sofer/learning
skills/learning/SKILL.md
Append a one-line learning to ~/.agents/learning-log.md. Use when the user types /learning, or when something genuinely worth remembering surfaced during work and the user confirms it should be captured.
$ install --global
skillsauthnpx skillsauth add sofer/.agents learningInstall 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 1, 2026, 6:39 AM146.2s1 file scanned
SKILL.md
- name:
- learning
- description:
- Append a one-line learning to ~/.agents/learning-log.md. Use when the user types /learning, or when something genuinely worth remembering surfaced during work and the user confirms it should be captured.
Learning
Purpose
Capture durable lessons without turning every task into memory noise.
Rules
- Append one line only.
- Capture reusable preferences, tool quirks, non-obvious fixes, workflow improvements, or lessons likely to change future behaviour.
- Do not capture routine progress, trivia, secrets, credentials, private email/calendar content, or anything obvious from the current code.
- If the user invoked
/learning, treat that as permission to write. - If the agent noticed a possible learning during normal work, offer the exact candidate learning and wait for confirmation before writing.
- Do not read or summarise the log before appending. It is append-only.
Format
YYYY-MM-DDTHH:MM:SS [short-cwd] <learning text>
Where:
short-cwdis the current working directory relative to$HOME, prefixed with~/, or~if cwd is$HOME.<learning text>is a single grep-friendly sentence.
Instructions
If the user invoked /learning without text, ask once: "What did you learn?"
Append with this command shape:
printf '%s [%s] %s\n' \
"$(date +%Y-%m-%dT%H:%M:%S)" \
"$(pwd | sed "s|^$HOME|~|")" \
"the learning text" \
>> "$HOME/.agents/learning-log.md"
After appending, briefly confirm what was captured.
Related Skills
sofer/agent-config-audit
tools
VerifiedTrustedCommunity
Check whether Claude and Codex have equivalent access to shared agent resources, skills, hooks, plugins, MCP servers, permissions, startup behaviour, and provider-specific adapter config. Use when comparing agent environments, debugging missing capabilities after restart, or deciding whether to symlink a resource or configure a runtime.
4SKILL.mdUpdated May 10, 2026
sofer/skill-usage
testing
VerifiedTrustedCommunity
Record substantive skill use in an append-only local log. Use after choosing or invoking a non-system skill for real work, when a skill is inspected but not used, or when a skill fails to apply. Do not use for routine system skills or incidental file reads.
4SKILL.mdUpdated May 1, 2026
sofer/problem-statement
testing
VerifiedTrustedCommunity
Turn a vague or underspecified request into a self-contained problem statement. Use when the user has a rough idea, when a request would fail if handed directly to an agent, or before non-trivial work that needs shared understanding.
4SKILL.mdUpdated May 1, 2026
sofer/evaluate
testing
VerifiedTrustedCommunity
Define evaluation criteria, tests, or quality checks for a deliverable, implementation, workflow, or recurring agent task. Use when defining done, improving a test harness, or checking whether output meets its specification.
4SKILL.mdUpdated May 1, 2026