cellm/skills/implement/SKILL.md
Implement code from CellmOS spec context. Loads spec tree from Oracle DB, picks next pending task, writes code, runs quality gate, transitions state on completion. Use when: 'implement next task', 'implement spec', 'pick next task'.
npx skillsauth add murillodutt/cellm cellm/skills/implementInstall 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.
Implement the next executable spec task as a thin consumer of SCE context.
context_preflight is mandatory before implementation (flow='implement').spec_get_tree to load check/phase/task context and constraints.context_record_outcome for the learning loop.spec_search + spec_get_tree).spec_get_tree returns empty YAML/JSON for an active check, run spec_get_counters. If counters also show 0 tasks, STOP and escalate: "Check is active but has 0 tasks — decomposition likely failed. Run /cellm:plan-to-spec to recreate." Do NOT execute work outside the spec tree.context_preflight and consume renderedMarkdown/envelope as-is.spec_get_verifications + spec_record_verification).spec_transition.spec_get_counters and verify completed count incremented. If the task transition succeeded but counters did not change, warn: "Task transitioned but counters stale — possible DB inconsistency."context_record_outcome.When CELLM_DEV_MODE: true (verify via get_status MCP -> config.devMode):
Before implementing, extract the fallback path from the check's context field (look for [fallback: .claude/specs/...]). If not in context, try .claude/specs/{check-slug}.yaml. Check if the file exists:
[+] Fallback YAML found: {path} — Worker crash recoverable[!] No fallback YAML. Worker crash = unrecoverable spec loss. Generate with /cellm:plan-to-spec or create manually.Do NOT block execution if missing — warn only.
context_preflight.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.