Automated summary
Displays the current state of a project's knowledge base and recent learnings extracted by the AI.
Strengths
- Provides a quick overview of accumulated knowledge
- Shows learning mode status and per-category statistics
- Lists the last 5 entries for immediate insight
Limitations
- Only works if knowledge files exist and are in the expected format
- Read-only; does not modify the knowledge base
- Relies on frontmatter entry counts or header parsing
When you want to check what the AI has learned about the project or the status of learning mode.
When you want to extract new knowledge (use /learn instead).
Security analysis
SafeThe skill only reads local project files (knowledge/state.json and markdown files) and displays formatted information. It does not execute any commands, write files, or communicate externally, posing no security risk.
No concerns found
How this analysis is madeExamples
What has the AI learned about this project? Show the knowledge base status.Is learning mode on? Show me the knowledge base.Show me the most recent learnings and decisions from the knowledge base.name: knowledge description: Display knowledge base status and recent learnings user_invokable: true
Knowledge
Display the current state of the project's knowledge base and recent learnings.
What This Does
Shows:
- Learning mode status (on/off)
- Knowledge base statistics (entry counts per category)
- Recent learnings extracted
Instructions
- Read
knowledge/state.jsonfor learning mode status - Read each knowledge file and count entries:
knowledge/learnings/patterns.mdknowledge/learnings/quirks.mdknowledge/learnings/decisions.md
- Extract recent entries (last 5) from learnings files
- Format and display
Output Format
+---------------------------------------------------+
| Project Knowledge Base |
+---------------------------------------------------+
Learning Status
---------------------------------------------------
Mode: ON (since 2026-01-08 14:00)
Last Extraction: 5 minutes ago
Extractions This Session: 3
** Remember to run /learn before ending your session **
Knowledge Statistics
---------------------------------------------------
Learnings:
- Patterns: 8 entries
- Quirks: 3 entries
- Decisions: 5 entries
- Total: 16 insights
Recent Learnings
---------------------------------------------------
[Pattern] "Use async/await for API calls in this codebase"
Discovered: 2026-01-08 | Confidence: high
[Quirk] "Auth module uses non-standard token format"
Discovered: 2026-01-07 | Confidence: high
[Decision] "Chose Redis over in-memory cache for session storage"
Made: 2026-01-06 | Confidence: high
Commands
---------------------------------------------------
/learn - Extract insights now
/learn-on - Enable learning mode reminder
/learn-off - Disable learning mode reminder
When Knowledge Base is Empty
+---------------------------------------------------+
| Project Knowledge Base |
+---------------------------------------------------+
Learning Status
---------------------------------------------------
Mode: OFF
No extractions yet
Knowledge Statistics
---------------------------------------------------
Knowledge base is empty.
Get Started
---------------------------------------------------
Use /learn to extract insights from your current session.
Use /learn-on to enable learning mode.
The knowledge base will grow as you work, capturing:
- Patterns that work well in this project
- Quirks and gotchas to remember
- Decisions and their rationale
Steps
- Read
knowledge/state.json - Read frontmatter from each knowledge file to get entry counts
- Parse recent entries from learnings files (look for
## Pattern:,## Quirk:,## Decision:headers) - Format and display the summary
- If files are missing or empty, show the "empty" state
Notes
- Entry counts come from frontmatter
entry_countfield or by counting##headers - Recent learnings are shown most recent first (by discovered/made date)
- This is a read-only command - it doesn't modify any files
- When learning mode is ON, show a reminder to run /learn before ending the session
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/knowledge-base-display-mmio71e7/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/knowledge-base-display-mmio71e7' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/knowledge-base-display-mmio71e7/download' --output '.skill-downloads/knowledge-base-display-mmio71e7/SKILL.md.part' && mv '.skill-downloads/knowledge-base-display-mmio71e7/SKILL.md.part' '.skill-downloads/knowledge-base-display-mmio71e7/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/knowledge-base-display-mmio71e7/SKILL.md' && test -s '.skill-downloads/knowledge-base-display-mmio71e7/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/knowledge' && cp -R '.skill-downloads/knowledge-base-display-mmio71e7' '.claude/skills/knowledge'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/knowledge-base-display-mmio71e7'openskills read 'knowledge-base-display-mmio71e7'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/knowledge-base-display-mmio71e7/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.