New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Help

by agenticnotetaking in agenticnotetaking/arscontexta

Contextual guidance and command discovery. An agent skill from agenticnotetaking/arscontexta.

MITAuto-check: notesKnowledge Management

Install Help

skills CLI
$ npx skills add agenticnotetaking/arscontexta --skill help -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install agenticnotetaking/arscontexta help --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/agenticnotetaking/arscontexta.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/help .claude/skills/help && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
help
GitHub stars
3.5k
Token cost
~3.3k tokens
SKILL.md length
1,022 words
Files
2
Skills in repo
25
Repo updated
First seen
Licence
MIT

At a glance

Contextual guidance and command discovery. An agent skill from agenticnotetaking/arscontexta.

  • Works in 5 steps: Gather Vault State → Resolve Domain Vocabulary → Determine Mode → …
  • How does this work
  • SKILL.md covers EXECUTE NOW, Step 1: Gather Vault State, Step 2: Resolve Domain… and Step 3: Determine Mode, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Help is an agent skill from agenticnotetaking/arscontexta. Contextual guidance and command discovery. Three modes — narrative (first-time), contextual (mid-task), compact (quick reference). Shows available commands, active skills, and intelligent suggestions based on vault state. Triggers on "/help", "what can I do", "show commands", "how does this work".

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `skill.json`).

It sits in Knowledge Management. The repository describes itself as: Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you think and work, have a conversation and get a complete second brain as… The licence is MIT.

When your agent uses it

  • How does this work

Example prompts

  • “what can I do”
  • “show commands”
  • “how does this work”
  • “/help”

Requirements

  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Gather Vault State
  2. Resolve Domain Vocabulary
  3. Determine Mode
  4. Discover Commands
  5. Render

What it can do on your machine

Read from SKILL.md and the folder at commit 2acfd5c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Help loads about 3.3k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 1,022 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Grep, Glob, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from agenticnotetaking/arscontexta at commit 2acfd5c, republished under its MIT licence (© agenticnotetaking). 1,022 words, ~3,347 tokens.

Download SKILL.mdSave it as .claude/skills/help/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
help
description
Contextual guidance and command discovery. Three modes — narrative (first-time), contextual (mid-task), compact (quick reference). Shows available commands, active skills, and intelligent suggestions based on vault state. Triggers on "/help", "what can I do", "show commands", "how does this work".
allowed-tools
Read, Grep, Glob, Bash
user-invocable
true
version
1.0
generated_from
arscontexta-v1.6

EXECUTE NOW

Target: $ARGUMENTS

Parse immediately:

  • If target contains --compact: force compact mode regardless of vault state
  • If target contains a skill name (e.g., "help reduce" or "help reflect"): show detailed help for that specific skill
  • If target is empty: determine mode from vault state

Execute these steps:

  1. Gather vault state (Step 1)
  2. Resolve domain vocabulary (Step 2)
  3. Determine mode (Step 3)
  4. Discover commands dynamically (Step 4)
  5. Render the appropriate mode (Step 5)

START NOW. Reference below defines each step.

Step 1: Gather Vault State

Determine the notes folder by checking which domain-named directory exists (notes/, reflections/, concepts/, ideas/, decisions/, memories/, or any custom name from derivation-manifest.md). Then gather counts:

