murillodutt/cellm/skills/version-control
cellm/skills/version-control/SKILL.md
Deep versioning guidance for any project — SemVer vs EffVer vs CalVer, release automation, AI artifact versioning. Use when: 'versioning strategy', 'which versioning scheme', 'setup releases', 'version AI artifacts'. For CELLM-specific version bumps and inflation checks, use cellm:versioning.
tools
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add murillodutt/cellm cellm/skills/version-controlInstall 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: Apr 16, 2026, 5:23 AM22.9s1 file scanned
SKILL.md
- description:
- Deep versioning guidance for any project — SemVer vs EffVer vs CalVer, release automation, AI artifact versioning. Use when: 'versioning strategy', 'which versioning scheme', 'setup releases', 'version AI artifacts'. For CELLM-specific version bumps and inflation checks, use cellm:versioning.
- cellm_scope:
- universal
- user-invocable:
- true
- argument-hint:
- [question or project context]
- allowed-tools:
- Read, Grep, Glob, AskUserQuestion
Version Strategy — Before Choosing
Decision Tree
Is the project in production with users depending on the API?
NO -> 0.x.y (SemVer pre-stable)
MINOR = breaking, PATCH = features + fixes. Iterate freely.
YES -> Published library/package?
YES -> Strict SemVer. Batch breaking changes. Deprecate before remove.
NO -> Need to communicate impact? -> EffVer
Date matters more? -> CalVer
Want simplicity? -> SemVer with fixed cadence
Schemes
| Scheme | Format | Best For | Adopted By | |--------|--------|----------|-----------| | SemVer | MAJOR.MINOR.PATCH | Libraries, packages, APIs | npm, Cargo, Go, PyPI | | EffVer | MACRO.MESO.MICRO | Effort-based communication | Matplotlib, JAX, JupyterHub | | CalVer | YYYY.MM.DD (variable) | Date-driven releases | Ubuntu, pip, Black | | Epoch SemVer | {EPOCH*1000+MAJOR}.MINOR.PATCH | Era-based projects | Experimental only |
Anti-Inflation
| Strategy | When |
|----------|------|
| Stay on 0.x.y | Pre-production — no stable API yet |
| Pre-release tags (-alpha, -beta, -rc) | Separate maturity from version |
| Batch breaking changes | Accumulate on branch, release on cadence |
| Deprecate before remove | Mark deprecated in MINOR, remove in next MAJOR |
| Codemods | Automate migration to reduce MAJOR cost |
| Release channels (stable/beta/canary) | Rapid iteration without inflating stable version |
AI Artifacts
| Artifact | Version How | |----------|-------------| | Prompts | SemVer: structural change = MAJOR, new field = MINOR, wording = PATCH | | ML Models | SemVer-ML: architecture = MAJOR, hyperparams = MINOR, training data = PATCH | | Datasets | DVC/LakeFS + link to model version |
Automation
Conventional Commits (type(scope): description) + automated release tools:
| Tool | Ecosystem | |------|-----------| | changelogen | Nuxt/UnJS | | semantic-release | npm | | release-please | Google/GitHub | | changesets | Monorepos (Turborepo, pnpm) |
NEVER
- Reach v1.0.0 without real users — 0.x.y is correct for pre-production
- Bump MAJOR on every AI refactor — batch breaking changes into cycles
- Use version number for maturity signal — that's what pre-release tags are for
- Version without automation — conventional commits + changelogen minimum
Related Skills
murillodutt/cellm/skills/prose
data-ai
VerifiedTrustedCommunity
Prose override — temporarily disable quantization and respond in readable prose. Use when relational density matters, for safety-critical explanations, onboarding handoffs, or when token economy is not the priority.
SKILL.mdUpdated Apr 23, 2026
murillodutt/cellm/skills/pr-guardian
development
VerifiedTrustedCommunity
Govern explicit weekly Super PRs or maintainer-requested PR merges. Evaluates a 10-criterion readiness checklist and performs governed merge only when a user-requested PR is READY. Never creates or keeps permanent PRs. Use when: 'pr-check', 'pr-merge', 'merge this PR safely', 'is PR ready', 'guard merge', or /sk-git delegates pr-merge.
SKILL.mdUpdated Apr 23, 2026
murillodutt/cellm/skills/compress-llm
data-ai
VerifiedTrustedCommunity
Operational surface for the compress-llm Layer-1 token I/O compressor. Enable, disable, switch mode, and inspect status without editing config files. Use when tuning compression pressure for the current session or project.
SKILL.mdUpdated Apr 23, 2026
murillodutt/cellm/skills/cellm-feedback
tools
VerifiedTrustedCommunity
Generate structured upstream feedback for the CELLM engineering team. Produces evidence-first Markdown at docs/evidence/<date>-cellm-feedback-*.md for bugs, anti-patterns, deprecation gaps, and harness surprises, with optional atom registration via knowledge_ops. Use when: 'feedback for CELLM', 'send to CELLM team', 'register this as atom', 'document this anti-pattern', 'report this bug upstream'. Trigger proactively on MCP schema/runtime mismatches, mechanical edit loops (>=3 sequential edits), short deprecation windows (<6 weeks), or reusable harness surprises. Do NOT trigger for routine feature work or project-local bugs.
SKILL.mdUpdated Apr 21, 2026