update-memory
Skill1 starsChanged 4 months agoMITView on GitHub
Log what worked (or didn't) to improve future applications. Argument: [company] [outcome] [what worked / what to change]
5 other projects use a version of this.
Adopted by
Most recently taken up by
- lumpcode/lumpcodetheir own version, first seen Nov 1, 2026
- cerredz/vidbyte-memorytheir own version, first seen Nov 1, 2026
- madeordinary/serel-memorytheir own version, first seen Oct 9, 2026
- zhiyuzi/Signextheir own version, first seen Feb 27, 2026
- cogotemartinez/ai-second-brain-templatetheir own version, first seen Feb 11, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- zhiyuzi/Signex★ 98same name
- lumpcode/lumpcode★ 12same name
- cogotemartinez/ai-second-brain-template★ 9same name
- cerredz/vidbyte-memory★ 2same name
- madeordinary/serel-memory★ 1same 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 repository11 other files it gives its agents.
- applySkill
- evaluateSkill
- followupSkill
- generic-letterSkill
- humanizerSkill
- interviewSkill
- outreachSkill
- patternsSkill
- resume-customizerSkill
- salary-negotiateSkill
- track-applicationSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
3
Distinctive
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
- Very specific: line 10
Read ${CLAUDE_PLUGIN_ROOT}/references/CUSTOMIZATION_MEMORY.md fully (the user's real, git-ignored file).
- Distinctive: line 14
Ask the user (or extract from their input):
- Very specific: line 34
Write the updated CUSTOMIZATION_MEMORY.md to ${CLAUDE_PLUGIN_ROOT}/references/CUSTOMIZATION_MEMORY.md.
- Distinctive: line 36
Add the new entry under the correct company-type section.
- Distinctive: line 44
After updating, analyze across all logged applications:
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are updating the customization memory — the learning log that makes every future application smarter.
STEP 1: Read the current memory file
Read ${CLAUDE_PLUGIN_ROOT}/references/CUSTOMIZATION_MEMORY.md fully (the user's real, git-ignored file). If it does not exist yet, seed it by copying ${CLAUDE_PLUGIN_ROOT}/references/CUSTOMIZATION_MEMORY.example.md to that path first. Understand the existing patterns before adding anything.
STEP 2: Gather information
Ask the user (or extract from their input):
- Which company and role?
- What was the outcome? (Resume screen passed / rejected / screened / interviewed / offered)
- What resume strategy was used? (Which company-type template?)
- What was the cover letter hook?
- Was there a referral involved?
- For rejections: any feedback or signal about why?
- For successes: what specific framing or metric seemed to resonate?
STEP 3: Identify the learning
Based on the outcome, generate a specific, actionable learning:
- NOT "good resume" — say WHAT specifically seemed to work
- NOT "bad fit" — say which framing missed the mark
- Connect to company-type patterns already in the file
STEP 4: Update the file
Write the updated CUSTOMIZATION_MEMORY.md to ${CLAUDE_PLUGIN_ROOT}/references/CUSTOMIZATION_MEMORY.md.
Add the new entry under the correct company-type section. Update:
- "Successful Customizations" if outcome was positive
- "Unsuccessful Patterns" if outcome was negative or no response
- "Screen Rate" with the updated percentage if calculable
STEP 5: Surface patterns
After updating, analyze across all logged applications:
- Which company types are yielding screens?
- Which cover letter hooks got the most traction?
- Which resume strategies need improvement?
- Are there any keywords or framings that appear in multiple successful applications?
Output a brief "What We Know So Far" summary with 3-5 actionable insights.
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.