  • Note count: .md files in the notes folder, excluding MOCs (files with type: moc in frontmatter)
  • Inbox count: .md files in the inbox folder (inbox/, journal/, encounters/, etc.)
  • Observation count: .md files in ops/observations/ or ops/methodology/
  • Tension count: .md files in ops/tensions/
  • Connection density: count wiki links ([[) across notes folder; sparse if fewer than 2x note count
  • Queue state: pending tasks in ops/queue/queue.yaml or ops/queue/queue.json
  • Health warnings: check latest report in ops/health/ if it exists
  • Tutorial state: check ops/tutorial-state.yaml for incomplete tutorial
  • Session count: estimate from ops/sessions/ file count (indicates usage maturity)
bash
# Quick state gathering
note_count=$(ls -1 {vocabulary.notes}/*.md 2>/dev/null | wc -l | tr -d ' ')
inbox_count=$(ls -1 {vocabulary.inbox}/*.md 2>/dev/null | wc -l | tr -d ' ')
obs_count=$(ls -1 ops/observations/*.md ops/methodology/*.md 2>/dev/null | wc -l | tr -d ' ')
tension_count=$(ls -1 ops/tensions/*.md 2>/dev/null | wc -l | tr -d ' ')

Step 2: Resolve Domain Vocabulary

Read ops/derivation-manifest.md (or fall back to ops/derivation.md Vocabulary Mapping section). Extract domain-native names for: reduce, reflect, reweave, verify, rethink, note, MOC, inbox. If neither file exists, use universal names.

For display, show domain name with universal in parentheses when they differ:

  /{domain:reduce} (reduce)   Extract patterns from journal entries

If domain name equals universal name, show just the name:

  /reduce   Extract insights from source material

Step 3: Determine Mode

ConditionMode
--compact in argumentsCompact
Specific skill name in argumentsSkill detail
Note count < 5Narrative
Note count >= 5Contextual

Step 4: Discover Commands

Scan ${CLAUDE_PLUGIN_ROOT}/skills/ dynamically:

  • Subdirectories containing SKILL.md (e.g., reduce/SKILL.md)

Extract name: and description: from each frontmatter. Do NOT hardcode the command list.

Command categories:

CategoryCommandsWhen to Show
Core/ask, /learn, /next, /helpAlways
Processing/reduce, /reflect, /reweave, /verifyAlways (all skills from day one)
Maintenance/health, /rethink, /rememberAlways
Evolution/architect, /reseed, /add-domain, /upgradeAlways
Meta/tutorial, /graph, /statsAlways

Step 5: Render

NARRATIVE MODE (note count < 5)

This is the first impression. The user is new or nearly new. Explain what the system IS before listing what it DOES.

What narrative mode communicates:

  1. What Ars Contexta is (one sentence)
  2. What THEIR system was built to do (read from ops/derivation.md if available)
  3. What they can do RIGHT NOW (concrete actions, not abstract possibilities)
  4. How the system grows with them
--=={ ars contexta : help }==--

Your knowledge system is ready. It turns thoughts
into a connected graph where every note compounds
the value of every other note.

[If ops/derivation.md exists:]
Your system: [domain description from derivation]

Getting started:

  Tell me a thought, observation, or question.
  I will turn it into a note and show you what
  the system does with it.

  Or try one of these:

  /ask [question]    Ask about [domain] -- I will
                     answer from your graph
  /learn [topic]     Research [topic] and grow
                     your graph with findings
  /tutorial          Walk through the system
                     step by step (5 minutes)

As your graph grows, you will use:
  /reduce [source]   Extract insights from articles,
                     notes, or any raw material
  /reflect           Find connections between notes
  /health            Check your system's health

Your system also learns from experience:
  /remember             Capture when something goes wrong
                        (your system remembers corrections)
  /ask [question]       Ask about [domain] -- answers draw
                        from 249 methodology notes AND your
                        system's own methodology notes

Type /help anytime for guidance.

Manual reference (if manual/ exists): If the vault contains a manual/ directory, add to the narrative output:

  For a deeper guide, read manual/getting-started.md
  or explore the full manual in manual/manual.md.

Key principles for narrative mode:

  • Conversational, not list-like
  • Show the easiest entry point first ("tell me a thought")
  • Group commands by when the user would need them, not alphabetically
  • Reference the user's actual domain when possible
  • If tutorial is incomplete, mention: "You have an unfinished tutorial (step N of 5). Resume with /tutorial"
Show full SKILL.md (526 more words)Show less
CONTEXTUAL MODE (note count >= 5)

The user has been working. Show them what is happening NOW and what would be most valuable NEXT.

