docops/skills/init/SKILL.md
Docops: scaffold LLM-first documentation structure, templates, and docops.json for a project. Creates directory hierarchy without overwrite. Use when: 'init docs', 'setup documentation', 'create docops structure'. Not for Oracle setup (use cellm:oracle).
npx skillsauth add murillodutt/cellm docops/skills/initInstall 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.
Scaffold LLM-first documentation structure, templates, and docops.json for a project.
docops.json config as the single source of docRoot for subsequent docops skills.context_preflight recommended but failure does NOT block execution; if preflight fails, warn and proceed without context..claude/docops.json exists, use its docRoot; otherwise require docRoot argument.${CLAUDE_PLUGIN_ROOT}/templates/<language>/.docops.json after scaffold is complete (mandatory write-back).Run context_preflight with flow='generic'; if it fails, log a warning and continue without context (do not block).
Check for existing .claude/docops.json; if present, read docRoot from it. Otherwise, use the argument (fail if neither exists).
Create the following hierarchy, skipping any directory or file that already exists:
{docRoot}/
index.md # Entry point
glossary.md # Terms and definitions
project-conveyor.md # Source of truth
specs/ # .spec.md files
reference/ # .ref.md files
code-evidence/ # Auto-extracted code
conveyor-gaps.md # Drift tracking
howto/ # .howto.md files
runbooks/ # .runbook.md files
decisions/ # ADR-YYYYMMDD-slug.md files
Naming conventions: <name>.spec.md, <name>.ref.md, <name>.howto.md, <name>.runbook.md, ADR-YYYYMMDD-slug.md.
Write .claude/docops.json with resolved docRoot (create or update).
Emit outcome via context_record_outcome.
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.