Wb Xhs Topic Bank
wenziai/wenzi-xhs-agent-skills
A skill your agent uses when the user has positioning and wants a reusable Xiaohongshu topic/title bank instead of asking AI to freely brainstorm, especially to map topics to user needs such as…
Pre-definition collaborative discovery. An agent skill from jumbocontext/cli.
$ npx skills add jumbocontext/cli --skill jumbo-design-goal -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jumbocontext/cli jumbo-design-goal --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jumbocontext/cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/assets/skills/jumbo-design-goal .claude/skills/jumbo-design-goal && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "jumbo-design-goal" agent skill from https://github.com/jumbocontext/cli/tree/main/assets/skills/jumbo-design-goal into .claude/skills/jumbo-design-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jumbo-design-goal", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jumbocontext/cli/tree/main/assets/skills/jumbo-design-goalType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jumbocontext/cli --skill jumbo-design-goal -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jumbocontext/cli jumbo-design-goal --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jumbocontext/cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/assets/skills/jumbo-design-goal .agents/skills/jumbo-design-goal && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "jumbo-design-goal" agent skill from https://github.com/jumbocontext/cli/tree/main/assets/skills/jumbo-design-goal into .agents/skills/jumbo-design-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jumbo-design-goal", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jumbocontext/cli --skill jumbo-design-goal -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jumbocontext/cli jumbo-design-goal --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jumbocontext/cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/assets/skills/jumbo-design-goal .cursor/skills/jumbo-design-goal && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "jumbo-design-goal" agent skill from https://github.com/jumbocontext/cli/tree/main/assets/skills/jumbo-design-goal into .cursor/skills/jumbo-design-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jumbo-design-goal", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jumbocontext/cli.git --path assets/skills/jumbo-design-goal--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jumbocontext/cli --skill jumbo-design-goal -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jumbocontext/cli jumbo-design-goal --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jumbocontext/cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/assets/skills/jumbo-design-goal .gemini/skills/jumbo-design-goal && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "jumbo-design-goal" agent skill from https://github.com/jumbocontext/cli/tree/main/assets/skills/jumbo-design-goal into .gemini/skills/jumbo-design-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jumbo-design-goal", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jumbocontext/cli jumbo-design-goalInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jumbocontext/cli --skill jumbo-design-goal -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jumbocontext/cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/assets/skills/jumbo-design-goal .github/skills/jumbo-design-goal && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "jumbo-design-goal" agent skill from https://github.com/jumbocontext/cli/tree/main/assets/skills/jumbo-design-goal into .github/skills/jumbo-design-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jumbo-design-goal", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jumbocontext/cli --skill jumbo-design-goal -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jumbocontext/cli jumbo-design-goal --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jumbocontext/cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/assets/skills/jumbo-design-goal .opencode/skills/jumbo-design-goal && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "jumbo-design-goal" agent skill from https://github.com/jumbocontext/cli/tree/main/assets/skills/jumbo-design-goal into .opencode/skills/jumbo-design-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jumbo-design-goal", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
jumbo-design-goalPre-definition collaborative discovery. An agent skill from jumbocontext/cli.
Jumbo Design Goal is an agent skill from jumbocontext/cli. Pre-definition collaborative discovery. Aligns a proposed goal with project audience, pains, and value propositions; surfaces design gaps and open questions before handing off to define-jumbo-goals.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Marketing & SEO, covering Positioning and messaging. The repository describes itself as: Memory and Context Orchestration for Coding Agents. The licence is AGPL-3.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit a02a339. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Jumbo Design Goal loads about 1.7k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 907 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from jumbocontext/cli at commit a02a339, republished under its AGPL-3.0 licence (© jumbocontext). 907 words, ~1,737 tokens.
.claude/skills/jumbo-design-goal/SKILL.md (or your agent's skills folder).Prompt: Guide collaborative goal design by aligning a proposed piece of work with the project's audience, audience pains, and value propositions — surfacing design gaps and open questions before handing off to the define-jumbo-goals skill for formal decomposition and registration.
