CYBRUM SOLUTIONS

Is safhe par

Chapter 05

Skills & Connectors

Chat box se ek operating layer tak — AI ko sikhana ek baar, aur apne apps se jorna

Ye chapter CCAO-F ke Configuration aur Knowledge Management domain ke liye foundation hai

Core Idea

Zyada tar log AI ko ek vending machine ki tarah treat karte hain: har baar fresh request type karte hain, kuch bhi retain nahi hota. Ye chapter ek different model sikhata hai: Skills se AI ko ek baar sikhao, Connectors se usay apne apps tak access do, aur AI ek chat interface se ek intelligent operating layer ban jata hai.

Kitchen Wali Example

3 cheezein mil kar kaam karti hain:

Chat

Ek baari ka order, AI ko batata hai is baar kya karna hai

Skill = Recipe Card

Sikhati hai har baar wahi kaam apne tareeke se kaise karna hai

Connector = Kitchen

AI ko haath deta hai aapke real apps aur data tak pahunchne ke liye

Kitchen bina recipe ke improvised, recipe bina kitchen ke sirf padhi ja sakti hai. Teenon mil kar reliable output banate hain

6 Essential Terms

TermMatlab
SkillSaved instructions jo AI ko sikhati hain ek task aapke specific tareeke se kaise karna hai
ConnectorEk safe link jo AI ko ek app tak pahunchne deta hai (files, email, messages)
Fire / TriggerJab request kisi skill se match kare to AI khud usay activate karta hai
ScopeAap kitni access grant karte ho, jitni chhoti utni safe
Read-onlyAI dekh sakta hai lekin change nahi kar sakta
Progressive disclosureAI sirf short summaries loaded rakhta hai, poori instructions sirf zaroorat par kholta hai

Part 1 · 2 Upgrades

1. Chat Box Se Operating Layer Tak

Har professional ke paas repeated friction hoti hai:

  • Accountants har mahine formatting instructions dobara paste karte hain
  • Doctors roz SOAP format requirements dobara explain karte hain
  • Marketers har chat mein brand-voice rules dohrate hain
  • Engineers har baar design-review structures restate karte hain

Ye tasks repeatable hain, ek specific tareeke se hote hain, sirf input badalta hai, yehi exactly Skills solve karti hain. Doosri friction copy-paste hai (Excel, emails, Drive folders, project trackers se), yehi Connectors solve karte hain, AI ko seedha wahan tak access de kar jahan real kaam hota hai.

2. Ek Skill Actually Kya Hai

Fundamentally simple: ek folder jismein ek text file hai jiska naam exactly SKILL.md hai. Is file mein:

  • Top pe ek required name aur description
  • Neeche plain-English instructions

Yehi minimum hai. Optional: example files, templates, reference documents, aur scripts (jo AI khud likhta hai, aap nahi). Key innovation progressive disclosure hai: AI sirf short description hamesha loaded rakhta hai, poori instructions sirf tab kholta hai jab request match kare. Isi wajah se dus skills install karne se bhi koi performance impact nahi hota.

3. Ek Connector Actually Kya Hai

Safe, permission-scoped access external apps aur data tak, ek open standard MCP (Model Context Protocol) par chalta hai. 3 critical facts:

  • AI aapki existing permissions inherit karta hai, aap khud jo files nahi reach kar sakte, wo AI bhi nahi kar sakta
  • Aap choose karte ho read-only ya read-and-write access
  • Aap control karte ho kaunsa connector har conversation mein active hai

Ready-made connectors Google Drive, Gmail, Slack, Notion, Figma, Linear, Atlassian, aur bohot sab ke liye maujood hain. Kuch interactive hain, live dashboards ya design surfaces conversation ke andar render karte hain.

4. Skills Vs Connectors Vs Projects Vs Custom Instructions

FeaturePurposeBest ForKey Test
SkillReusable how-to instructionsRepeatable tasks aapke tareeke se (formatting, voice, methodology)"Main baar baar explain karta hoon kaise"
ConnectorExternal apps tak safe accessFiles, email, messages, tickets mein padhna/act karna"Main baar baar doosri app se copy-paste karta hoon"
ProjectHamesha-loaded files/instructions ka workspaceStanding context (client, course, book)"Ye rules yahan har cheez pe apply hote hain"
Custom InstructionsHar chat pe apply hone wali preferencesGlobal style preferences"Ye har jagah, hamesha chahiye"

Key Distinction

Projects hamesha context automatically load karte hain (always on), jabke Skills trigger hone tak dormant rehti hain. Connectors access dete hain, Skills expertise deti hain, ye partners hain, alternatives nahi. Custom Instructions global hain, Skills specific task types target karti hain.

