, then regenerate your machine-readable skill catalog.
vc-generate-plan transforms feature ideas and product requirements into structured implementation plan artifacts saved to your repo. It handles both straightforward single-phase work and large multi-phase programs, organizing plans with required sections for touchpoints, contracts, blast radius, and verification gates. The skill enforces answer-first communication and ensures execution handoff clarity through explicit resume notes.
vc-generate-context creates and updates process/context/all-context.md, your project's durable knowledge layer for sharing context across agents. It supports full scans for new projects, delta updates for existing repos, and grouped context generation for organized documentation. Validation scripts ensure routing integrity before context is marked refreshed.
More skills vc-scout (MIT) · vc-generate-spec (MIT) · vc-autopilot (MIT)