Automated summary
Captures key takeaways from the current session and writes a note to a Thinking log, auto-detecting whether the session was research/exploration or a decision.
Strengths
- Automatic classification of session type (research or decision)
- Structured templates for each type (decision with alternatives, research with open questions)
- Organized saving into work/personal directories
- Quick mode for abbreviated capture
Limitations
- May misclassify ambiguous sessions (requires user confirmation)
- Depends on analyzing the entire conversation, not suitable for multi-part sessions
- Only works in Claude Code environment
When you want to log key takeaways from a research or decision session for later reference.
When you need a free-form note without structured templates, or the session is trivial.
Security analysis
SafeThe skill only instructs writing structured markdown notes to user-specific directories (~/SecondBrain/...). No destructive commands, no network calls, no exfiltration, no obfuscation. It's purely for local note-taking.
No concerns found
How this analysis is madeExamples
/done/done quick/done researchCapture session notes to Thinking log
v2 — Research & decision capture
Captures key takeaways from the current session and writes a note to a Thinking log. Auto-detects whether the session was research/exploration or a decision, and uses the appropriate template.
Setup
By default, notes are saved to separate work and personal directories inside ~/SecondBrain/:
- Work →
~/SecondBrain/2Work/Thinking/ - Personal →
~/SecondBrain/1Personal/Thinking/
The skill classifies each session as work or personal and saves to the appropriate directory.
Arguments
$ARGUMENTS can include (in any order):
- (none) — auto-detect type, full capture
quick— abbreviated capture (skip Open Questions, Follow-ups, and Context/Source sections)research— force research templatedecision— force decision template
Examples: /done, /done quick, /done research, /done decision quick
Instructions
Step 1: Determine Session Type
If $ARGUMENTS contains research or decision, use that template.
Otherwise, analyze the conversation to auto-detect:
- Decision — the session contains an explicit choice between options, a comparison that led to a conclusion, or a commitment to a specific course of action. Look for: "go with X", "decided on", choosing between alternatives, weighing pros/cons with a winner.
- Research — the session contains exploration, synthesis, learning, or analysis without converging on a binary choice. Look for: investigating a topic, reading/summarizing content, understanding how something works, gathering information.
- Mixed — if the session contains both research and a decision, prefer the Decision template. The research naturally becomes the Context and Rationale sections.
- Genuinely ambiguous — ask the user: "This session had both research and decision elements. Should I capture this as a decision or research note?"
Step 2: Determine Output Directory
Classify the session topic to decide where the note is saved:
- Work →
~/SecondBrain/2Work/Thinking/— directly related to your job, company, product, engineering, hiring, customers, etc. - Personal →
~/SecondBrain/1Personal/Thinking/— everything else (personal research, family, investments, health, side projects, general knowledge, etc.)
Step 3: Extract Content
Review the full conversation and extract the relevant content for the detected template.
For Decision sessions, extract:
- The decision itself (clear, bold statement)
- Context that led to the decision
- Rationale (why this choice wins)
- Alternatives considered (and why they lost)
- Action items / next steps
- Sources (emails, documents, links, conversations referenced)
For Research sessions, extract:
- A 1-2 sentence summary of what was researched and why
- Key findings — the substantive takeaways. Be flexible with format: use prose paragraphs for nuanced points, bullet lists for enumerations, sub-headings (
###) for distinct sub-topics, and blockquotes for exact quotes or citations. Match the format to the content. - Open questions — unresolved items raised but not answered
- Follow-ups — concrete next actions (as checkboxes)
- Sources — documents, links, emails, or conversations referenced
Important: Only include sections that have real content. Never write "None", "None created", "N/A", or leave a section empty. If there are no open questions, omit the Open Questions section entirely.
Step 4: Write the Note
Create a new file in the output directory named: YYYY-MM-DD - Topic Name.md
Use Title Case with spaces for the topic name (e.g., 2026-02-24 - EV Charging Selection.md, 2026-02-26 - Trust Signing Authority Research.md).
If a file with the same name already exists, append a number: 2026-02-26 - Topic Name 2.md
Decision Template
**Decision:** [Clear statement of what was decided]
**Context:**
- [Relevant background point]
- [Relevant background point]
**Rationale:**
- [Why this choice wins — specific, concrete reasons]
- [Why this choice wins]
**Alternatives Considered:**
- [Alternative 1]: [Why it wasn't chosen]
- [Alternative 2]: [Why it wasn't chosen]
**Action:** [Next step(s) — who does what]
**Source:** [Where the information came from — emails, docs, links, conversations]
Research Template
# [Topic Name]
**Summary:** [1-2 sentence summary of what was researched and the key takeaway]
## Key Findings
[Flexible format. Use whatever structure best fits the content:
- Prose paragraphs for nuanced analysis
- Bullet points for lists of facts
- Sub-headings (###) for distinct sub-topics
- Blockquotes (>) for exact quotes or citations
- Combinations of all of the above]
## Open Questions
- [Unresolved question 1]
- [Unresolved question 2]
## Follow-ups
- [ ] [Concrete next action 1]
- [ ] [Concrete next action 2]
## Sources
- [Source 1 — document path, URL, email thread, etc.]
Quick Mode
For quick captures, use abbreviated versions:
Quick Decision — include only: Decision, Rationale (2-3 bullets max), and Action. Skip Context, Alternatives, and Source.
Quick Research — include only: the # title, Summary, and Key Findings (condensed to the most important 3-5 points). Skip Open Questions, Follow-ups, and Sources.
Step 5: Confirm
Display a brief confirmation:
CAPTURED: [Topic Name]
Type: [Decision/Research]
Saved to: [directory]/[filename].md
If there are follow-ups, add:
Next: [Most important follow-up item]
Error Handling
- No substantive content: If the session was just a quick lookup or greeting, report: "Nothing to capture — session was too brief."
- File write fails: Display the full note content in the terminal so it can be manually saved.
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/session-note-capture-to-thinking-log-mrwakc78/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/session-note-capture-to-thinking-log-mrwakc78' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/session-note-capture-to-thinking-log-mrwakc78/download' --output '.skill-downloads/session-note-capture-to-thinking-log-mrwakc78/SKILL.md.part' && mv '.skill-downloads/session-note-capture-to-thinking-log-mrwakc78/SKILL.md.part' '.skill-downloads/session-note-capture-to-thinking-log-mrwakc78/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.
Original excerpt: Setup
By default, notes are saved to separate work and personal directories inside ~/SecondBrain/:
- Work →
~/SecondBrain/2Work/Thinking/ - Personal →
~/SecondBrain/1Personal/Thinking/
The skill classifies each session as work or personal and saves to the appropriate directory.
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
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual 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/session-note-capture-to-thinking-log-mrwakc78/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.
PDF Reader
Productivity
Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.
Discord Messaging Workflows
Productivity
Use the message tool to send, edit, and moderate Discord messages with interactive components.
Interactive Verdict Preview
Productivity
Generate an interactive HTML preview of keep/drop verdicts for maintainer review, then process the pasted feedback JSON.