What contextual mode communicates:

  1. Current system state (brief metrics)
  2. What needs attention right now (state-aware)
  3. Suggested next action (the single most valuable thing)
  4. Commands they might not know yet
  5. Full command reference
--=={ ars contexta : help }==--

Your system: [domain] knowledge graph
  [N] notes, [M] connections, [P] pending tasks

Right now:
  [State-aware observations — pick up to 3 most relevant:]
  Your inbox has [N] items (oldest: [age])
  [N] pending observations -- approaching /rethink threshold
  Pipeline: [N] tasks at [phase] phase
  [N] notes have sparse connections (< 2 links)

Suggested:
  [Single most valuable next action with rationale]

[If user hasn't tried certain commands:]
Commands you might not know:
  /remember    Capture when something goes wrong
               (teaches your system from friction)
  /graph       Explore your knowledge graph visually
  /stats       See vault metrics in shareable format

All commands:
  /ask [question]        Query your knowledge system
  /learn [topic]         Research and grow your graph
  /next                  Next recommended action
  /{reduce} [source]     Extract insights from material
  /{reflect}             Find connections between notes
  /{reweave}             Update older notes
  /verify [note]         Combined quality verification
  /health                Run vault diagnostics
  /{rethink}             Challenge assumptions
  /remember              Capture methodology learning
  /architect             Research-backed evolution advice
  /reseed                Principled restructuring
  /add-domain            Extend with a new domain
  /upgrade               Check for skill improvements
  /tutorial              Interactive walkthrough
  /graph                 Graph exploration
  /stats                 Vault metrics

State-aware suggestion logic:

Pick the FIRST matching condition:

ConditionSuggestion
Inbox has itemsProcess your inbox: /{reduce} [oldest-inbox-item-filename]
Pipeline has pending tasksResume processing: /next
10+ observations or 5+ tensionsReview accumulated evidence: /{rethink}
Health warnings existCheck health: /health
Notes exist, sparse connectionsBuild connections: /{reflect}
User hasn't tried /learnGrow your graph: /learn [topic related to their domain]
Methodology folder has friction notesYour system is learning from friction -- review with /{rethink}
Methodology folder has notes beyond derivation-rationaleYour system has [N] operational learnings -- query them with /ask or browse ops/methodology/
Sessions accumulating without miningMine session learnings: /remember
Healthy vault, no pressureWhat is next: /next

Reference a specific file when possible (e.g., the actual oldest inbox filename, the actual pending task description).

Manual page suggestion (if manual/ exists): Based on the first matching state-aware condition, suggest the relevant manual page:

ConditionManual Page
Inbox has items[[workflows]] (processing pipeline)
Pipeline has pending tasks[[workflows]] (batch processing)
Observations/tensions accumulated[[meta-skills]] (/rethink guide)
Health warnings exist[[troubleshooting]]
Sparse connections[[workflows]] (connection finding)
General orientation needed[[getting-started]]

Add: For details, see manual/{page}.md

"Commands you might not know" logic:

Track which commands the user has likely used by checking for their artifacts:

  • /learn used if ops/sessions/ has learn-related transcripts or inbox has research files
  • /remember used if ops/methodology/ or ops/observations/ has files
  • /graph used if... (no artifact, always suggest if note count > 20)
  • /stats used if... (no artifact, always suggest if note count > 10)

Show up to 3 commands the user probably has not tried. Skip commands they clearly have used.

COMPACT MODE (--compact flag)

Quick reference. No state analysis. No suggestions. Just the commands.