Definition without alignment produces goals that solve the wrong problem or miss the audience's actual pain. The define-jumbo-goals skill assumes the what and why are already clear — it focuses on decomposition, criteria, and scope. If those inputs are vague or misaligned, every downstream artifact (criteria, relations, implementation) inherits the drift. Design is where alignment happens.
Before discussing the goal, load the project's north-star context:
jumbo project show --northstarAlso extract the projectContext from your session start output. From these two sources, note:
These three lists are the alignment targets for every goal.
Ask the user what they want to achieve and why. Extract the raw intent before shaping it:
Listen for the what and the why. Do not jump to solution design. The goal at this stage is understanding, not specification.
Map the proposed goal against each alignment target:
| Alignment Target | Question |
|---|---|
| Each audience | Does this goal serve this audience? If so, how? |
| Each audience pain | Does this goal address this pain? Directly or indirectly? |
| Each value proposition | Does this goal advance this value proposition? |
Document which targets the goal serves. If the goal does not align with any audience pain or value proposition, surface that explicitly:
"This goal doesn't appear to address any of the project's stated audience pains or value propositions. That may be fine — it could be infrastructure, tech debt, or a new direction. But let's confirm that's intentional before proceeding."
Misalignment is not a blocker — it is a signal that needs acknowledgment.
Surface missing information that would prevent clean definition. For each category, ask targeted questions:
| Gap Category | What to Surface |
|---|---|
| Unclear scope | What is included? What is explicitly excluded? Where are the boundaries? |
| Unstated assumptions | What is being taken for granted about the current system, user behavior, or environment? |
| Unknown constraints | Are there performance, compatibility, security, or process constraints? |
| Missing success criteria | How will we know this is done? What does "correct" look like? |
| Unresolved dependencies | Does this require other work to be completed first? Does it depend on external systems or teams? |
Ask one category at a time. Iterate until each gap is resolved or explicitly deferred. Do not overwhelm the user with all questions at once.
Before handing off, verify the following checklist:
If any item is unresolved, return to the relevant protocol step. Do not proceed with open gaps.
Once the design is confirmed, invoke the define-jumbo-goals skill:
/define-jumbo-goalsCarry forward the gathered context: the objective, the audience alignment, the resolved design gaps, and any constraints or dependencies discovered. The define-jumbo-goals skill will handle decomposition, criteria authoring, scope definition, and goal registration.
If the user prefers to defer definition, output a structured summary they can carry forward:
## Goal Design Summary
- **Objective:** [one-sentence what + why]
- **Audiences served:** [list]
- **Pains addressed:** [list]
- **Value propositions advanced:** [list]
- **Constraints:** [list]
- **Dependencies:** [list]
- **Deferred questions:** [list, if any]| Anti-Pattern | Problem | Fix |
|---|---|---|
| Skipping straight to definition without design | Goals are defined without alignment, producing work that misses the audience's actual pain | Always run the design protocol first — load context, elicit intent, align, identify gaps |
| Assuming alignment without checking | The goal feels related to the project but no explicit mapping was done | Walk through each audience, pain, and value proposition explicitly |
| Asking too many questions at once | The user is overwhelmed and gives shallow answers | Iterate one gap category at a time, confirming resolution before moving on |
| Force-fitting alignment | The agent claims the goal serves a pain it does not actually address | State misalignment honestly — the user may have context that resolves it, or may accept the gap |
| Treating design as a gate instead of a collaboration | The agent blocks progress because alignment is imperfect | Misalignment is a signal, not a blocker — surface it, discuss it, let the user decide |
© jumbocontext, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in assets/skills/jumbo-design-goal of jumbocontext/cli.
