Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Goodies

ASecurity

Ingest, contextualize, and index curated resources (websites, tools, design references, research papers, UI kits) into a public GitHub Pages vault while automatically linking them to the local Knowledge Graph via /checkit and P6 bookkeeping. Dynamically resolves and expands category ontologies, generates client-side search indices, and publishes the updated vault database to a public repository. USE WHEN: /goodies, goodies, goodies add, add to goodies, bookmark this site, save to goodies, boo...

4 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentspythongonodegitapidatabase

Works with

cliapi

Security Analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned 9/27/2026

$npx -y skills add broomva/skills --skill goodies --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Goodies?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Goodies
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/broomva-goodies/badge)](https://www.skillsdirectory.com/skills/broomva-goodies)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: goodies
category: knowledge
description: >
  Ingest, contextualize, and index curated resources (websites, tools, design references,
  research papers, UI kits) into a public GitHub Pages vault while automatically linking
  them to the local Knowledge Graph via /checkit and P6 bookkeeping. Dynamically resolves
  and expands category ontologies, generates client-side search indices, and publishes
  the updated vault database to a public repository. USE WHEN: /goodies, goodies,
  goodies add, add to goodies, bookmark this site, save to goodies, bookmark good resource,
  curate website. NOT FOR: internal-only notes without public vault indexing; general web
  searches without curating a resource.
---

# goodies — Curate, KG-Index, and Publish to Public Goodies Vault

`/goodies` takes a URL or resource pointer (website, tool, design reference, research paper), metabolizes it into the local Knowledge Graph using `/checkit` and P6 bookkeeping, dynamically classifies it within an evolving category taxonomy, and publishes the rich record to a public GitHub Pages repository (`goodies`).

It is a **bstack composition skill**: it fires `/checkit` research, P6 bookkeeping, dynamic taxonomy resolution, and git sync scripts in sequence.

## The One Rule

> **Curate with depth, index with provenance, publish with dynamic taxonomy.**
>
> A resource saved to goodies must never be a bare link. It must carry deep context, primary-source verification, Knowledge Graph linkage (`kgEntity`), and an evolving category taxonomy so the public vault remains searchable, beautiful, and valuable.

## Pipeline (what `/goodies add <URL>` does)

1. **Ingest & Verify (`/checkit`)**
   - Run the `/checkit` pipeline on the target URL/artifact.
   - Fetch primary source verbatim, extract title, tagline, deep summary, key highlights, stack tags, and favicon/OG image.

2. **Index into Knowledge Graph (P6 Bookkeeping)**
   - Create or update the corresponding entity page in `research/entities/tool/` or `research/entities/concept/`.
   - Score the entity using Nous gate criteria (novelty, specificity, relevance).
   - Capture `kgEntity` reference path for vault linking.

3. **Dynamic Taxonomy Resolution**
   - Execute `scripts/vault_schema.py` to inspect `data/taxonomy.json`.
   - Determine if the resource fits an existing category OR dynamically expands the ontology with a new category node.
   - Assign primary category, subcategory, and tag taxonomy.

4. **Format & Validate Vault Record**
   - Construct Vault Item JSON conforming to schema specification.
   - Execute schema validation tests (`scripts/vault_schema.py`).

5. **Sync & Publish (`scripts/vault_sync.py`)**
   - Write individual record to `data/items/<slug>.json`.
   - Merge into consolidated `data/vault.json` database.
   - Regenerate client-side search index (`data/search-index.json`).
   - Scaffold missing OSS standards (`LICENSE`, `CONTRIBUTING.md`, `.gitignore`, enhanced `README.md` with badges & live links).
   - Enforce CSS `[hidden] { display: none !important; }` rule to guarantee modal backdrops stay hidden on load.
   - Sync GitHub repository metadata (`description`, `homepage`, `topics`) via `gh repo edit`.
   - Commit & push to public repository (e.g. `goodies`), triggering GitHub Pages auto-deploy.

## Deterministic Scripts & Core Tools

- `scripts/vault_schema.py`: Validates item JSON schemas and manages dynamic category taxonomy resolution.
- `scripts/vault_sync.py`: Merges vault items, updates aggregate DB, scaffolds OSS files, syncs GH repo metadata, generates Fuse search indices, and handles Git sync.
- `scripts/vault_ingest.py`: Orchestrates URL ingestion, `/checkit` extraction, metadata scraping, and item construction.

## Anti-Rationalization

| Excuse | Reality |
|---|---|
| "A bare link and title is enough." | Bare links degrade quality. /goodies requires summary, highlights, and KG provenance. |
| "Categories should be hardcoded." | Categories are dynamic ontologies that evolve as new domains are discovered. |
| "I'll sync the public repo later." | The skill commits & pushes automatically to keep GitHub Pages live and fresh. |

## Validation

- Executing `python3 scripts/vault_schema.py` validates schema compliance.
- Executing `pytest tests/` runs unit tests for schema and sync modules.
- Executing `bstack skills audit` verifies skill integrity.

## References

- [`references/vault-architecture.md`](references/vault-architecture.md) — Architectural specification for vault data model and GitHub Pages integration.

Attribution

broomvabroomva
View sourceSee grades on GitHubMore from broomva →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →