goal-research SKILL.md skillA

goal-research from jongwony/cc-plugin is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jongwony/cc-plugin/goal-research@git:20261006.c816326

Pins git:20261006.c816326 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jongwony/cc-plugin
Path
goal-research/skills/goal-research/SKILL.md
Versions recorded
2
Latest version
git:20261006.c816326, committed Oct 6, 2026
First version recorded
Oct 4, 2026
Size
14,283 bytes
Repository stars
11
License
none declared

Delegate academic-literature research to a background Claude or Codex run using Aitesis and Tavily; check its citations against its Tavily record until the goal holds. User-invoked via /goal-research.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Goal Research

Invoke directly with `/goal-research [runner] <research question>` when the user wants a research question — typically one about the scholarly literature — investigated by a background run that drives Aitesis with Tavily search and extract, and wants the run's citations checked against what its own Tavily calls returned.

**Why this composition**: `/inquire` carries the epistemic contract — its reading of each uncertainty, its record of what collection reached, and what stays open for the person to settle. goal-research refines that contract for academic research in a background run; it adds no second reading beside it. A research run can answer fluently and cite papers it never opened, and nothing in its narrative distinguishes that from a searched answer. So the run's own tool record, never its account of itself, says which Tavily calls succeeded and what they returned; whether a cited source is among them is this session's reading, marked as such.

## Dependency

- **Aitesis** (`/inquire`; `$inquire` on Codex) — the run drives it, so the
  epistemic-protocols `aitesis` plugin must be installed where the run executes.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jongwony/cc-plugin/goal-research@sha256:059b6e81db9f3dac

The line at the top of this page pins the label git:20261006.c816326, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_gr7dfb4exddilcqj.svg)](https://markdownregistry.com/a/art_gr7dfb4exddilcqj)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Oct 4, 2026 and Oct 6, 2026, about one every day.

versioncommittedcommitsizeaudit
git:20261006.c816326 latest2026-10-06 c816326 14,283 BA view · diff
git:20261004.d56db1d2026-10-04 d56db1d 14,255 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14283 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jongwony/cc-plugin · 11 stars · license none declared · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gr7dfb4exddilcqj
GET https://markdownregistry.com/api/v1/resolve?ref=jongwony/cc-plugin/goal-research
GET https://markdownregistry.com/api/v1/blob/059b6e81db9f3dac895c1f9ade4a1ee86affcfef153b1bd9f1398d769e925d0c

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jongwony/cc-plugin

cdp-bootstrap SKILL.md skill
jongwony/cc-plugin · .claude/skills/cdp-bootstrap/SKILL.md · This skill should be used when the user explicitly asks to "bootstrap CDP on Linux", "start Chromium on a headless…
git:20261004.9dadfdb · audit B · 11 stars
CLAUDE.md CLAUDE.md file
jongwony/cc-plugin · CLAUDE.md
git:20261004.9dadfdb · audit B · 11 stars
agent-device-preflight SKILL.md skill
jongwony/cc-plugin · agent-device-preflight/skills/agent-device-preflight/SKILL.md · This skill should be used when the user asks to "connect my phone to agent-device", "attach a device to agent-device"…
git:20260803.01ab2dc · audit A · 11 stars
caffeinate SKILL.md skill
jongwony/cc-plugin · caffeinate/skills/caffeinate/SKILL.md · This skill should be used when the user asks to "prevent sleep", "caffeinate", "keep awake", "stop sleeping"…
git:20260401.43c71ef · audit A · 11 stars
linkedin-polish SKILL.md skill
jongwony/cc-plugin · choi-voice/skills/linkedin-polish/SKILL.md · 최종원(Jongwon Choi)의 LinkedIn 글 톤으로 초안을 윤문할 때 사용. LinkedIn 글, 링크드인 포스트, 톤 다듬기, 윤문, 내 말투로 고쳐줘 요청에 적용.
git:20260926.9a41fea · audit A · 11 stars
claude-code-internals SKILL.md skill
jongwony/cc-plugin · claude-code-internals/skills/claude-code-internals/SKILL.md · This skill should be used when the user asks to "explore claude code source", "find internal features", "investigate…
git:20260705.d349ada · audit A · 11 stars
codex-plus-session SKILL.md skill
jongwony/cc-plugin · codex-plus/skills/codex-session/SKILL.md · This skill should be used when the user asks to "find codex session", "codex session context", "lookup codex session"…
git:20260719.744fc68 · audit A · 11 stars
codex-plus SKILL.md skill
jongwony/cc-plugin · codex-plus/skills/codex/SKILL.md · This skill should be used when the user asks to "run codex", "use codex CLI", "delegate to codex", "codex resume", or…
git:20261009.dbc6013 · audit A · 11 stars
comment-review SKILL.md skill
jongwony/cc-plugin · comment-review/skills/comment-review/SKILL.md · Review a markdown or HTML artifact in a live browser preview: right-click any element to anchor a comment by CSS…
git:20260821.4467ba3 · audit C · 11 stars
explain SKILL.md skill
jongwony/cc-plugin · explain/skills/explain/SKILL.md · Explain a concept, topic, codebase, paper, or system to the reader in front of you
git:20260917.73fbd92 · audit A · 11 stars
gemini-cli SKILL.md skill
jongwony/cc-plugin · google/skills/gemini-cli/SKILL.md · This skill should be used when the user asks to "run gemini", "ask gemini", "delegate to gemini", "use Gemini CLI"…
git:20261014.adf16a7 · audit A · 11 stars
veo SKILL.md skill
jongwony/cc-plugin · google/skills/veo/SKILL.md · This skill should be used when the user specifically asks for Veo, or names a Veo-specific control: "generate video…
git:20260811.80c136f · audit A · 11 stars

Every file in jongwony/cc-plugin

Browse by kind, by grade A, or by owner.