save-insight
Skill509 starsChanged 3 months agoMITView on GitHub
Capture a reusable learning from completed work so future similar work is easier. Use when the user says 'save this learning', 'capture this insight', or finishes something tricky. Also use proactively after non-routine work. Not for recording a *decision* and its rationale; use `decision-log`.
In this repository153 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .claude/plugins/compound-engineering/CLAUDE.mdCLAUDE.md
- .cursor/rules/search-routing.mdcCursor rule
- anthropic-algorithmic-artSkill
- anthropic-brand-guidelinesSkill
- anthropic-doc-coauthoringSkill
- anthropic-docxSkill
- anthropic-frontend-designSkill
- anthropic-internal-commsSkill
- anthropic-mcp-builderSkill
- anthropic-pptxSkill
- anthropic-slack-gif-creatorSkill
- anthropic-theme-factorySkill
- anthropic-webapp-testingSkill
- anthropic-web-artifacts-builderSkill
- anthropic-xlsxSkill
- atlassian-setupSkill
- backup-nowSkill
- backup-restoreSkill
- backup-setupSkill
- calendar-setupSkill
- commitmentsSkill
- create-mcpSkill
- daily-planSkill
- daily-reviewSkill
- decision-logSkill
- delegate-checkSkill
- dex-backlogSkill
- dex-doctorSkill
- dex-improveSkill
- dex-obsidian-setupSkill
- dex-rollbackSkill
- dex-updateSkill
- dex-whats-newSkill
- diff-profileSkill
- enable-semantic-searchSkill
- getting-startedSkill
- goal-backlogSkill
- google-workspace-setupSkill
- granola-setupSkill
- identity-snapshotSkill
- industry-truthsSkill
- initiative-kickoffSkill
- integrate-mcpSkill
- journalSkill
- manage-capabilitiesSkill
- meeting-closeoutSkill
- meeting-prepSkill
- ms-teams-setupSkill
- pipedrive-setupSkill
- pipeline-syncSkill
- process-meetingsSkill
- product-briefSkill
- project-healthSkill
- prompt-improverSkill
- relationship-radarSkill
- reviewSkill
- scrapeSkill
- skill-scoreSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Ask the user (or extract from recent work context):
- Distinctive: line 44
Create new category files as needed for domain-specific learnings.
- Distinctive: line 70
If the learning relates to:
- Distinctive: line 77
Ask reflection questions (or extract from context)
- Distinctive: line 78
Create/update the appropriate learning file
- Very specific: line 97
Call track_event with event_name insight_saved and properties:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- Generated from `.claude/skills/save-insight/SKILL.md` by `scripts/generate-agents-skills.py`. Do not edit. -->Capture what you learned from completing work. This is the "compound" step—making future similar work easier.
Arguments
$WORK_COMPLETED: What did you just complete? (project milestone, tricky problem, meeting, workflow improvement, etc.)
Process
1. Reflection Questions
Ask the user (or extract from recent work context):
- What was the situation?
- Original goal or challenge
- Why it was harder than expected (if applicable)
- What approach worked?
- Strategy or tactic used
- Key decisions made
- What would you do differently?
- Gotchas encountered
- Better approaches discovered late
- What's reusable?
- Patterns that apply elsewhere
- Mental models that help
2. Create or Update Learning Note
Store in: 06-Resources/Learnings/[Category]_Learnings.md
Categories:
Working_Preferences- How you like to work, communication style, tool preferencesMistake_Patterns- Common errors to avoid, with triggers and corrections
Create new category files as needed for domain-specific learnings.
3. Learning Entry Format
Append to the appropriate file:
---
## [Short Title] — [Date]
**Context:** [1 sentence on what you were doing]
**Challenge:** [What was tricky or non-obvious]
**What Worked:**
[The approach that succeeded]
**Key Insight:**
> [The memorable takeaway—something you'd tell past-you]
**See Also:** [Related notes if any]4. Cross-Link (Optional)
If the learning relates to:
- A person → Add to their person page
- A project → Add link in project's note
- A recurring workflow → Update relevant template
Output
- Ask reflection questions (or extract from context)
- Create/update the appropriate learning file
- Suggest any cross-links
- Confirm saved
Philosophy
"The palest ink is better than the best memory." — Chinese proverb
This isn't documentation for others—it's a gift to future-you. Be specific. Include the gotcha. Make it searchable.
Track Usage (Silent)
Call the mark_feature_used tool on the dex-analytics MCP server with save-insight. This ticks the feature's box in System/usage_log.md, which is what /dex-level-up reads to recommend features that have not been tried. It writes locally and sends nothing, so it runs whether or not analytics is enabled.
Analytics (Silent):
Call track_event with event_name insight_saved and properties:
- category
This only fires if the user has opted into analytics. No action needed if it returns "analytics_disabled".
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

