contribute-knowledge-to-cogni
Contributes verified, durable knowledge to a central Cogni node hub.
Install
mkdir -p .claude/skills/contribute-knowledge-to-cogni && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16769" && unzip -o skill.zip -d .claude/skills/contribute-knowledge-to-cogni && rm skill.zipInstalls to .claude/skills/contribute-knowledge-to-cogni
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Umbrella skill for contributing durable knowledge to a Cogni node hub. Triggers when an agent has — or is about to research — context worth compounding for future agents/humans, AND the knowledge is durable enough to survive the syntropy bar. Routes to the right sub-skill by content shape (falsifiable prediction → `edo-loop`; visual for humans → `dolt-human-visuals`; AI-readable text → direct contribution). Use whenever you'd otherwise drop a research finding into a chat log or PR description that should outlive the session. RARE by design — most agent context dies with the session; only what compounds earns an entry.Key capabilities
- →contribute durable knowledge to a Cogni node hub
- →refine existing knowledge entries
- →cite relationships between atoms
- →write new atomic knowledge entries
- →route contributions by content shape
- →track work items with citations
How it works
The skill guides agents through a hierarchy of actions to contribute knowledge, prioritizing staying silent, recalling existing knowledge, refining, citing, and then writing new atomic entries, routing by content shape.
Inputs & outputs
When to use contribute-knowledge-to-cogni
- →Contribute research
- →Update knowledge base
- →Share findings
About this skill
Contribute durable knowledge
This file selects the contracts; the hub holds their maintained content.
Write in ASD-STE100 style: short active sentences, one idea each, plain words a 10-year-old knows, one meaning per term.
Read GET /api/v1/knowledge/knowledge-contribution-flow on the current node,
using its verified origin and saved COGNI_NODE_API_KEY. Read the full response
content, not only its index row. That guide owns recall of merged knowledge
and open inboxes, edit operations, citations, provenance, and human review.
| decision | read next |
|---|---|
| What are we trying to compound? | md-to-hub-design |
| Does this deserve durable knowledge? | knowledge-syntropy-protocol |
| Which registered domain owns it? | cogni-domain-taxonomy |
| How do repository docs, specs, or skills move into the hub? | migrate-markdown-to-hub and its required guides |
| Does it document an operator service that nodes use? | cogni-domain-taxonomy, then operator-service-index |
| Is this a prediction that resolves later? | edo-loop |
| Does visual structure help human review? | knowledge-human-visuals, then dolt-human-visuals |
Reuse the focused inbox for the existing work item; unrelated work gets its own inbox. A human reviews and merges knowledge. Verify the merged replacement, retrieval route, and consumers before removing a repository source.
If the hub is unavailable or an entry is missing, retain existing sources and record the failed gate. Do not register a fresh principal, silently change the target node, or invent the missing contract.
When not to use it
- →when context is ephemeral or routine work-item state
- →when an existing entry already covers the knowledge
- →when the contribution would create a new branch instead of appending
Limitations
- →requires one principal and one open contribution at a time
- →does not allow re-POSTing /contributions to avoid fracturing
- →new atoms should nearly always cite at least one existing entry
How it compares
This skill enforces a structured, hierarchical approach to knowledge contribution, emphasizing refinement and citation over creating new entries, which prevents knowledge sprawl compared to ad-hoc contributions.
Compared to similar skills
contribute-knowledge-to-cogni side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| contribute-knowledge-to-cogni (this skill) | 0 | 4mo | Caution | Advanced |
| qmd | 26 | 5mo | Review | Intermediate |
| deep-reading-analyst | 1 | 1y | No flags | Beginner |
| knowledge-base | 1 | 9mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by cogni-dao
View all by cogni-dao →You might also like
qmd
tobi
Search personal markdown knowledge bases, notes, meeting transcripts, and documentation using QMD - a local hybrid search engine. Combines BM25 keyword search, vector semantic search, and LLM re-ranking. Use when users ask to search notes, find documents, look up information in their knowledge base, retrieve meeting notes, or search documentation. Triggers on "search markdown files", "search my notes", "find in docs", "look up", "what did I write about", "meeting notes about".
deep-reading-analyst
ginobefun
Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems thinking, six thinking hats). Use when users want to: (1) deeply understand complex articles/content, (2) analyze arguments and identify logical flaws, (3) extract actionable insights from reading materials, (4) create study notes or learning summaries, (5) compare multiple sources, (6) transform knowledge into practical applications, or (7) apply specific thinking frameworks. Triggered by phrases like 'analyze this article,' 'help me understand,' 'deep dive into,' 'extract insights from,' 'use [framework name],' or when users provide URLs/long-form content for analysis.
knowledge-base
incidentfox
Search runbooks, documentation, and knowledge base articles from Confluence. Use when looking for incident response procedures, service documentation, post-mortems, or troubleshooting guides.
ask
Lambenthan
对 wiki 提问,综合检索相关页面后回答,好的回答可 crystallize 回 wiki
trace
Kingjinsight
Use when the user runs /trace [topic] or wants to see how an idea evolved over time across the vault. Tracks the arc of thinking on a specific topic.
search
V1CeVersaa
>-