Claude Skills by muratsilahtaroglu

Adopt Keel's discipline into an EXISTING project (brownfield) — inventory, non-destructive merge, back-fill docs from real code, migrate security. Never overwrites.

OWNER-only setup wizard for a same-machine agent team — name the roster (one orchestrator + specialized workers), generate .claude/agents/team-<name>.md charters with owner-approved full text, seed TASKS lanes + reports/team author folders. Structured co-agents per rules §10.42.

Adopt an agent-team identity for THIS chat (run once per new chat) — load the charter, record the session→agent mapping so the reground hook re-injects the identity from disk after every compaction/--resume, then resume from the agent's lane.

Periodic rules-compliance spot-check — spawns the read-only auditor subagent over the commits since the last audit, reports violations with file:line + rule §, fixes only what the user approves. Skips itself on an empty (phase-0) project.

Gated autonomy for one session — advance phases back-to-back with the full /keel-phase-review run at every gate, auto-commit at phase ends, batch pushes for ONE approval. Stops on gate FAIL, UNCERTAIN decisions, architecture surprises, or security-adjacent changes. Push is never automatic. Solo sessions or an agent team's orchestrator ONLY — never a worker/co-agent (it runs phase-review and commits, both forbidden to them by rules §10.42).

Pre-compact ritual — bring the disk fully up to date (runs the /keel-handover procedure, which cascades to /keel-distill, PLAN flips and the LESSONS sweep), verify freshness, then hand off to the built-in /compact. One command to remember instead of several.

Work out what this session should do NEXT and continue from it — resume half-done work, or pick up the lane's newly assigned task, or report that there is nothing to do and go idle. Cross-checks the auto-loaded memory against PLAN.md + git. Role-aware: read-only in a worker/solo session (so any session type may run it); in the ORCHESTRATOR it also SYNCS worker boards into the shared files, ROUTES what waits in Review and ASSIGNS the next item — §10.42 makes it their sole writer.

Consolidate project memory — rotate old HANDOVER blocks to the archive, promote critical facts to LESSONS.md, dedup/merge, and lint for contradictions. Run when caps are exceeded.

Add this session's block to HANDOVER.md before ending or compacting — done / tried-failed / latest / next. Rotates via /keel-distill when the 3-block cap is hit.

End-of-phase gate — verify working product, tests, docs, ADRs, and handover before committing a phase.

Staged bulk-run gate — before any mass-output job (labeling, generation, migration) enforce, in order, declare thresholds → smoke sample → gold-set validation → progressive ramp with halt conditions → acceptance sample. No full run on an unvalidated pipeline.

Create or revise PLAN.md — propose the phase DAG (phases · gates · dependencies) from the user's goal, get approval, write the table and regenerate the colored Mermaid diagram from it. Statuses flip at rituals (/keel-handover, /keel-phase-review); post-completion fixes land in the Fix log.

Opt-in external research — scan GitHub/articles/LinkedIn/HuggingFace/web and save cited findings per platform under research/.

Render the ritual telemetry visually — turns .claude/ritual-log into reports/ritual-stats.md with PLAN.md-style colored Mermaid interval boxes (session/compact boundaries) + a counts table. Answers "which skills/commands/hooks ran, how often, in which interval".

OWNER-only setup wizard for a REAL human team (different people, different machines) — declare the owner (arm owner-guard), register members (@tags), seed lanes + author folders + the comprehension protocol, size the caps, pick the §6 contribution model + host wall. Packages the existing Multi-user playbook into one approved run; invents no new rules.

Layout-hygiene ritual — sweep stray/obsolete files (loose root scripts, dead code, logs, stale scratch), attach EVIDENCE to each (references incl. reports/ citations, test collection; age never decides alone), then triage with approval — module-ize · delete (git is the archive; deletes are a separately-confirmed list, never inside a blanket yes) · scratch/archive/ · gitignore the class. Never touches memory files or the reports/ evidence trail.

Pull the latest Keel template improvements into THIS project — kit tooling in one reviewed batch, likely-tailored files hunk-by-hunk; only approved hunks are applied. Never touches project memory (HANDOVER/LESSONS/TASKS) or project-owned files (src/, CLAUDE.md, ADRs).