bigeasyfreeman/learning-refresh
skills/learning-refresh/SKILL.md
Scoped maintenance for docs/solutions entries when stale signals, refactors, or explicit user scope require refresh.
$ install --global
skillsauthnpx skillsauth add bigeasyfreeman/adlc learning-refreshInstall 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: Jun 8, 2026, 2:21 AM156.8s1 file scanned
SKILL.md
- name:
- learning-refresh
- description:
- Scoped maintenance for docs/solutions entries when stale signals, refactors, or explicit user scope require refresh.
- contract_version:
- 1.0.0
- side_effect_profile:
- mutating
- mode:
- scoped_maintenance
- consumes_manifest:
- true
Learning Refresh
Purpose
Keep docs/solutions useful without turning every ADLC run into a documentation sweep.
Trigger
Run only with a concrete scope:
- a stale condition from a learning entry fired
- a user requested refresh for a module, domain, or tag
- a significant refactor touched cited source evidence
- learning capture detected overlap with an older entry
Outcomes
Use one outcome per reviewed entry:
Keep: still accurate and usefulUpdate: same learning, refreshed evidence or verifierConsolidate: merge overlapping entries and delete duplicatesReplace: supersede misleading guidance with a new entryDelete: remove obsolete or unsupported entries; git history is the archive
Ambiguous headless cases should be marked stale rather than rewritten.
Process
- Inventory only the scoped entries.
- Read cited source evidence and run the verifier when practical.
- Update frontmatter and body only when the evidence supports it.
- Validate every changed entry with
python3 scripts/validate_learning_entry.py. - Emit a refresh report with unchanged, changed, stale-marked, and deleted paths.
Rules
- No broad refresh by default.
- No archive directory; delete obsolete files.
- No unsupported rewrites when evidence is missing.
- No full solution-store dump into model context.
Related Skills
bigeasyfreeman/paved-road-registry
development
VerifiedTrustedCommunity
Discovers and records repo-local approved build paths so agents reuse proven patterns instead of inventing parallel architectures.
1SKILL.mdUpdated Jun 8, 2026
bigeasyfreeman/learning-capture
documentation
VerifiedTrustedCommunity
Conditionally captures verified reusable ADLC learnings into docs/solutions after successful closeout.
1SKILL.mdUpdated Jun 8, 2026
bigeasyfreeman/graph-research
development
VerifiedTrustedCommunity
Uses Graphify as ADLC's graph-backed research layer and Beads as an optional dependency-aware task memory layer. Produces evidence for compatibility, reuse, accuracy, dark-code hotspots, and long-horizon handoff.
1SKILL.mdUpdated Jun 8, 2026
bigeasyfreeman/dark-code-audit
tools
VerifiedTrustedCommunity
Assesses structural and velocity dark-code risk from architecture, AI tool usage, ownership, and deployment practices. Produces a direct risk assessment without inventing missing facts.
1SKILL.mdUpdated Jun 8, 2026