Open the folder on GitHubat commit a02a339
Jumbo Design Goal next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Jumbo Design Goal this skilljumbocontext/cli | 276 | — | ~1.7k | Automated safety check: Pass | AGPL-3.0 | |
| Wb Xhs Topic Bankwenziai/wenzi-xhs-agent-skills | 168 | — | ~821 | Automated safety check: Pass | None | |
| Sk Exportmohamedameen-io/StartupKit | 163 | — | ~8k | Automated safety check: Pass | MIT | |
| Shortform Strategyericrisco/rsc-harness | 180 | — | ~3.4k | Automated safety check: Pass | MIT | |
| Marketing OsYuzzyuk/marketing-os | 540 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Revenue Centric Designheliocosta-dev/revenue-centric-design | 740 | — | ~1.6k | Automated safety check: Pass | Custom licence |
wenziai/wenzi-xhs-agent-skills
A skill your agent uses when the user has positioning and wants a reusable Xiaohongshu topic/title bank instead of asking AI to freely brainstorm, especially to map topics to user needs such as…
mohamedameen-io/StartupKit
Phase 11: Export your brainstorming session as a clean, shareable one-pager summarizing all phases (Diverge, Niche, Competitors, Positioning, Offer, Validate, Money, Leads, Skills, Pitch).
ericrisco/rsc-harness
A skill your agent uses when the unit of work is a TikTok/Reels account, not one clip: positioning, sustainable cadence and format mix, ride-or-skip on a trend or sound, recurring series, diagnosing…
Yuzzyuk/marketing-os
A complete marketing department in one skill. An agent skill from Yuzzyuk/marketing-os.
heliocosta-dev/revenue-centric-design
Playbook for designing SaaS and startup products that convert, retain, and monetize — landing pages & CRO, checkout & forms, onboarding/activation, churn reduction, pricing psychology, dashboards…
ferdinandobons/startup-skill
Market positioning strategy using the April Dunford framework, enriched with JTBD discovery, Moore positioning statement, and Neumeier's Onliness Test.
jumbocontext/cli
A skill your agent uses when a Jumbo goal has been approved by QA review and needs architectural reconciliation before closing.
jumbocontext/cli
A skill your agent uses when a project has Architecture data that needs migrating to fine-grained entities (Decisions, Invariants, Components, Dependencies).
jumbocontext/cli
Add Jumbo goals liberally to decompose objectives into finite units of work with bounded context.
jumbocontext/cli
Use liberally when the user expresses a preference about how work should be done — coding style, process, testing approach, communication style.
jumbocontext/cli
A skill your agent uses when Jumbo goals need refinement before implementation.
jumbocontext/cli
A skill your agent uses when a Jumbo goal fails QA review and needs to be returned for rework.
Categories
Pre-definition collaborative discovery. An agent skill from jumbocontext/cli. Jumbo Design Goal is an agent skill from jumbocontext/cli. Pre-definition collaborative discovery.
Jumbo Design Goal fits situations like: tasks that involve Positioning and messaging.
Run `npx skills add jumbocontext/cli --skill jumbo-design-goal -a claude-code`. Or copy the skill folder (assets/skills/jumbo-design-goal in jumbocontext/cli) into .claude/skills/jumbo-design-goal in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jumbocontext/cli --skill jumbo-design-goal -a codex`. Or copy the skill folder (assets/skills/jumbo-design-goal in jumbocontext/cli) into .agents/skills/jumbo-design-goal in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jumbocontext/cli --skill jumbo-design-goal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jumbo-design-goal, .gemini/skills/jumbo-design-goal, .github/skills/jumbo-design-goal and .opencode/skills/jumbo-design-goal in your project.
SKILL.md names no scripts, command-line tools or credentials: Jumbo Design Goal is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Jumbo Design Goal is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Jumbo Design Goal: Wb Xhs Topic Bank (wenziai/wenzi-xhs-agent-skills, 168 stars), Sk Export (mohamedameen-io/StartupKit, 163 stars), Shortform Strategy (ericrisco/rsc-harness, 180 stars) and Marketing Os (Yuzzyuk/marketing-os, 540 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
jumbocontext (a GitHub organization) maintains it in jumbocontext/cli, which has 276 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 23, 2026.
Source: jumbocontext/cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.