New: 98,000+ 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

Knowledge Wiki Synthesis

by CatChen in CatChen/knowledge-wiki-template

Scan the wiki for cross-cutting connections, implicit relationships, contradictions, and gaps across concepts and summaries, then write synthesis concept files.

MITAuto-check passedKnowledge Management

Install Knowledge Wiki Synthesis

skills CLI
$ npx skills add CatChen/knowledge-wiki-template --skill knowledge-wiki-synthesis -a claude-code

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

GitHub CLI
$ gh skill install CatChen/knowledge-wiki-template knowledge-wiki-synthesis --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/CatChen/knowledge-wiki-template.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/knowledge-wiki-synthesis .claude/skills/knowledge-wiki-synthesis && 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
knowledge-wiki-synthesis
GitHub stars
106
Token cost
~1.9k tokens
SKILL.md length
710 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Scan the wiki for cross-cutting connections, implicit relationships, contradictions, and gaps across concepts and summaries, then write synthesis concept files.

  • Works in 7 steps: Establish the working directory → Find recently updated summaries → Load the concept list → …
  • The user wants to discover non-obvious connections
  • Calls node and git
  • Synthesize the knowledge base

What it does

Knowledge Wiki Synthesis is an agent skill from CatChen/knowledge-wiki-template. Scan the wiki for cross-cutting connections, implicit relationships, contradictions, and gaps across concepts and summaries, then write synthesis concept files. Use when the user wants to discover non-obvious connections, synthesize the knowledge base, or run a reflection pass after adding new content.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management, covering Knowledge bases. The licence is MIT.

When your agent uses it

  • The user wants to discover non-obvious connections
  • Synthesize the knowledge base
  • Run a reflection pass after adding new content

Example prompts

  • “/knowledge-wiki-synthesis”

Workflow steps

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

  1. Establish the working directory
  2. Find recently updated summaries
  3. Load the concept list
  4. Discover connection candidates
  5. Process each candidate
  6. Update state
  7. Print summary

What it can do on your machine

Read from SKILL.md and the folder at commit 77b9be8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Knowledge Wiki Synthesis loads about 1.9k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 710 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 passed

The automated check found no risky patterns in SKILL.md.

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 CatChen/knowledge-wiki-template at commit 77b9be8, republished under its MIT licence (© CatChen). 710 words, ~1,899 tokens.

Download SKILL.mdSave it as .claude/skills/knowledge-wiki-synthesis/SKILL.md (or your agent's skills folder).
name
knowledge-wiki-synthesis
description
Scan the wiki for cross-cutting connections, implicit relationships, contradictions, and gaps across concepts and summaries, then write synthesis concept files. Use when the user wants to discover non-obvious connections, synthesize the knowledge base, or run a reflection pass after adding new content.

Knowledge Wiki Synthesis

Discover non-obvious connections across the wiki and write synthesis concept files. Uses a two-phase process: a cheap index-scan to find candidates, then a targeted deep-read to synthesize each one.

Steps

1. Establish the working directory

The knowledge base root is the Git repository root. Run git rev-parse --show-toplevel and store the result as KNOWLEDGE_PATH.

Use KNOWLEDGE_PATH for all subsequent steps.

2. Find recently updated summaries

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-state.mjs find-unprocessed-summaries knowledge-wiki-synthesis

This outputs a JSON array of summary file paths (relative to KNOWLEDGE_PATH) whose summarized_at is newer than the last time this skill ran. On the first run (no prior state), it returns all summary files.

Store this list as RECENT_SUMMARIES. These paths are used as a priority signal in step 4 — candidates that involve at least one recent summary are ranked higher. They are not an exclusive filter; older summaries and concepts are still considered.

3. Load the concept list

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-index.mjs read-concepts > /tmp/wiki-concepts.md

Then read /tmp/wiki-concepts.md in full using the Read tool, using offset and limit to page through it if the file exceeds the Read tool's line limit. Do not pipe through head or any other truncating command — the concept list may be thousands of lines, and truncating it means missing potential synthesis candidates.

Each line is one concept entry in the form:

- [[Wiki/Concepts/{slug}|{Display Name}]] — {one-line description}
4. Discover connection candidates

Using only the one-line descriptions from step 3, identify 3–5 strong connection candidates. Look for:

TypeWhat to look for
cross-cuttingA theme that appears across multiple unrelated summaries or concepts
relationshipTwo or more concepts that seem deeply related but are not explicitly linked
contradictionTwo summaries or concepts that appear to take opposing positions on the same topic
gapA theme strongly implied by multiple entries but with no dedicated concept article

Priority: Rank higher any candidate that involves at least one entry from RECENT_SUMMARIES. If RECENT_SUMMARIES is empty (no summaries have been updated since the last run), use your judgment across the whole index.

Deduplication: Before proposing a candidate, check whether a concept file already exists at {KNOWLEDGE_PATH}/Wiki/Concepts/{proposed-slug}.md. Skip any candidate whose synthesis concept already exists.

