cellm/skills/file-context/SKILL.md
Passive file relationship classifier — detects multi-file systems and enforces Related files headers. Activates when creating or modifying files that participate in cross-file protocols, shared data flows, or lifecycle chains. Inactive when the file has no Related files header AND the edit touches under 30 LOC, on read-only operations, on standalone scripts, on .test/.spec/.d.ts files, and on documentation/markdown edits.
npx skillsauth add murillodutt/cellm cellm/skills/file-contextInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
When touching a file, classify its relationship to other files:
| Signal | Classification | Action | |--------|---------------|--------| | Single-purpose utility, no imports from siblings | STANDALONE | No header needed | | Request/response chain, event emitter/listener | PROTOCOL | Add Related files header | | Shared config, DB schema used by multiple consumers | SHARED DATA | Add Related files header | | Start/stop/cleanup sequence across files | LIFECYCLE | Add Related files header | | Pipeline stage: output of one file is input of next | PIPELINE | Add Related files header |
You are in a multi-file system when ANY of these are true:
/**
* <Title> — <One-line purpose>
*
* <Optional: deeper explanation, patterns, constraints>
*
* Related files (<System Name>):
* - path/to/file-a.ts — <role in the system>
* - path/to/file-b.sh — <role in the system>
* - path/to/file-c.ts — <role in the system>
*/
Rules:
~/.cellm/sdk-sidecar.json) when relevantIf the file you are about to modify has a Related files header:
Add a Related files header when you create or significantly modify a file that:
Do NOT add headers to:
.d.ts, pure interfaces)data-ai
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.
development
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.
data-ai
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.
tools
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.