--=={ ars contexta : help --compact }==--

  /ask [question]        Query knowledge system
  /learn [topic]         Research and grow graph
  /next                  Next recommended action
  /{reduce} [source]     Extract insights
  /{reflect}             Find connections
  /{reweave}             Update older notes
  /verify [note]         Quality verification
  /health                Vault diagnostics
  /{rethink}             Challenge assumptions
  /remember              Capture methodology learning
  /architect             Evolution advice
  /reseed                Restructure system
  /add-domain            Add new domain
  /upgrade               Check for improvements
  /tutorial              Interactive walkthrough
  /graph                 Graph exploration
  /stats                 Vault metrics
  /help                  This guide
SKILL DETAIL MODE (help [skill-name])

When the user asks for help with a specific skill (e.g., /help reduce or /help reflect):

  1. Find the skill's SKILL.md file
  2. Read its frontmatter (name, description) and first section
  3. Display a focused guide:
--=={ ars contexta : help /{skill-name} }==--

{Description from frontmatter}

Usage:
  /{skill-name} [arguments]

Examples:
  /{skill-name} inbox/article.md
  /{skill-name} --since 7d

What it does:
  {2-3 sentence summary extracted from the skill's
   philosophy or first methodology section}

Related:
  /{related-skill}    {one-line description}

Special case for /help ask: Expand the "What it does" section to mention both knowledge layers:

What it does:
  Queries the bundled methodology knowledge base (249
  research claims) AND your local methodology notes
  in ops/methodology/. Answers are grounded in
  specific claims and applied to your system's
  configuration.

Extract the pipeline position (what comes before and after this skill) to show workflow context.

Manual cross-reference: If manual/skills.md exists, also check it for additional context about the requested skill. The manual may contain domain-specific examples and workflow context that the SKILL.md frontmatter does not include.

Rendering Rules

  • Max width: 76 characters
  • No ANSI color codes
  • No emoji
  • Monospaced alignment assumed
  • Display short command forms (/reduce), not plugin-qualified forms (/arscontexta:reduce)
  • Domain-native names in curly braces (e.g., /{reduce}) are resolved from derivation-manifest.md
  • When domain name equals universal name, drop the braces

Edge Cases

No ops/derivation-manifest.md: Use universal vocabulary for all command names.

Pre-init invocation: If no vault structure exists at all (no notes folder, no ops/), show a minimal message:

Ars Contexta is not initialized in this directory.
Run /setup to create your knowledge system.

Multiple domains: If ops/derivation-manifest.md lists multiple domains, show commands grouped by domain in contextual mode.

© agenticnotetaking, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/help of agenticnotetaking/arscontexta.

  • SKILL.md
  • skill.json

Open the folder on GitHubat commit 2acfd5c

Compare with similar skills

Help next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Help compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Help this skillagenticnotetaking/arscontexta3.5k—~3.3kAutomated safety check: NotesMIT
Logseq Review Workflow Evallogseq/logseq45k—~1kAutomated safety check: PassAGPL-3.0
Baoyu URL To Markdownsdyckjq-lab/llm-wiki-skill2.5k2 repos~3.2kAutomated safety check: PassNone
Obsidian CLIAtmosphere/atmosphere3.8k13 repos~795Automated safety check: PassApache-2.0
Esm Cjs Risk Scanlogseq/logseq45k—~3.3kAutomated safety check: PassAGPL-3.0
Karpathy LLM WikiAstro-Han/karpathy-llm-wiki2.4k—~3.6kAutomated safety check: PassMIT

Similar skills

  • Logseq Review Workflow Eval

    logseq/logseq

    Compare two revisions of the Logseq logseq-review-workflow skill by running the same review prompt against isolated before and after skill snapshots, collecting both outputs, and producing a…

    45k GitHub stars~1k tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Baoyu URL To Markdown

    sdyckjq-lab/llm-wiki-skill

    Fetch any URL and convert to markdown using Chrome CDP. An agent skill from sdyckjq-lab/llm-wiki-skill.

    2.5k GitHub starsUsed in 2 repos~3.2k tokens
    Knowledge ManagementAuto-check passed

  • Obsidian CLI

    Atmosphere/atmosphere

    Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more.