For each candidate, record internally:

type: cross-cutting | relationship | contradiction | gap
concepts: [slug-a, slug-b, ...]
hypothesis: one sentence describing the connection
files_to_read: [full paths to concept and summary files — prioritize RECENT_SUMMARIES entries and their neighbors]
proposed_slug: lowercase-kebab-case slug for the new concept file
proposed_title: correctly-cased human-readable title

If fewer than 2 strong candidates are found, print:

Nothing strong enough to synthesize yet. Run again after adding more content.

And stop.

5. Process each candidate

For each candidate from step 4, run the following sub-steps in order.

5a. Read relevant articles

Read each file listed in files_to_read using the Read tool. If any file references additional concepts or summaries that seem directly relevant to the hypothesis, read those too. Maximum 8 files total per candidate.

5b. Evaluate synthesis quality

Assess whether the evidence from the files actually supports the hypothesis:

  • Strong evidence (2+ files directly support the connection) → proceed to 5c and 5d
  • Weak evidence (only superficial overlap) → note as skipped, do not write a file, continue to next candidate
Show full SKILL.md (275 more words)Show less
5c. Create the synthesis concept file

  1. Run:

    bash
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-concept.mjs create "{proposed_slug}" "{proposed_title}" --type Synthesis --icon notepad

    This creates Wiki/Concepts/{proposed_slug}.md. The command prints the file path.

  2. Read the file using the Read tool, then edit it to add:

    • Article body — insert between # {proposed_title} and ## Sources: 3–5 paragraphs of synthesis in American English. Explain the connection, relationship, contradiction, or gap clearly.
      • For connections: what do these concepts share, and why does it matter?
      • For relationships: how are they related, and what does understanding the relationship reveal?
      • For contradictions: what are the opposing positions, and what might explain the disagreement?
      • For gaps: what is the missing concept, and what would an article about it say? Write as a standalone reference — the reader has not read the source articles.
    • tags: [] — replace with relevant lowercase English tags. Use judgement; do not blindly copy all tags from the connected concepts.

  3. For each concept this synthesis draws from, add it to the Connected Concepts section (idempotent):

    bash
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-concept.mjs insert-connected-concept "{proposed_slug}" "{linked-slug}" "{Display Name}"

  4. For each source consulted, add its link (idempotent):

    bash
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-concept.mjs insert-source "{proposed_slug}" "{summary-path-without-md}"

    where {summary-path-without-md} is the summary file path with .md stripped, e.g. Wiki/Summaries/Posts/foo.summary.

For each {linked-slug} / {Display Name} pair added via insert-connected-concept in step 5c.3, back-link that concept's own file to the synthesis:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-concept.mjs insert-connected-concept "{linked-slug}" "{proposed_slug}" "{proposed_title}"

This appends - [[Wiki/Concepts/{proposed_slug}|{proposed_title}]] to the ## Connected Concepts section of each connected concept file, creating the section before ## Sources if it does not exist. The operation is idempotent.

5e. Update the index

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-index.mjs upsert-concept "{proposed_slug}" "{proposed_title}" "{one-line English description}"
6. Update state

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-state.mjs set-last-run knowledge-wiki-synthesis
7. Print summary
Synthesized {N} concept(s) from {M} candidate(s):

  ✓ Created: {proposed_slug} — {proposed_title}
      Type: {cross-cutting | relationship | contradiction | gap}
      Connects: {slug-a}, {slug-b}, ...

  ✗ Skipped: {hypothesis} (weak evidence)
      Files consulted: {list}

Suggested follow-up ingestion:
  - {topic} — referenced in {synthesis-slug} but no summary exists yet

Omit the "Suggested follow-up ingestion" section if there are no gaps.

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

Files

Just SKILL.md in .claude/skills/knowledge-wiki-synthesis of CatChen/knowledge-wiki-template.

Open the folder on GitHubat commit 77b9be8

Compare with similar skills

Knowledge Wiki Synthesis 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.

Knowledge Wiki Synthesis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Knowledge Wiki Synthesis this skillCatChen/knowledge-wiki-template106—~1.9kAutomated safety check: PassMIT
Capture Conversationoutline/outline41k—~474Automated safety check: PassCustom licence
Project CairniBlinkQ/project-cairn2352 repos~861Automated safety check: PassMIT
LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything86k1 repos~1.5kAutomated safety check: PassMIT
Find And Citeoutline/outline41k—~537Automated safety check: PassCustom licence
Xhs Virtual Productchenjin-cmd/xhs-virtual-product727—~862Automated safety check: PassMIT

Similar skills

  • Capture Conversation

    outline/outline

    Save the current conversation, a decision, or a set of notes as a document in an Outline collection; use when the user wants to keep what was discussed in their knowledge base.

    41k GitHub stars~474 tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Project Cairn

    iBlinkQ/project-cairn

    Standardize how an AI-collaboration project turns work into reusable knowledge.

    235 GitHub starsUsed in 2 repos~861 tokens
    Knowledge ManagementAuto-check passed

  • LLM Wiki Knowledge Graph

    Egonex-AI/Understand-Anything

    Detects a Karpathy-pattern LLM wiki and builds an interactive knowledge graph with entities, implicit relationships and topic clusters.

