zoom-out
Skill1 starsChanged 53 days agoMITView on GitHub
Go up a level of abstraction and map all relevant modules and callers. Use when unfamiliar with a section of code or needing to understand how something fits into the bigger picture.
114 other projects use a version of this, 74 of them edited.
Adopted by
Most recently taken up by
- ishandutta2007/Awesome-Claude-Skillstheir own version, first seen Nov 8, 2026
- matheus3006/my-claude-skillsedited, first seen Nov 8, 2026
- anotherben/claude-harnesstheir own version, first seen Nov 8, 2026
- shkodnik1917/claude-brainlabedited, first seen Nov 8, 2026
- gustaferiksson/skillsedited, first seen Nov 7, 2026
- MatthewYe/autopilot-toolkittheir own version, first seen Nov 7, 2026
Used with
Projects with it also use request-refactor-plan, design-an-interface and 8 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
simo97Skillrequest-refactor-plan
Use this skill when user wants to create a refactor plan.
Also in 16 projects that use this
simo97Skilldesign-an-interface
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Also in 16 projects that use this
GoogleSkillsetup-matt-pocock-skills
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
Also in 45 projects that use this
kennethkeimSkillubiquitous-language
Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
Also in 15 projects that use this
Code-ShockSkillgit-guardrails
Set up git guardrails — a Claude Code PreToolUse hook that intercepts and blocks dangerous git commands such as force-push and hard reset before they run. Use to install git safety hooks or when the user runs /git-guardrails.
Also in 3 projects that use this
AnasX7Skillsetup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
Also in 26 projects that use this
- +3 more from simo97
Other versions114 projects use a version of this.
Word for word · 0
None found.
Edited · 74
- victorgarciaesgi/regle★ 50814% same
- amazingloft999-droid/mattpocock-skills★ 42214% same
- openvetta/open-vetta★ 30214% same
- InditexTech/weavejs★ 26614% same
- yamcodes/arkenv★ 15113% same
- alex-on-ai/WebReaper★ 14914% same
- aurorasoft2/Matt_Pocock_Skills★ 13314% same
- GGGODLIN/gggodlin-cc-harness★ 7313% same
- VisualxIntelligence/mattpocok-skills★ 5514% same
- javimosch/supercli★ 5314% same
64 more not listed
Wrote their own version · 40
- jpcaparas/skills★ 53same name
- drvoss/everything-copilot-cli★ 48same name
- felvieira/claude-skills-fv★ 27same name
- aveproject/ave★ 24same name
- helderberto/agent-skills★ 19same name
- ishandutta2007/Awesome-Claude-Skills★ 16same name
- fusebase-dev/fusebase-flow★ 9same name
- uwvwko-zzz/mattpocock-skills-openclaw★ 9same name
- anotherben/claude-harness★ 7same name
- AshExplained/roblox-skills★ 5same name
30 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- adversarial-gameplay-acceptanceSkill
- ai-daily-pulseSkill
- beautiful-feishu-whiteboardSkill
- cpp-codereviewSkill
- daily-weekly-reportSkill
- feishu-cardSkill
- architectSkill
- brainstormSkill
- cavemanSkill
- debugSkill
- grillSkill
- guideSkill
- handoffSkill
- implementSkill
- planSkill
- prototypeSkill
- reviewSkill
- to-issuesSkill
- to-prdSkill
- triageSkill
- silk-designSkill
- tig-acting-taskSkill
- xhs-zine-coverSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 24 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Ask or infer what the user wants to understand:
- Distinctive: line 76
Use the project's actual vocabulary — Manager names, struct names, sdp command names — not generic terms.
- Very specific: line 80
Always check CommandRegister.h for command routing (REGISTER_COMMAND entries)
- Distinctive: line 81
Look for Manager singletons and their dependencies
- Very specific: line 82
Check .sdp files in Common/ (CS/SC) and Inter/ (server-to-server) for protocol definitions
“Common” is measured: kept by at least 6 in 10 of the 24 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Zoom Out
Get a map of how a piece of code fits into the bigger picture. Use when you're unfamiliar with an area, about to make changes, or need to understand call chains before modifying behaviour.
When to Invoke
- About to work in an unfamiliar module or subsystem
- Need to understand who calls a function, Manager, or CmdParser handler
- Planning changes that might have side effects elsewhere
- User asks "what touches this?" or "how does this connect?"
Process
1. Identify the Target
Ask or infer what the user wants to understand:
- A specific function, class, Manager, or CmdParser handler
- A subsystem (e.g. "the mail system", "guild logic")
- A data flow (e.g. "how does player login work end to end?")
2. Map Upward — Callers
Walk up from the target:
- Who calls this function/handler? (grep for function name, check CommandRegister.h for command routing)
- What triggers this code path? (client CS command? server-to-server Inter command? timer?)
- Which Managers or Logic layers are involved?
3. Map Downward — Dependencies
Walk down from the target:
- What does this module depend on? (other Managers, utility classes, data loaders)
- What data does it read/write? (player data, global data, caches)
- What protocols does it send/receive? (SC responses, Inter messages)
4. Map Sideways — Peers
Identify related modules at the same level:
- Other handlers in the same CmdParser
- Other methods on the same Manager
- Sibling modules in the same subsystem
5. Present the Map
Output a structured overview:
## Target: <module/function name>
### Call Chain (upward)
Client → CmdParser::<Handler>::onCmd → <Manager>::<method>
### Dependencies (downward)
- <Manager>::getData() — reads player data
- SafeSub() — balance calculation
- SC_<protocol> — sends response to client
### Peers (sideways)
- CmdParser::<OtherHandler> — related command in same parser
- <Manager>::<otherMethod> — sibling operation
### Key Data Flows
- Reads: PlayerData.stXXX, GlobalData.iXXX
- Writes: PlayerData.stXXX (calls setChanged())
- Protocols: CS_XXX → SC_YYY
### Notes
- <any important context: race conditions, ordering constraints, known issues>Use the project's actual vocabulary — Manager names, struct names, sdp command names — not generic terms.
C++ Game Server Specifics
- Always check
CommandRegister.hfor command routing (REGISTER_COMMAND entries) - Look for Manager singletons and their dependencies
- Check
.sdpfiles inCommon/(CS/SC) andInter/(server-to-server) for protocol definitions - Note
setChanged()calls — these indicate persistent state modifications - Identify which layer owns the logic (CmdParser should only parse + delegate, Manager owns business logic)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