5. Slash Commands Type Karoon Ya AI Khud Jaan Le?

Claude.ai (web aur mobile) mein, Skills khud fire hoti hain, aap plain language mein apna task describe karte ho, AI aapki request ko enabled skills ki short descriptions se match karta hai, aur matching skill khud load kar leta hai. Koi slash command ki zaroorat nahi.

1Aap plain language mein apna task describe karte ho
2AI enabled skills ki descriptions se match dhoondta hai
3Matching skill khud load ho ke fire hoti hai (~90% baar automatic)
Override: skill ka naam le lo, ya doosri surfaces (Cowork, Claude Code) mein / type karo browse karne ke liye

Ahem Number

Ye automatic behavior roughly 90% baar hoti hai, isliye skill ki description likhna sab se important control mechanism ban jata hai.

Override options:

  • Skill ko explicitly plain English mein naam se bulao ("use my brand-voice skill")
  • Doosri surfaces (Cowork, Microsoft 365 add-ins, Claude Code) mein / type karo browse aur manually pick karne ke liye

Part 2 · Jo Pehle Se Hai Wo Use Karo

6. Built-In Skills

Kai document-generation skills automatically kaam karti hain jab ek switch on ho: Settings → Capabilities → “Code execution and file creation” (“Required for skills” label ke sath). Ye engine chalati hai:

  • Word: professional .docx documents
  • PowerPoint: complete slide decks
  • Excel: real spreadsheets with formulas
  • PDF: PDFs banana aur fill karna

Bas naturally poocho: “[topic] introduce karne wala ek slide deck tayar karo, general audience ke liye” aur ek finished deck download ke liye ready milegi.

Note

Jab aap Customize → Skillskholte ho, sirf ek skill dikhegi shuru mein: skill-creator (Anthropic ka skill banane ka tool). Document skills missing nahi hain, wo engine ke andar rehte hain. “+” menu ke “Browse skills” option se installable skills ki directory dekho, Notion/Figma/Atlassian ki partner skills samet.

7. Apni Apps Connect Karna

Roughly ek minute lagta hai:

  1. 1

    Chat Se

    "+" (neeche-left) click karo, Connectors pe hover karo, Manage connectors choose karo, phir Connectors ke sath "+" click karo directory kholne ke liye

  2. 2

    Ya Sidebar Se

    Customize → Connectors kholo

  3. 3

    Connect Karo

    Service select karo, Connect click karo, standard OAuth authorization complete karo

  • Connect karne ke baad, har conversation ke liye specific connectors usi "+" menu se enable karo
  • Free plans mein 1 custom connector shamil hai, ready-made directory connectors broadly available hain
  • Tool access setting sirf zaroorat par tools load kar sakti hai, jab kai connectors manage karne hon
  • Interactive badge dekho, jo live interfaces indicate karta hai jo chat ke andar render hote hain

Worked Example

Ek practice patient intake form create kar ke Google Drive mein save karo, phir usay wapis parh kar SOAP-style notes mein summarize karo, dono directions dikhata hai: write aur read, bina manual file transfer ke.

8. Skills + Connectors Sath Mein

Pattern real data fetch karna (Connector) aur output ko aapke tareeke se shape karna (Skill) combine karta hai.

1Ek plain-English sentence
2Connector real data khinch ke laata hai
3Skill usay aapke tareeke se shape karta hai
4Aap sirf finished result review karte ho
Live data se, bina copy-paste kiye

Monthly Client Close

Ek “client-summary” skill aur Google Drive connected ke sath, accountant ka monthly ritual 2 ghante ki paste-and-format se 2-minute review mein simat jata hai. Drive connector ledger fetch karta hai, skill amounts ko reporting currency mein format karti hai, expense head se group karti hai, withholding-threshold payments flag karti hai, aur 4-section template automatically apply karti hai.

