meditation
Skill0 starsChanged 4 months agoMITView on GitHub
Consolidate session learning into permanent architecture — extract patterns into skills, instructions, prompts, or memory
2 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- fabioc-aloha/Alex_Skill_Malledited, first seen Aug 1, 2026
- fabioc-aloha/alex-cognitive-architecturetheir own version, first seen Apr 26, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- fabioc-aloha/Alex_Skill_Mall★ 572% same
Wrote their own version · 1
- fabioc-aloha/alex-cognitive-architecture★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository38 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- agent-creatorSkill
- agent-reviewSkill
- ai-memory-setupSkill
- alex-banner-generationSkill
- anti-hallucinationSkill
- brain-auditSkill
- browser-toolsSkill
- code-reviewSkill
- creative-writingSkill
- critical-thinkingSkill
- deep-reviewSkill
- doc-hygieneSkill
- docx-to-mdSkill
- git-workflowSkill
- greeting-checkinSkill
- html-to-mdSkill
- humanizerSkill
- instruction-creatorSkill
- instruction-reviewSkill
- lint-clean-markdownSkill
- markdown-mermaidSkill
- markdown-sanitization-chainSkill
- md-to-emlSkill
- md-to-htmlSkill
- md-to-txtSkill
- md-to-wordSkill
- planSkill
- problem-framing-auditSkill
- prompt-creatorSkill
- prompt-reviewSkill
- security-and-hardeningSkill
- skill-creatorSkill
- skill-reviewSkill
- spikeSkill
- status-reportingSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
After solving a hard problem with a reusable insight
- Distinctive: line 18
Before a long break from a project
- Very specific: line 56
If the session arc was substantial, write to .github/episodic/meditation-YYYY-MM-DD-<topic>.md:
- Very specific: line 81
If the user is closing the thread, write to repo-root HANDOFF.md:
≈ “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
<!-- intentional divergence from Supervisor: Edition omits the "Brain Retraining (longer cycles)" section and Cardinal Rule 3 audit criteria — those govern Supervisor's curation cadence (weekly brain-qa, quarterly retraining ADRs) which heirs don't run. Edition also generalizes the script-location rows (heirs may not have a `scripts/` root). Audited 2026-05-31. -->Meditation
Transform session insights into durable knowledge. Most sessions don't need it; some have a pattern worth keeping.
When to Fire
- User says "let's meditate", "consolidate", or invokes
/meditate - End of a significant work session
- After solving a hard problem with a reusable insight
- Before a long break from a project
Skip when: the session was routine execution of patterns already encoded. Meditation on every session produces noise; the discipline is to write only what's new and portable.
The Five Steps
1. Review
Scan the session honestly:
- What problems did we solve?
- What mistakes did we make?
- What patterns emerged that weren't already encoded?
- What would help future sessions?
2. Extract
Separate signal from noise. For each candidate pattern, ask: "Is this already covered by an existing skill, instruction, or memory?" If yes, skip. If no, route by type:
| If pattern is... | Create / update |
| Reusable domain knowledge | Skill (.github/skills/<name>/SKILL.md) |
| Always-on behavior or rule | Instruction (.github/instructions/<name>.instructions.md) |
| Repeatable workflow / slash command | Prompt (.github/prompts/<name>.prompt.md) |
| Automatable task tied to one skill | Script in that skill's folder (.github/skills/<skill>/scripts/<name>.cjs) |
| Cross-cutting automation | Script (.github/scripts/<name>.cjs) |
| User preference (cross-project) | User memory (/memories/<name>.md) |
| Project / repo convention | Repo memory (/memories/repo/<name>.md) |
| Cross-session handoff (next session needs to know) | Repo file (HANDOFF.md at repo root) — NOT session memory |
3. Write
Each artifact gets correct frontmatter, concrete examples (not abstractions), and tables with real data. Avoid the "capabilities list" anti-pattern — describe behavior, not features.
For skills and instructions: include a Trigger or When to fire section so future sessions know when the pattern applies.
4. Chronicle (optional)
If the session arc was substantial, write to .github/episodic/meditation-YYYY-MM-DD-<topic>.md:
# Meditation: <Topic>
**Date**: YYYY-MM-DD
**Focus**: What we worked on
## Accomplished
- [Key outcomes]
## Patterns Extracted
- [What became skills / instructions / memory]
## Lessons
- [Insights worth remembering]
## Open Questions
- [What remains unresolved]Skip the chronicle for short sessions or when nothing new emerged.
5. Handoff (when ending a session)
If the user is closing the thread, write to repo-root HANDOFF.md:
# Session Handoff
Last updated: YYYY-MM-DD HH:MM
## Just shipped
- [SHAs / files / outcomes]
## In progress
- [Specific next step + file paths]
## Pending queue
- [ ] [Ordered todos]
## Resume point
- [Where to pick up]Quality Bar
A meditation is complete when:
- New patterns are persisted, not just acknowledged
- Nothing important lives only in the context window
- Existing artifacts were checked for duplication before writing new ones
- The session can be closed without losing the thread
Anti-Patterns
| Anti-pattern | Correction |
| Writing a meditation note for every session | Most sessions are routine execution; only write when something new emerged |
| Duplicating an existing skill / memory under a new name | Always grep first: is this already covered? |
| Aspirational notes ("we should do X someday") | Memory is for what was learned, not what was wished |
| Long prose chronicles when a one-line memory suffices | Match artifact size to insight size |
| Skipping the duplication check to "just capture it" | Adds noise that the next session has to filter |
Related
- meditation.instructions.md — when this skill fires
- /meditate prompt — slash-command entry
- memory-triggers.instructions.md — automatic triggers between meditations
Falsifiability
- This skill adds no value if meditation sessions produce no actionable items (skill extractions, pattern recognitions, or architecture insights) over a 90-day window
- The protocol is wrong if chronicles written per this format are never consulted in future sessions
- Stale if the memory tier structure changes and this skill references obsolete storage locations
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.