AGENT SKILL

para-skill

PARA method knowledge management for Obsidian vaults. Use this skill whenever the user wants to organize notes using PARA (Projects, Areas, Resources, Archive), classify a note into a PARA category, route a note to the right vault folder, normalize frontmatter fields, run a PARA hygiene review, suggest archiving, audit vault structure, or process new knowledge inputs into an existing PARA-based vault. Also trigger when the user mentions inbox processing, vault cleanup, note classification, PARA review, or asks "where does this note belong?". Works with existing Obsidian skills (obsidian-markdown, obsidian-cli) — never replaces them.

License 许可
MIT
所属仓库
bg-szy/TOP-SKILLS
最近更新
2026-11-15
Stars
★ 6
Forks
0

01 前言 Front Matter

name
para-skill
description
PARA method knowledge management for Obsidian vaults. Use this skill whenever the user wants to organize notes using PARA (Projects, Areas, Resources, Archive), classify a note into a PARA category, route a note to the right vault folder, normalize frontmatter fields, run a PARA hygiene review, suggest archiving, audit vault structure, or process new knowledge inputs into an existing PARA-based vault. Also trigger when the user mentions inbox processing, vault cleanup, note classification, PARA review, or asks "where does this note belong?". Works with existing Obsidian skills (obsidian-markdown, obsidian-cli) — never replaces them.

02 资源文件 4

03 SKILL.md 正文

PARA Obsidian Skill

What this skill does

This skill provides PARA-method decision logic for Obsidian vaults. It decides where notes belong, when to archive, and how to keep the vault healthy — while leaving file creation, markdown formatting, and Obsidian syntax to the installed base skills.

PARA is an organizational framework by Tiago Forte that structures information by action relevance, not topic:

  • Projects — concrete initiatives with a goal and an endpoint
  • Areas — ongoing responsibilities with no fixed end date
  • Resources — reference knowledge for potential future use
  • Archive — completed, paused, or inactive content

Read references/classification-rules.md for detailed classification heuristics.


Vault Configuration

Default paths for this vault (override in conversation if different):

paths:
  inbox: "0_Inbox"          # created on demand if missing
  projects: "1_Projects"
  areas: "2_Areas"
  resources: "3_Resources"
  archive: "4_Archives"

Default mode: cautious — suggest first, act only when confident or explicitly asked.


Core Workflow

For every PARA-related task, follow this sequence:

  1. Read the note content, title, existing frontmatter, tags, and current file path
  2. Collect signals — look for project indicators (deadlines, tasks, goals), area indicators (ongoing, recurring), resource indicators (reference, no action pressure), archive indicators (done, cancelled, historical)
  3. Check conventions — respect existing para_type frontmatter; existing folder placement is a strong signal
  4. Classify with a confidence level: high, medium, or low
  5. Plan frontmatter additions — only add fields from the schema, never overwrite non-PARA fields
  6. Propose routing — suggest the target path
  7. Assess risk — only act directly when confidence is high AND the user has given explicit permission or the mode is balanced/aggressive
  8. Log changes when writing anything

When in doubt: set needs_review: true, place in Inbox, and explain why.

See references/classification-rules.md for the full decision tree.


Available Actions

capture — Process new content

Accept raw text, meeting notes, ideas, or document descriptions. Classify them, propose or create a note in the right location, and set frontmatter.

Example trigger: "Capture this: Vorbereitung Workshop Führungsteam April" Output: PARA classification + proposed path + frontmatter draft

classify — Classify an existing note

Read a note and determine its PARA type. Return classification, confidence level, and reasoning.

Example trigger: "Welcher PARA-Typ ist diese Notiz?" or "Klassifiziere 2_Areas/Weiterbildung/..." Output: para_type, confidence, explanation, suggested changes

route — Determine or apply target location

Calculate the correct target folder for a note. In cautious mode: suggest only. With explicit permission: move the file.

Example trigger: "Wo gehört diese Notiz hin?" or "Route diese Notiz korrekt ein" Output: Current path → suggested path, reasoning, conflict check

normalize — Fix frontmatter

Add missing PARA frontmatter fields to a note without touching non-PARA fields. Never remove existing fields.

Example trigger: "Normalisiere das Frontmatter dieser Notiz" or "Füge PARA-Metadaten hinzu" Output: Updated frontmatter block (show diff before applying)

review — PARA hygiene report

Scan a folder or the whole vault for hygiene issues. See references/review-playbook.md for what to check.

Example trigger: "Mach einen PARA-Review" or "Zeig mir, was im Vault aufgeräumt werden sollte" Output: Structured report (projects without next steps, stale areas, inbox backlog, archiving candidates)

archive — Archive a note defensively

Move a note to the Archive folder with archived: true, archive_date, and updated status. Never delete. Preserve all wikilinks.

