Wang-Cankun/cankun-skills

Index of my agent skills

2Stars on the repository
14Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

Wang-Cankun/cankun-skills

Skill Codex

Create, plan, direct, critique, generate, or edit slow-travel and lifestyle photography using the visual language associated with Italian photographer Roberta Mazzone (@lagiuditta): architectural composition, natural light, warm restraint, lived-in detail, and quiet cinematic narrative. Use when the user names Roberta…

not rated 2 changed 19d ago A 108 tokens original MIT

art-poster-mondo

02

Wang-Cankun/cankun-skills

Skill Codex

Research, art-direct, create, and critique original alternate movie, television, game, and pop-culture posters using the curatorial and screen-print production principles associated with Mondo: deep source knowledge, a fresh conceptual hook, artist-to-property fit, integrated typography, collectible-object craft…

not rated 2 changed 19d ago A 123 tokens original MIT

cankun-blog-preview

03

Wang-Cankun/cankun-skills

Skill Codex

Generate and integrate exactly one article preview image for cankun-blog by inferring one visual metaphor from a target MDX post, maintaining the Franklin Booth-inspired neutral-white series, updating the prompt manifest, creating the 2000×800 PNG original, running the repository optimizer for the 1400×560 WebP…

not rated 2 changed 19d ago A 122 tokens original MIT

confer

04

Wang-Cankun/cankun-skills

Skill Codex

Consult another model (GPT, Claude, Codex or Gemini) for an independent opinion or review, and resume earlier consultation threads. Use when the user asks for a second model's view or to continue a peer discussion; not when another model should do the work itself.

not rated 2 changed yesterday A 57 tokens original MIT

known-unknowns

05

Wang-Cankun/cankun-skills

Skill Codex

Explore blind spots when a judgment is hard to express, familiar knowledge may illuminate the situation, or unfamiliar possibilities deserve investigation. Use for sustained discovery, not routine clarification or a direct factual answer.

not rated 2 changed 19d ago A 43 tokens copy · 92% MIT

Wang-Cankun/cankun-skills

Skill Codex

A workflow that turns a meeting, webinar, seminar, or question-and-answer recording into a full transcript and an actionable written report. It checks whether every part of the recording was transcribed and marks uncertain details.

not rated 2 changed 19d ago A 97 tokens original MIT

repo-wayfinder

07

Wang-Cankun/cankun-skills

Skill Codex

Check or design a repository's documentation system (README, AGENTS.md, CLAUDE.md, docs/): which document owns each question and how agents reach it. Use when existing docs have drifted, conflict or keep needing sync passes, or to design or rebuild a project's documentation set.

not rated 2 changed 8d ago A 63 tokens original MIT

skill-release

08

Wang-Cankun/cankun-skills

Skill Codex

Release and sync skills in the cankun-skills collection. Use when the user wants to publish or release a skill, add a new skill to the index, sync or fix a drifted skills README or the cankun.me skills page, run publish-hygiene checks, or promote a skill to its own flagship repo (or fold one back).

not rated 2 changed yesterday A 73 tokens original MIT

travel-dossier

09

Wang-Cankun/cankun-skills

Skill Claude CodeCodex

A workflow for turning travel plans and booking documents into a phone-friendly A5 travel handbook and PDF. It keeps each time, number, and rule linked to its source.

not rated 2 changed 19d ago A 52 tokens original MIT

common-ground

10

Wang-Cankun/cankun-skills

Skill Codex

Align with the user on what a task is for before acting, closing with a brief that names the finish line. Use when the user brings a half-formed idea or direction to think through, asks how something should be designed or scoped, says a result misses what they meant, before you start a long autonomous run, or after…

not rated 2 changed 17d ago A 83 tokens original MIT

taste

11

Wang-Cankun/cankun-skills

Skill Codex

Taste in made things. Use when improving a design, UI, diagram, document or code structure that works but is unsatisfying, when choosing between design alternatives, or when reviewing a design.

not rated 2 changed 19d ago A 41 tokens original MIT

ambition

12

Wang-Cankun/cankun-skills

Skill Codex

A planning method that rethinks a task through speed, ambition, depth, and range before work begins. It recommends whether the requested deliverable should be improved or reframed.

not rated 2 yesterday A 100 tokens original MIT

crew

13

Wang-Cankun/cankun-skills

Skill Codex

Run resident agents of any model family in Herdr panes, with this session as coordinator: it chooses how many agents, which models and how work and review flow, from general rules and the user's model roster. Use when the user invokes /crew or asks for side agents, several models working or discussing together, or a…

not rated 2 changed 2d ago A 71 tokens original MIT

fleet

14

Wang-Cankun/cankun-skills

Skill Codex

Workflows whose stages run on any of the user's models: Claude natively, GPT and Gemini through omp (or Pi and agy), with this session designing the stages and accepting each result. Use when the user invokes /fleet, asks for a workflow across models, or names GPT, Gemini, omp, Pi, Codex or agy workers for the work.

not rated 2 changed yesterday A 76 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: