AgentStack
SKILL verified MIT Self-run

Update Memory

skill-aksheyw-career-command-center-template-update-memory · by aksheyw

Log what worked (or didn't) to improve future applications. Argument: [company] [outcome] [what worked / what to change]

No reviews yet
0 installs
2 views
0.0% view→install

Install

$ agentstack add skill-aksheyw-career-command-center-template-update-memory

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Update Memory? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.