Example trigger: "Archiviere dieses Projekt" or "Das Projekt ist abgeschlossen" Output: Confirmation of move + frontmatter changes (dry-run by default)

audit — Full vault consistency audit

Scan all notes for PARA inconsistencies: missing frontmatter, wrong folder placement, orphaned notes, stale reviews. Produces a prioritized action list.

Example trigger: "Mach einen vollständigen Vault-Audit" or "Was stimmt in meinem Vault nicht?" Output: Audit report with actionable items

suggest — Recommendation without changes

Give a PARA recommendation with full reasoning, but make no changes to any file.

Example trigger: "Was würdest Du mit dieser Notiz machen?" or "Vorschlag für diese Datei" Output: Recommendation + reasoning (read-only)


Safety Rules

These rules are non-negotiable regardless of mode:

  1. No mass moves without explicit user authorization — always ask first
  2. No deletion — archive means move, never delete
  3. No overwriting non-PARA frontmatter fields — only add/update defined PARA fields
  4. Low confidence → needs_review — never force a classification when unsure
  5. Dry-run by default — show what would happen before doing it
  6. Preserve wikilinks — never rename files in ways that break [[links]]
  7. Log every structural change — use the change log format below
  8. No reclassification from a single weak signal — require 2+ supporting indicators

Change Log Format

When making structural changes, append to a PARA-Changelog.md in the vault root:

## 2026-03-14
- Classified `Meeting Notes Team Alpha` → project (confidence: medium)
- Suggested move to `1_Projects/team-alpha/` (not yet applied, needs_review: true)
- Normalized frontmatter in `2_Areas/Weiterbildung/KI-Kurs.md`

Frontmatter Schema

Read references/frontmatter-schema.md for the full field definitions.

Quick reference — only write these fields:

para_type: project        # project | area | resource | archive
status: active            # active | on-hold | done | archived | reference | needs_review
review_date: 2026-03-21
confidence: high          # high | medium | low
needs_review: false
archived: false
archive_date:             # only when archiving
source: manual            # manual | meeting | import | daily-note | web

Never touch: titles, body content, existing tags not prefixed with para/, wikilinks, non-PARA frontmatter fields.


Cooperation with Other Skills

This skill handles: classification logic, routing decisions, PARA frontmatter, review reports

Leave to obsidian-markdown / obsidian-cli: file creation, markdown syntax, wikilink formatting, template application, dataview queries

When creating a new note as part of capture or route, delegate file creation to the obsidian-markdown or obsidian-cli skill if available. Only use direct file writes as fallback.

Read references/compatibility-notes.md for conflict avoidance rules.


Response Format

Always communicate:

  1. What you classified/found (with para_type and confidence)
  2. Why — at least 2 supporting signals
  3. What you propose to change (as a clear list)
  4. What you're uncertain about (if anything)
  5. What you'll do next — or ask for permission before acting

For reviews and audits, use the structured report format in references/review-playbook.md.

04 同仓库更多 Skills

bg-szy
bg-szy/TOP-SKILLS

serpmaven

Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-landing-page-audit

Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: "audit my landing page", "why isn't this page converting", "review my homepage", "my ads get clicks but no signups", "people bounce from the pricing page", "CRO review", "improve conversion rate", "is my hero section clear", "roast my landing page", "rewrite my headline", "what's wrong with this page", "landing page feedback", "make the signup page convert better". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-growth-context

Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents/revnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says "set up our marketing context", "who is our ideal customer", "write our ICP", "describe the product for marketing", "positioning doc", "what's our brand voice", "remember this about our customers", "log what we tried", "what have we learned from marketing", "we changed pricing, update the context", "update our growth notes", "summarize the business for the agent", "import my product-marketing.md", "start a growth doc", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-get-listed

Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: "best X" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says "get us listed", "which directories should we submit to", "how do we get into best-of lists", "why does ChatGPT recommend competitors and not us", "get mentioned in AI answers", "submit to awesome lists", "get on G2", "where are our competitors listed", "pitch listicle authors", "find backlink opportunities", "launch directories", "get into roundups", "Product Hunt alternatives", "where should we be listed", "get cited by Perplexity". Never submits, pays or posts without a yes. Works without a Revnu account.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-ai-readiness-audit

Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks "is my site ready for AI search", "audit my site for AI answers", "AEO audit", "GEO audit", "why doesn't ChatGPT quote our pricing", "make our pages citable by AI", "do I need llms.txt", "does schema help with ChatGPT", "check our structured data", "is our content visible without JavaScript", "AI SEO audit", "optimize our homepage for AI answers", "LLM SEO check", "why does AI get our product wrong", "fix our site for AI Overviews". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.

★ 6
bg-szy
bg-szy/TOP-SKILLS

proxy-troubleshooting

Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.

★ 6