Weekly Content Batch

Ek “brand-voice” skill rules encode karti hai (no exclamation marks, question hooks, banned buzzwords, CTA format). Ek Notion connector content calendar tak pahunchta hai. Request “is week ke 3 scheduled posts ke liye captions draft karo, hamari voice mein” connector se calendar parhta hai, skill se on-brand captions likhta hai, kaam composition se editing tak shift ho jata hai.

9. Kaunse Problems Ko Kya Chahiye?

Kya main baar baar explain karta hoon ke kaise karna hai?Skill chahiye
Kya main baar baar kisi doosri app se data copy-paste karta hoon?Connector chahiye
Dono?Dono chahiye
Har cheez skill nahi maangti, ek-baari sawal sirf ek achhe prompt ki zaroorat rakhte hain
CategoryExamples
Sirf SkillBrand voice, report templates, SOAP notes, review checklists
Sirf ConnectorLedgers, emails, tickets apps se pull karna
DonoMonthly closes, weekly batches, design reviews (real data fetch + specific shape apply)

2 Ehtiyat

Har cheez skill deserve nahi karti, ek-baari sawal bas ek achhe prompt ki zaroorat rakhte hain. Aur ek unnecessary connector ek khula darwaza hai, sirf wo apps connect karo jo workflow actually maangta hai.

Part 3 · Apna Skill Banana

10. Fastest Path: AI Se Likhwao

skill-creator skill use karo apna chahiye jo describe karne ke liye:

Use the skill-creator skill to help me build a skill. The skill
prepares a monthly client financial summary for my accounting firm.
Whenever I ask for a 'client summary' or 'monthly close,' it should:
Format all amounts in our reporting currency with thousands
separators; Group line items by expense head; Flag any payment above
the tax-withholding reporting threshold; Output using my standard
four-section report layout (Overview, Income, Expenses by Head,
Flags & Notes). Ask me anything you need, then build it.

AI clarifying sawal poochta hai, phir ek complete, correctly formatted skill generate karta hai. Ye “code you never write” principle ki misaal hai: aap client ho jo requirements specify kar raha hai, AI commissioned artifact produce karta hai, ek skill jo ek baar commission karo aur hamesha reuse karo.

11. SKILL.md Ki Anatomy

Level 1 · Frontmatter

Sirf name + description, hamesha loaded, decide karti hai skill relevant hai ya nahi

Level 2 · Body

Actual instructions, sirf tab load hoti hain jab description match kare

Level 3 · references/, assets/, scripts/

Detailed docs, templates, aur exact-step programs, sirf zaroorat par

Isi trick ko progressive disclosure kehte hain, dus skills install karo koi performance issue nahi hoga

Rules jo upload errors se bachate hain:

  • File ka naam exactly SKILL.md hona chahiye
  • Folder ka naam kebab-case mein ho (client-monthly-summary, na ke Client Monthly Summary)
  • Name aur description mein XML-style tags na hon (angle brackets mein kuch bhi nahi)
  • Descriptions short aur specific rehni chahiye
  • Skills ko "claude" ya "anthropic" naam se mat banao (reserved hain)

12. Description Field Hi Poora Game Hai

Description decide karti hai ke aapki skill kabhi fire hogi ya nahi. AI relevance decide karne ke liye aapki instructions nahi parhta, sirf description parhta hai. Ek vague description matlab skill jo kabhi trigger nahi hoti, ek sharp description matlab exact activation.

Formula

Kya karti hai + kab use karni hai + wo exact phrases jo aap actually bolte ho
BadBetter
"Helps with reports" (too vague)"Prepares a monthly client financial summary. Use when the user asks for a 'client summary', 'monthly close', or 'month-end report'."
"Handles patient documentation" (no trigger words)"Converts consultation notes into SOAP-format clinical notes. Use when the user asks for a 'SOAP note', 'clinical note', or to 'write up' a consultation."

Debugging Trick

AI se poocho: “Mera [skill-name] skill kab use karoge?” Agar answer bohot narrow ya wide hai, aapko exactly wo mil gaya jo description mein fix karna hai. Negative triggers overeager skills ko narrow karte hain: “Do NOT use for one-off calculations or quick questions, only for full month-end reports.”

