popoffvg/context-check
harness/plugins/memory-keeper/skills/context-check/SKILL.md
This skill should be used when the user says "context check", "check for insights", "anything worth saving", "review session", or wants to analyze the current conversation for valuable learnings worth persisting — debugging discoveries, architectural decisions, corrections, workflow patterns.
$ install --global
skillsauthnpx skillsauth add popoffvg/dotfiles context-checkInstall 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 20, 2026, 4:42 AM209.1s1 file scanned
SKILL.md
- name:
- context-check
- description:
- This skill should be used when the user says "context check", "check for insights", "anything worth saving", "review session", or wants to analyze the current conversation for valuable learnings worth persisting — debugging discoveries, architectural decisions, corrections, workflow patterns.
Context Check
Analyze the current conversation for facts worth persisting. Save immediately without asking.
Usage
/context check
What to extract
Scan the conversation for concrete, reusable knowledge:
insight — completed work worth remembering:
- How a system works (architecture, data flow, API behavior)
- Patterns applied and why they work
- Gotchas, pitfalls, surprising behaviors
- Decisions made with reasoning
agent_edit — AI behavior changes:
- Hook logic, prompt changes, skill updates
- CLAUDE.md or plugin config changes
- Directives that change how the assistant behaves
none — skip silently:
- Routine: "ran tests", "committed code", "read a file"
- Too vague: "fixed authentication issues"
- Too granular: "added field X to struct Y" (what is it FOR?)
Entry Format
## <Keyword-rich title, 3-7 words> — YYYY-MM-DD HH:MM
<Lead: direct statement of what this is and why it matters. 1-3 sentences.
Include concrete identifiers: file paths, function names, config keys.
No preamble. Write for someone with zero memory of this session.>
### Subsection (only when topic has multiple distinct aspects)
<Details>
Heading = the search key. Must be findable by someone who forgot the topic:
- Good:
Go context: cancel propagates through goroutine tree - Good:
better-sqlite3 native module: breaks on Node version upgrade - Bad:
Context stuff,Fixed bug,Important pattern
Lead sentence = complete picture. Self-contained, states facts directly:
- Good:
Pi's shutdown() awaits all session_shutdown handlers before process.exit(0), giving handlers unlimited time for cleanup or LLM calls. - Bad:
In this session we discovered that the shutdown handler was being called...
Process
- Scan the conversation — identify distinct topics with reusable value
- For each topic: classify, write entry in wiki format
- Deduplicate against target file (exact heading, semantic overlap, superset/subset)
- Save immediately — do NOT ask for confirmation
- Report: topic + classification + file saved to
If nothing worth saving: return "nothing worth saving".
Related Skills
popoffvg/improve-claude-local
tools
VerifiedTrustedCommunity
Improve a whole CLAUDE.local.md — the private, per-project rules captured from user corrections. Wraps each conditional rule in a <task-relevant> block so it only surfaces for matching work, merges duplicates, generalizes one-off facts, drops stale entries, and routes raw project facts to engram. Use when the user says "improve claude.local", "clean up the local rules", "claude.local is bloated", or after the Stop hook has appended many rules.
2SKILL.mdUpdated Jun 25, 2026
popoffvg/workflow
testing
VerifiedTrustedCommunity
WM pipeline and conventions shared across all phases. Agents must read this before spec, impl, or verify work.
2SKILL.mdUpdated Jun 19, 2026
popoffvg/code
development
VerifiedTrustedCommunity
One entry point for spec writing, implementation, and bug fixing. Default is new (write spec → grill loop → produce notes → author TODO bodies). Other subcommands: verify (audit), revise (sync to shipped), prototype (settle a decision), code-map (diagram), impl (execute one TODO), fix (analyze cause, correct thoughts, fix behavior), help (this page). Invoke as /code <subcommand>.
2SKILL.mdUpdated Jun 19, 2026
popoffvg/red-green-refactor
development
VerifiedTrustedCommunity
Red-Green-Refactor cycle for bug fixes. Before fixing a bug, first write a failing test that reproduces it (Red), then make the minimal change to pass (Green), then clean up the code (Refactor). Use on any bug fix, error correction, failing test repair, or when user says "fix this bug".
2SKILL.mdUpdated Jun 18, 2026