weekly-reflecting
Skill0 starsChanged 7 months agoMITView on GitHub
Friday depth test from memory. Triggers on /reflect, weekly reflection, or friday reflection. The student writes answers from memory with NO code lookup allowed. Gaps in writing equal gaps in understanding. Connects to spaced review deck, trend scout, and system check for a complete weekly audit.
In this repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adr-captureSkill
- adversarial-reviewSkill
- architect-firstSkill
- blog-draftingSkill
- brainstorming-knowledge-builderSkill
- code-reviewingSkill
- session-startSkill
- debug-systemsSkill
- evolution-logSkill
- faang-loop-simulationSkill
- learn-in-publicSkill
- mock-assessingSkill
- os-lensSkill
- partner-systemSkill
- progress-updatingSkill
- review-systemsSkill
- spaced-reviewingSkill
- system-checkingSkill
- systems-traceSkill
- trend-scoutingSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 38
Run /review-deck -- any struggling concepts this week?
- Very specific: line 39
Run /trends -- anything relevant from the industry this week?
- Very specific: line 40
Run /system-check -- is the learning system itself working?
- Distinctive: line 48
NO CODE LOOKUP during reflection.
- Distinctive: line 49
If the student reaches for code to answer a question, stop them.
≈ “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
Weekly Reflection -- Friday Depth Test
Gaps in writing = gaps in understanding. Written from MEMORY. No code lookup.
Trigger
/reflector "weekly reflection" or "friday reflection"- End of each week (Friday)
Execution
- Read ROADMAP.md for current topic and exercise. DO NOT read any code files.
- Prompt the student to write FROM MEMORY (no lookup):
WEEKLY REFLECTION 1. What did you build since the last reflection? (list each session's work) 2. What concept clicked that didn't before? 3. What was the hardest thing? Why? 4. Explain ONE concept you learned as if teaching a junior dev. 5. What would you do differently if you started over? 6. What's your plan for the coming sessions? - Challenge the answers:
- Vague explanation → "What actually happens under the hood?"
- Missed sessions → "What happened between session X and Y?"
- Everything sounds easy → "If nothing was hard, you weren't pushing enough."
- Concept explanation is shallow → "A junior dev would ask: why? What would you say?"
- Cross-reference with other skills:
- Run
/review-deck-- any struggling concepts this week? - Run
/trends-- anything relevant from the industry this week? - Run
/system-check-- is the learning system itself working?
- Run
- Ask the student to commit reflection to
reflections/reflection-{N}.md - Identify concepts to add or update in the spaced review deck.
Rules
- NO CODE LOOKUP during reflection. This tests internalized knowledge.
- If the student reaches for code to answer a question, stop them. Memory only.
- Friday reflection is non-negotiable. Low-energy Friday → shorter reflection, not no reflection.
- The reflection file itself becomes a learning artifact -- quality matters.
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.