13. Test, Phir Iterate

  1. 1

    Describe Aur Generate Karwao

    Skill describe karo, AI se pehla version banwao

  2. 2

    Instructions Parho Aur Fix Karo

    Testing se pehle obviously galat cheezein pakro (poocho: kya 2 colleagues isay parh kar same kaam karte?)

  3. 3

    Triggering Test Karo

    Wo phrases try karo jo activate honi chahiye, confirm karo load hoti hai aur unrelated requests hijack nahi karti

  4. 4

    Output Test Karo

    Kya format sahi hai, grouping sahi hai, flags sahi hain, sab sections cover hote hain?

  5. 5

    Hard Cases Test Karo

    No income wale clients, threshold pe exactly payments, messy data

  6. 6

    Failures Wapis Le Jao

    skill-creator ke paas updates ke liye

TimingProblem Kahan Hai
Pehli reply se hi galatFile mein hi problem hai (description bohot vague/broad, ya instruction bohot loose)
Shuru mein sahi, chat barhne pe kharabChat bohot lambi ho gayi, AI ne track lose kar diya, skill theek hai, naya chat start karo
Har run mein wahi mistakeStep galat jagah hai, exact steps sentences mein nahi, scripts mein honi chahiye
Pehle kaam karta tha, ab nahiSkill wahi hai, isliye context badla hai (threshold, template, workflow, ya data shift hua)

14. Skill Save Aur Share Karna

Jab skill-creator khatam kare, ek panel dikhta hai Save skill button ke sath. Click karo, skill Personal skills mein (Customize → Skills) gir jati hai, toggled on, ready, aur private. Koi zip ya upload hassle nahi.

Team ya Enterprise plans pe, specific colleagues ke sath share kar sakte ho, ya apni organization ki directory mein publish kar sakte ho. Shared skills view-only hoti hain aur khud update ho jati hain jab aap original change karte ho, isse teams standardize hoti hain.

Part 4 · Same Skill, 5 Jagah

December 2025 mein, Anthropic ne Agent Skills open standard publish kiya (agentskills.io). Adoption fast thi, OpenAI ka Codex CLI aur Google ka Gemini CLI ab wahi SKILL.md files parhte hain. Ek basic skill tools ke across travel karti hai, chahe har tool apna install path, invocation syntax, permissions, aur features us portable core ke around add karta ho.

Linux Foundation ne Agentic AI Foundation banayi, MCP (jis standard par connectors chalte hain) aur related infrastructure ko khule tareeke se govern karne ke liye, kisi ek vendor ke through nahi.

SurfaceKis Ke LiyeSkill InstallApp ConnectApna Banana
Claude.ai (web/mobile)Sab ke liye, main toolDirectory mein Install click karo ya zip upload karo"+" → Connectors → chuno → sign inskill-creator likhta hai, Save skill click karo
Cowork/OpenWork (desktop)Knowledge workers, non-codersWahi directory, skills automatically dikhti hainWahi flow, plus computer ki files bhi reach karta haiDescribe karo, agent folder mein save kar sakta hai
Claude Code/OpenCode (terminal)Code ke sath kaam karne wale logSkill folder ko skills directory mein drop karoConfig mein ek dafa setup karo, phir plain language mein poochoAgent se create karwao, wo files likhta hai

Note

Har jode ka pehla tool commercial hai, doosra open-source hai. Dono wahi SKILL.md parhte hain. Non-programmers ke liye: Claude.ai mein start aur rehna karo (buttons, toggles, koi file management nahi). Cowork agla natural step hai jab aap chahte ho AI seedha desktop files pe kaam kare.

ChatGPT Aur Gemini Ka Kya?

Skills pe, picture cross-vendor hai, kyunke Agent Skills ek open standard hai, OpenAI (Codex CLI) aur Google (Gemini CLI), plus VS Code aur Cursor, wahi SKILL.md files parhte hain. Ek skill portable hai, ek baar likho, kai tools mein chalao.

Lekin “ek baar sikhao” consumer chat apps ke andar, har vendor ka apna, non-portable version hai:

VendorNaamKya Hai
ChatGPTCustom GPTsEk saved version, instructions aur knowledge files ke sath, GPT Store se distribute hoti hai, sirf ChatGPT ke andar rehti hai
GeminiGemsSaved Gemini personas, instructions aur files ke sath, sirf Google apps ke andar rehte hain

Connectors pe, teenon ke paas equivalents hain (ChatGPT connectors/apps se, Gemini Workspace aur extensions se). MCP technology increasingly shared hai, principles har jagah same hain.

