hoangnb24/compounding
plugins/khuym/skills/compounding/SKILL.md
Use when reviewing completes or work is intentionally abandoned. Extract durable patterns, decisions, and failures into history/learnings, then promote only critical reusable lessons to critical-patterns.md.
$ install --global
skillsauthnpx skillsauth add hoangnb24/skills compoundingInstall 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 3, 2026, 3:16 AM129.0s3 files scanned
SKILL.md
- name:
- compounding
- description:
- >-
- version:
- 1.0
- ecosystem:
- khuym
- position:
- 8 of 9 — runs after reviewing, before next feature
- kind:
- command
- command:
- br
- missing_effect:
- degraded
- reason:
- Compounding reads bead history to reconstruct what work actually ran.
Compounding
If .khuym/onboarding.json is missing or stale for the current repo, stop and invoke khuym:using-khuym before continuing.
Compounding captures reusable lessons from completed work and feeds them back into future Khuym planning and exploring. Run it after khuym:reviewing completes and the feature is merged or intentionally abandoned with lessons.
Required Inputs
history/<feature>/CONTEXT.mdhistory/<feature>/discovery.mdhistory/<feature>/approach.md.khuym/state.jsonor retained handoff artifacts.beads/orbr showoutput- review findings and debugging notes, if they exist
- feature commit history
If history files are incomplete, use the session summary and recent git diff as fallback evidence. Do not fabricate learnings.
Operating Contract
- Gather the feature context and reconstruct what actually ran.
- Launch three analysis subagents in parallel: patterns, decisions, failures.
- Synthesize findings into one dated
history/learnings/YYYYMMDD-<slug>.mdfile. - Promote only genuinely critical, reusable lessons to
history/learnings/critical-patterns.md. - Optionally integrate with CASS/CM when repo config enables it.
- Update
.khuym/state.jsonwith the completed compounding run.
Load references/compounding-reference.md for analysis prompts, promotion criteria, state update, and the learnings template.
Hard Gates
- Do not skip compounding for meaningful feature work just because the session feels done.
- Do not promote everything as critical; keep
critical-patterns.mdhigh signal. - Do not write generic lessons. Each entry needs a concrete situation, root cause, and future rule.
- Do not let subagents write final learnings files; the orchestrator synthesizes.
Handoff
Compounding complete.
- Learnings: history/learnings/YYYYMMDD-<slug>.md
- Critical promotions: <N> findings added to critical-patterns.md
- The ecosystem now has <N total> accumulated learnings.
Reference Files
| File | When to Load |
|---|---|
| references/compounding-reference.md | Protocol and learnings template |
Related Skills
hoangnb24/smart-commits
tools
VerifiedTrustedCommunity
Use when the user asks to commit everything, smart commit, group commits, organize staged or unstaged changes, create logical commits, push current work, or preserve a clean commit stack from an existing working tree.
215SKILL.mdUpdated May 21, 2026
hoangnb24/using-khuym
development
VerifiedTrustedCommunity
Use when starting or resuming any Khuym project session, choosing the next Khuym skill, running go mode, checking onboarding/scout state, or enforcing workflow gates. Bootstrap meta-skill for routing across the Khuym agentic development ecosystem.
215SKILL.mdUpdated Apr 18, 2026
hoangnb24/goal-griller
development
VerifiedTrustedCommunity
Use when the user wants to turn a rough idea, vague task, feature wish, bug-fix intent, or Codex /goal objective into a clear verifiable goal prompt. Use when the user mentions goal mode, /goal, set_goal, long-running autonomous Codex work, or asks to be interviewed/grilled before creating a goal.
213SKILL.mdUpdated May 19, 2026
hoangnb24/concept-game-builder
tools
VerifiedTrustedCommunity
Use when Codex should turn a concept, topic, tutorial, lesson, algorithm, system, workflow, or abstract idea into a playable browser game that teaches through interaction. Use for planning or implementing educational web games with the Game Studio plugin, including concept-to-mechanic translation, gameplay loop design, learning progression, and browser-game QA.
213SKILL.mdUpdated May 19, 2026