full-picture
Skill1 starsChanged 4 months agoMITView on GitHub
Use whenever the user (a non-technical founder) asks to describe, explain, or show a feature/app/workflow/system — especially "tell me about X", "what does this do", "show me the workflow". Forces a full investigation first, then ONE complete business-language answer with no detail left out.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- federbenjamin/feder-skillstheir own version, first seen Oct 11, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- federbenjamin/feder-skills★ 3same name
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 repository9 other files it gives its agents.
- skills/nirmaan/CLAUDE.mdCLAUDE.md
- brainSkill
- fable-brainSkill
- graphifySkill
- kimi-webbridgeSkill
- neuronSkill
- nirmaanSkill
- no-slopSkill
- researchSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Read every relevant source: main logic, config/settings files, and edge-case behaviour.
- Distinctive: line 17
Do NOT answer until you can describe the whole thing.
- Distinctive: line 22
Don't trickle details across messages.
- Distinctive: line 26
NO file names, libraries, stacks, code, or internal mechanics unless he explicitly asks "how is it built".
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Full Picture — complete answers, no half answers
This founder hates partial answers and hates technical jargon. When he asks you to describe or explain anything, follow this every time.
1. Investigate BEFORE answering
- Read every relevant source: main logic, config/settings files, and edge-case behaviour.
- Specifically look for things that are easy to forget but matter to him:
- Operating / office hours (when does it run, when does it stop, quiet hours, queued-vs-sent windows)
- On/off conditions, limits, throttling, pacing
- Different states, tags, sources, and what triggers each
- What the customer/end-user actually receives
- Do NOT answer until you can describe the whole thing. A guess that omits a known dimension (like send hours) counts as a half answer.
2. Answer in ONE complete shot
- Deliver everything in a single consolidated response so he can review it once and spot any problem himself.
- Cover: what it is · the deliverables/outputs · every meaningful behaviour · timings/limits · what the end-user gets.
- Don't trickle details across messages. Don't make him ask "what about X".
3. Business language only — never technical
- Explain outcomes and value, not how it's built.
- NO file names, libraries, stacks, code, or internal mechanics unless he explicitly asks "how is it built".
- Translate technical config into plain business terms (e.g.
endHour: 20→ "messages stop at 8 PM and resume 9 AM").
4. Complete ≠ verbose
- Be precise and point-to-point. Use tight bullets/sections.
- Completeness means leaving nothing material out — not padding.
Self-check before sending
- Did I read the config/settings, not just the main logic?
- Did I include operating hours / limits / on-off conditions?
- Is it all in one answer he can review at a glance?
- Is it 100% business language, zero unrequested tech?
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.