Skills portable hain (open standard, kai tools), GPTs aur Gems vendor-specific hain (aap unhe kahin aur le nahi ja sakte). Agar sirf ek tool use karte ho, GPTs ya Gems theek hain. Multi-model strategy ke liye, Skills future-proof hain.

Part 5 · Safely Use Karo

Wahi principle jo pichli Foundations courses mein tha: model ke andar kuch bhi check nahi karta ke koi action safe ya correct hai, aap wo check ho.

Core Principle

“Ek skill un instructions ka set hai jo aap AI ko follow karne de rahe ho, aur ek connector aapki real data ka darwaza hai. Ek anjaan skill ko usi tarah treat karo jaise ek contract jis pe sign karne wale ho, aur ek connector ko usi tarah jaise ek chaabi jo aap kisi ko de rahe ho.”

Malicious Skills

Ek text file (aur scripts) hidden instructions rakh sakti hai jo data leak kare ya suspicious servers se contact kare. Prompt injection aur data exfiltration dono possible hain

Over-Broad Connector Access

Connector sirf wahi reach kar sakta hai jo aap kar sakte ho, lekin careless write-access ek galat edit, galat jagah record, ya bina undo ke deleted file bana sakta hai

Ek anjaan skill ko contract samjho jis pe sign karne wale ho, ek connector ko chaabi samjho jo aap kisi ko de rahe ho

Safe-Use Checklist

  • Trusted sources se skills install karo, built-in Anthropic skills aur official directory safe default hain
  • Enable karne se pehle skill parho, SKILL.md aur koi bhi bundled files kholo, AI se poocho "ye skill parh ke batao exactly kya instruct karti hai, external servers, credentials, ya data leak se juri koi cheez flag karo"
  • Connectors ko read-only se start karo, "search and summarize" ki permission pehle do, "send/create/delete" baad mein
  • Sab se chhoti folder ya app tak scope karo jo task ko chahiye, sab kuch connect mat karo
  • Scope ek connector ka idea hai, Skill ka nahi, connectors ke paas scope dials hote hain, skills ke paas nahi, skill parhna hi uska control hai
  • Edits/moves/deletes allow karne se pehle confirm karo connector recovery, version history, aur undo kaise handle karta hai
  • Team mein, shared skills ko organization ki directory se route karo, zips idhar udhar mat bhejo

Isse dar mat jao, built-in tools safe hain aur roz ka workflow low-risk hai. Point ye hai ke jaise jaise aap built-in tools se community skills install karne aur write access dene ki taraf barhte ho, aapki ehtiyat bhi capability ke sath barhni chahiye.

Poora Course, Compressed

  • Chat ek baar batata hai, Skill har baar sikhati hai, Connector haath deta hai apps tak (kitchen: connectors kitchen hain, skills recipes hain)
  • Ek Skill ek folder hai SKILL.md text file ke sath: name, description, plain-English instructions, koi code shuru mein nahi chahiye
  • Ek Connector ek app tak safe, permission-scoped access hai, MCP standard par chalta hai, AI aapki permissions inherit karta hai
  • Claude.ai mein, skills automatic fire hoti hain jab prompt description match kare, description sab se important cheez hai jo aap likhte ho
  • Friction se diagnose karo: kaise explain kar raha hoon → Skill, app se copy-paste kar raha hoon → Connector, dono → dono
  • AI ko describe kar ke skills banao (skill-creator likhta hai), phir triggering aur output test karo, iterate karo
  • Ek baar likhi hui skill Agent Skills open standard ki wajah se kai tools mein chalti hai, ChatGPT ke GPTs ya Gemini ke Gems (vendor-locked) ke ulat
  • Care capability ke sath scale karti hai: enable se pehle skills parho, trusted sources se install karo, connectors read-only se start karo

Underneath ek recurring shift hai: AI ek box jismein aap type karte ho, wo nahi rehta, ye ek layer ban jata hai jo aapke standards jaanta hai aur aapke tools tak pahunchta hai.