    3.8k GitHub starsUsed in 13 repos~795 tokens
    Knowledge ManagementAuto-check passed

  • Esm Cjs Risk Scan

    logseq/logseq

    Scan Logseq ClojureScript Node/Electron targets for npm module loading risks, especially ESM-only packages that may fail when loaded through js/require or shadow-cljs require-based shims.

    45k GitHub stars~3.3k tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Karpathy LLM Wiki

    Astro-Han/karpathy-llm-wiki

    A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.

    2.4k GitHub stars~3.6k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

  • Zlibrary To Notebooklm

    zstmfhy/zlibrary-to-notebooklm

    自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式，自动转换，一键创建知识库。

    1.7k GitHub starsUsed in 1 repo~968 tokens
    Knowledge ManagementAuto-check passed

More from agenticnotetaking/arscontexta

All 25 skills in this repo

  • Graph

    agenticnotetaking/arscontexta

    Interactive knowledge graph analysis. An agent skill from agenticnotetaking/arscontexta.

    3.5k GitHub starsUsed in 1 repo~4.9k tokens
    Auto-check: notes

  • Learn

    agenticnotetaking/arscontexta

    Research a topic and grow your knowledge graph. An agent skill from agenticnotetaking/arscontexta.

    3.5k GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check: notes

  • Recommend

    agenticnotetaking/arscontexta

    Get research-backed architecture advice for your knowledge system.

    3.5k GitHub starsUsed in 1 repo~5.1k tokens
    Auto-check passed

  • Stats

    agenticnotetaking/arscontexta

    Show vault statistics and knowledge graph metrics. An agent skill from agenticnotetaking/arscontexta.

    3.5k GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check: notes

  • Next

    agenticnotetaking/arscontexta

    Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals.

    3.5k GitHub stars~4.9k tokensUpdated 7 mo ago
    Auto-check: notes

  • Pipeline

    agenticnotetaking/arscontexta

    End-to-end source processing -- seed, reduce, process all claims through reflect/reweave/verify, archive.

    3.5k GitHub stars~2.4k tokensUpdated 7 mo ago
    Auto-check: notes

Categories

Questions about Help

What does Help do?

Contextual guidance and command discovery. An agent skill from agenticnotetaking/arscontexta. Help is an agent skill from agenticnotetaking/arscontexta. Contextual guidance and command discovery.

When should I use Help?

Help fits situations like: how does this work.

How do I install Help in Claude Code?

Run `npx skills add agenticnotetaking/arscontexta --skill help -a claude-code`. Or copy the skill folder (skills/help in agenticnotetaking/arscontexta) into .claude/skills/help in your project. Claude Code loads it when a task matches its description.

How do I install Help in Codex?

Run `npx skills add agenticnotetaking/arscontexta --skill help -a codex`. Or copy the skill folder (skills/help in agenticnotetaking/arscontexta) into .agents/skills/help in your project. Codex loads it when a task matches its description.

Can I use Help in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agenticnotetaking/arscontexta --skill help -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/help, .gemini/skills/help, .github/skills/help and .opencode/skills/help in your project.

What does Help need to run?

SKILL.md names no scripts, command-line tools or credentials: Help is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash.

Does Help access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Help safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Help use?

Help is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Help use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Help?

Skills that share tags, products or a category with Help: Logseq Review Workflow Eval (logseq/logseq, 45k stars), Baoyu URL To Markdown (sdyckjq-lab/llm-wiki-skill, 2.5k stars), Obsidian CLI (Atmosphere/atmosphere, 3.8k stars) and Esm Cjs Risk Scan (logseq/logseq, 45k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Help?

agenticnotetaking (a GitHub organization) maintains it in agenticnotetaking/arscontexta, which has 3,492 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on February 24, 2026.

Source: agenticnotetaking/arscontexta on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.