sofer/skill-usage
skills/skill-usage/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add sofer/.agents skill-usageInstall 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 AM132.3s1 file scanned
SKILL.md
- name:
- skill-usage
- description:
- 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.
- type:
- atomic
- input:
- Skill name, mode (used, inspected, failed), trigger (explicit, implicit, composite, manual), and a brief non-sensitive purpose
- output:
- One appended line in ~/.agents/skill-usage.log
Skill usage
Purpose
Track which personal skills are actually being used so the user can prune, improve, or keep skills based on evidence.
Rules
- Log only substantive personal skill activity.
- Do not log routine system skills, incidental file reads, or skill-review work unless the user asks to audit skill usage.
- Never log sensitive content from emails, calendar events, database rows, credentials, personal data, or user-private task details.
- Keep the purpose short and generic enough to be safe in a local audit log.
- Append only. Do not rewrite or summarise the log unless the user explicitly asks.
Fields
timestamp: local ISO-like timestamp, second precision.cwd: current working directory with$HOMEshortened to~.skill: skill name.mode:used,inspected, orfailed.trigger:explicit,implicit,composite, ormanual.purpose: short non-sensitive reason.
Instructions
- Identify the skill activity to record.
- Classify the mode:
used: the skill guided substantive work.inspected: the skill was opened to assess applicability but not used.failed: the skill should have applied but could not be used.
- Classify the trigger:
explicit: the user named the skill or requested that capability directly.implicit: the agent selected the skill from the request.composite: another skill invoked it as a step.manual: the user asked to record usage.
- Write one line to
~/.agents/skill-usage.log.
Use this command shape:
printf '%s [%s] skill=%s mode=%s trigger=%s purpose=%q\n' \
"$(date +%Y-%m-%dT%H:%M:%S)" \
"$(pwd | sed "s|^$HOME|~|")" \
"skill-name" \
"used" \
"implicit" \
"brief non-sensitive purpose" \
>> "$HOME/.agents/skill-usage.log"
Output format
After appending, briefly report the line that was recorded, unless the skill was invoked silently from an approved workflow.
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/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/learning
data-ai
VerifiedTrustedCommunity
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.
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