Ab Khud Try Karo: 6 Exercises

Har ek roughly 30 minute leta hai.

  1. 1

    1. Ek Built-In Skill Trigger Karo

    File creation on confirm karo, phir Claude se bolo "isay ek slide PowerPoint mein badal do, title aur 3 bullets ke sath: [3 facts paste karo]." Dekho PowerPoint skill khud fire hoti hai.

  2. 2

    2. Ek App Connect Karo, Read-Only

    Google Drive ya Gmail connect karo, chat ke liye enable karo, Claude se ek specific document dhoondh ke summarize karwao plus 3 important numbers identify karwao, notice karo koi download ya copy-paste nahi chahiye.

  3. 3

    3. Baat Kar Ke Apna Pehla Skill Banao

    Apna sab se repetitive re-explanation task chuno, phir: "skill-creator use kar ke [task] ke liye ek skill banao. Ye rules follow karo: [list]."

  4. 4

    4. Description Ko Pressure-Test Karo

    Banane ke baad: "Ye skill kab use karoge? Aur kab NAHI use karoge?" Agar answer bohot wide ya narrow hai, description update karwao.

  5. 5

    5. Ek Skill Ka Safety Audit Karo

    Koi bhi skill jo aap ne nahi likhi, poocho: "Ye skill parh ke plain language mein batao exactly kya instruct karti hai. External server, credentials, ya data leak se juri koi cheez flag karo."

  6. 6

    6. Apne 3 Tasks Diagnose Karo

    3 recurring annoyances likho. Har ek ke liye: friction kaise-explain-karna (Skill) hai, app-se-fetch (Connector) hai, ya dono?

5 Hands-On Projects

ProjectWaqtKya Banega
1. Apna Pehla Real Skill30-45 minApne sab se zyada re-explained task ko ek skill mein badlo jo aapka tareeqa jaanti ho
2. Ek App Connect Karo, Read-Only20-30 minGoogle Drive ya Gmail connect karo, real sawal poocho jise andar ki cheez chahiye
3. Skill Aur Connector Ko Sath Wire Karo45-60 minProject 1 aur 2 combine karo: connector real data fetch karta hai, skill usay aapke tareeke se shape karti hai
4. Portable Banao Ya Hand-Off Karo30 minApni skill kisi dost/colleague ke sath share karo, ya doosri surface (Cowork/Claude Code) pe load kar ke chalao
5. Trust Karne Se Pehle Audit Karo15-20 minOfficial directory se ek skill install karo (jo aapne nahi likhi), rely karne se pehle usay parh ke audit karo

Har Project Ka Success Statement

“Maine AI ko sikha diya main apna weekly kaam kaise karta hoon, ek dafa, ab wo ek sentence mein har baar karta hai.” — yehi feeling har project ka goal hai.

Agar Beech Mein Atak Jao

ProblemFix
Skill kabhi trigger nahi hoti, ya galat cheezon pe fire hoti haiDono description problems hain. Poocho: "Mera [naam] skill kab use karoge, aur kab nahi?" Description tighten karo
Connector file "nahi dhoond pata"Usually permissions ya scope. Confirm karo connector is chat ke liye enabled hai aur aapka apna account file khol sakta hai
AI ne connected data use karne ki bajaye glance se answer diyaExplicitly naam lo: "Mere [app] connector se actual file fetch karo answer dene se pehle"
Write access ya sensitive data se nervous hoRead-only raho, jo zaroorat nahi wo strip karo pehle, write access sirf un tools ko do jo achha behave kar chuke hon
Chat lambi ho ke confused ho gayiNaya chat start karo, task 2 lines mein restate karo, aage barho

Is Chapter Ke Naye Terms

Exam ke liye ye poori glossary yaad rakho, koi bhi term skip mat karo:

