kevin-mok/feedback-memory
dot_agents/skills/feedback-memory/SKILL.md
Persist durable user corrections and preferences across sessions through a repo-tracked plain-text `feedback.log`. Use when starting a session that should honor prior reusable feedback, or when the user gives durable guidance about workflow, formatting, style, tooling, review expectations, or communication that should apply again later.
tools
Updated May 5, 2026
$ install --global
skillsauthnpx skillsauth add kevin-mok/ai-cli-dotfiles feedback-memoryInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 5, 2026, 8:33 AM118.9s2 files scanned
SKILL.md
- name:
- feedback-memory
- description:
- Persist durable user corrections and preferences across sessions through a repo-tracked plain-text `feedback.log`. Use when starting a session that should honor prior reusable feedback, or when the user gives durable guidance about workflow, formatting, style, tooling, review expectations, or communication that should apply again later.
Feedback Memory
Purpose
Carry forward reusable user feedback across sessions with one canonical append-only log.
Log Path
Use this resolution order:
- Prefer
~/linux-config/dot_agents/skills/feedback-memory/feedback.logwhen it exists. In this chezmoi-managed setup, that is the canonical log because~/linux-configis the source state. - Otherwise, fall back to
feedback.login this installed skill folder. - If both files exist, read and append only the repo-tracked path.
When to use
Use this skill when:
- starting a session and prior durable feedback may matter
- the user gives a correction or preference that should change future behavior
- the feedback is about workflow, style, formatting, review expectations, tooling habits, or communication
When not to use
Do not log:
- task-specific instructions tied to the current ticket, branch, file, or investigation
- one-off requests or temporary preferences
- ephemeral facts that will age out quickly
- details that duplicate the current task context instead of generalizing beyond it
Required workflow
- Resolve the canonical log path using the rules above.
- Before doing anything else in the session, read the canonical
feedback.log. - Treat the log as durable operating guidance. Apply it throughout the session unless the user overrides it explicitly.
- When the user gives new durable feedback, append it to the canonical log immediately before continuing.
- Do not create, update, or reconcile a second log when the repo-tracked path exists.
- Keep the file append-only. Do not rewrite, reformat, dedupe, or move old entries unless the user explicitly asks.
- If the feedback is ambiguous, log only the durable part that would still help in a different future task.
What to log
Log reusable notes such as:
- formatting and response-style preferences
- review expectations and quality bars
- tooling habits or workflow preferences
- corrections that would prevent repeating the same mistake
Entry format
- Prefix each entry with
YYYY-MM-DD - - Use one line for brief durable preferences.
- For nuanced corrections, add one short continuation line indented by two spaces.
- Keep entries concrete and operational.
Rule Of Thumb
Log it only if it would still be useful in a different future task.
Related Skills
kevin-mok/typeset
tools
VerifiedTrustedCommunity
Improve typography by fixing font choices, hierarchy, sizing, weight consistency, and readability. Makes text feel intentional and polished.
SKILL.mdUpdated May 5, 2026
kevin-mok/transcribe
content-media
VerifiedTrustedCommunity
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
SKILL.mdUpdated May 5, 2026
kevin-mok/teach-impeccable
documentation
VerifiedTrustedCommunity
One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
SKILL.mdUpdated May 5, 2026
kevin-mok/smoke-test-capture
testing
VerifiedTrustedCommunity
Use when work in this repo introduces a concrete manual verification step, changes the expected outcome of an existing manual check, or exposes an obvious gap in the shared smoke-test checklist.
SKILL.mdUpdated May 5, 2026