    86k GitHub starsUsed in 1 repo~1.5k tokens
    Knowledge ManagementAuto-check passed

  • Find And Cite

    outline/outline

    Answer questions from the Outline knowledge base with quotes and links to the source documents; use when the user asks what the team knows, documented, or decided about a topic.

    41k GitHub stars~537 tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Xhs Virtual Product

    chenjin-cmd/xhs-virtual-product

    This skill helps plan, select, produce, and market Xiaohongshu (RED) virtual/digital products — templates, knowledge bases, test tools, study materials.

    727 GitHub stars~862 tokensUpdated 7 days ago
    Knowledge ManagementAuto-check passed

  • Openkb

    VectifyAI/OpenKB

    A skill your agent uses when the user asks about content in their OpenKB knowledge base — research topics, concepts compiled from their documents, cross-document synthesis — or mentions openkb, an…

    4.7k GitHub starsUsed in 1 repo~2k tokens
    Knowledge ManagementAuto-check: warnings

More from CatChen/knowledge-wiki-template

  • Knowledge Wiki Concept

    CatChen/knowledge-wiki-template

    Create or update wiki concept files from knowledge base summaries.

    106 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

  • Knowledge Wiki Summary

    CatChen/knowledge-wiki-template

    Generate or refresh wiki summaries for knowledge base markdown files.

    106 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed

  • Knowledge Wiki Cluster

    CatChen/knowledge-wiki-template

    Find groups of concepts that share an implied parent slug and handle them: if the parent does not exist, create it; if it already exists, link unconnected children to it.

    106 GitHub stars~5k tokensUpdated 3 mo ago
    Auto-check passed

  • Knowledge Wiki Enrich

    CatChen/knowledge-wiki-template

    Expand thin concept articles in the knowledge wiki using web search.

    106 GitHub stars~636 tokensUpdated 3 mo ago
    Auto-check passed

  • Knowledge Wiki Lint

    CatChen/knowledge-wiki-template

    Audit and repair the knowledge wiki. An agent skill from CatChen/knowledge-wiki-template.

    106 GitHub stars~3.5k tokensUpdated 3 mo ago
    Auto-check passed

  • Knowledge Wiki Merge

    CatChen/knowledge-wiki-template

    Interactively find and merge duplicate concept files in the knowledge wiki.

    106 GitHub stars~2.6k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Knowledge Wiki Synthesis

What does Knowledge Wiki Synthesis do?

Scan the wiki for cross-cutting connections, implicit relationships, contradictions, and gaps across concepts and summaries, then write synthesis concept files. Knowledge Wiki Synthesis is an agent skill from CatChen/knowledge-wiki-template. Scan the wiki for cross-cutting connections, implicit relationships, contradictions, and gaps across concepts and summaries, then write synthesis concept files.

When should I use Knowledge Wiki Synthesis?

Knowledge Wiki Synthesis fits situations like: the user wants to discover non-obvious connections; synthesize the knowledge base; run a reflection pass after adding new content.

How do I install Knowledge Wiki Synthesis in Claude Code?

Run `npx skills add CatChen/knowledge-wiki-template --skill knowledge-wiki-synthesis -a claude-code`. Or copy the skill folder (.claude/skills/knowledge-wiki-synthesis in CatChen/knowledge-wiki-template) into .claude/skills/knowledge-wiki-synthesis in your project. Claude Code loads it when a task matches its description.

How do I install Knowledge Wiki Synthesis in Codex?

Run `npx skills add CatChen/knowledge-wiki-template --skill knowledge-wiki-synthesis -a codex`. Or copy the skill folder (.claude/skills/knowledge-wiki-synthesis in CatChen/knowledge-wiki-template) into .agents/skills/knowledge-wiki-synthesis in your project. Codex loads it when a task matches its description.

Can I use Knowledge Wiki Synthesis 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 CatChen/knowledge-wiki-template --skill knowledge-wiki-synthesis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/knowledge-wiki-synthesis, .gemini/skills/knowledge-wiki-synthesis, .github/skills/knowledge-wiki-synthesis and .opencode/skills/knowledge-wiki-synthesis in your project.

What does Knowledge Wiki Synthesis need to run?

Going by SKILL.md and its folder, Knowledge Wiki Synthesis needs the command-line tools its instructions call (node and git).

Does Knowledge Wiki Synthesis access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Knowledge Wiki Synthesis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Knowledge Wiki Synthesis use?

Knowledge Wiki Synthesis 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 Knowledge Wiki Synthesis use?

About 1.9k tokens (SKILL.md is roughly 7.6k 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 Knowledge Wiki Synthesis?

Skills that share tags, products or a category with Knowledge Wiki Synthesis: Capture Conversation (outline/outline, 41k stars), Project Cairn (iBlinkQ/project-cairn, 235 stars), LLM Wiki Knowledge Graph (Egonex-AI/Understand-Anything, 86k stars) and Find And Cite (outline/outline, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Knowledge Wiki Synthesis?

CatChen (a GitHub user) maintains it in CatChen/knowledge-wiki-template, which has 106 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on June 24, 2026.

Source: CatChen/knowledge-wiki-template on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.