TermMatlab
SkillSaved instructions jo AI ko ek task aapke specific tareeke se karna sikhati hain
ConnectorEk safe, permission-scoped link jo AI ko ek app tak pahunchne deta hai
Fire / TriggerJab AI khud request ko skill ki description se match kar ke usay activate kare
ScopeKitni access grant ki gayi hai, jitni chhoti utni safe
Read-onlyAI dekh sakta hai lekin change nahi kar sakta
Progressive disclosureSirf short description hamesha loaded rakhna, poori instructions sirf zaroorat par kholna
SKILL.mdWo required text file jismein skill ka name, description, aur instructions hoti hain
FrontmatterSKILL.md ke shuru mein --- lines ke darmiyan hissa, sirf name aur description
MCP (Model Context Protocol)Wo open standard jis par Connectors chalte hain
Agent Skills standardDecember 2025 mein Anthropic ki published open specification, jo SKILL.md ko portable banati hai
Agentic AI FoundationLinux Foundation ki taraf se bani body jo MCP aur related infrastructure ko khule tareeke se govern karti hai
skill-creatorAnthropic ki apni skill jo naye skills banane mein madad karti hai
Custom GPTChatGPT ka vendor-specific, non-portable "teach it once" feature
GemsGemini ka vendor-specific, non-portable "teach it once" feature
Prompt injectionEk malicious skill ka AI ko unintended actions ki taraf manipulate karna
Data exfiltrationCode ka chupke se information bahar bhej dena

Source Note

Ye Cybrum notes Agent Factory book (agentfactory.panaversity.org) ke “Skills & Connectors” crash course par based hain, uski copy nahi. Original source dekho: agentfactory.panaversity.org/docs/skills-connectors-crash-course.

Self-Test

Khud Se Poocho

Pehle khud answer do, phir sawal pe click kar ke answer check karo.

1Skill aur Connector mein bunyadi farq kya hai?
Skill batati hai kaam kaise karna hai (recipe card), Connector real apps aur data tak access deta hai (kitchen). Skill on-demand fire hoti hai, Connector per-conversation enable hota hai. Dono partners hain, alternatives nahi.
2Progressive disclosure kya hai, aur ye kyun important hai?
AI sirf skill ki short description hamesha loaded rakhta hai, poori instructions sirf tab load karta hai jab request match kare. Isi wajah se dus skills install karne se bhi koi performance impact ya confusion nahi hoti.
3SKILL.md ki minimum requirement kya hai?
Ek folder jismein ek text file ho, naam exactly SKILL.md, jisme frontmatter mein name aur description ho (hamesha loaded), aur body mein plain-English instructions (sirf match hone par loaded).
4Skill ki description field itni important kyun hai?
AI relevance decide karne ke liye sirf description parhta hai, instructions nahi. Vague description matlab skill kabhi fire nahi hoti, sharp description (kya + kab + exact phrases) matlab exact activation.
5Skills, ChatGPT ke Custom GPTs ya Gemini ke Gems se kaise different hain?
Skills Agent Skills open standard par based hain, isliye portable hain, ek baar likho kai tools (Claude.ai, Claude Code, Codex CLI, Gemini CLI) mein chalao. Custom GPTs aur Gems vendor-specific hain, sirf apne hi product ke andar rehte hain.
6Skills aur Connectors ke liye safety control alag kyun hai?
Connectors ke paas scope dials hote hain jo aap grant aur narrow kar sakte ho, isliye read-only se start karna unka control hai. Skills ke paas koi scope dial nahi, wo chat ki jitni access hai usi mein chalti hain, isliye enable karne se pehle skill parhna hi unka control hai.
72 real risks kya hain jo is chapter mein named hain?
Malicious skills (hidden instructions jo data leak ya prompt injection kar sakti hain) aur over-broad connector access (careless write-access se galat edits, galat jagah records, ya bina undo ke deleted files).
8Kaunse problem ko Skill chahiye, kaunse ko Connector, ye kaise diagnose karte hain?
Sawal poocho: kya main baar baar explain karta hoon kaise karna hai? (Skill chahiye). Kya main baar baar kisi doosri app se data copy-paste karta hoon? (Connector chahiye). Dono? (Dono chahiye).
9Ek skill test karte waqt, agar wo pehli reply se hi galat ho, to problem kahan hai?
Problem file mein hi hai, description bohot vague ya broad hai, ya koi instruction bohot loose hai. (Agar chat barhne pe kharab ho, to problem chat ki length hai, skill ki nahi.)
10Ye poora chapter ka underlying shift kya hai?
AI ek box jismein type karte ho, wo nahi rehta, ye ek operating layer ban jata hai jo aapke standards jaanta hai (Skills se) aur aapke real tools tak pahunchta hai (Connectors se).