ztn-lint

Nightly slop catcher for ZTN. Reads the whole base, autonomously fixes the obvious, surfaces the non-obvious as CLARIFICATIONS with rich Context paragraphs (self-contained для LLM review session), generates Lint Context Store (30-day rolling daily + forever monthly summaries = system memory beyond lint). Confidence tier routing (silent/noted/reviewed/surfaced/hidden) via rule-floor × LLM-verdict. Dedup = content-merging (not destructive). Cross-skill lock awareness symmetric. Best-effort, idempotent, rollback via git.

Safety Notice

This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.

Copy this and send it to your AI assistant to learn

Install skill "ztn-lint" with this command: npx skills add S1lash/skillsmp-s1lash-s1lash-ztn-lint

No markdown body

This source entry does not include full markdown content beyond metadata.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Open in GitHub

Related Skills

Related by shared tags or category signals.

General

ztn-check-decision

Check a pending decision or observed behaviour against the active constitution tree at 0_constitution/. Returns a verdict — aligned, violated, tradeoff, or no-match — with citations to specific principles and prose rationale. Opus-backed reasoning. Auto-appends Evidence Trail citations on every cited principle and bumps their last_applied field (L1 autonomous write — the one thing this skill modifies under 0_constitution/, never the principle body).

Repository SourceNeeds Review

-0S1lash

Research

ztn-process

Process new voice transcripts from _sources/inbox/ into ZTN three-layer architecture (Records + Knowledge + Hubs). Full pipeline: pre-scan with People Resolution Map, LLM noise gate, 16-question classification (incl. content potential, concepts, privacy trio), atomization, cross-domain scan, hub detection, per-batch subagent dispatch with self-review, people profile enrichment, idea living documents. Emits batch report per run and Evidence Trail initial entry in every new knowledge note.

Repository SourceNeeds Review

-0S1lash

Coding

ztn-resolve-clarifications

Interactive facilitator for the owner's CLARIFICATIONS queue. Pre-syncs via /ztn:sync-data so the queue reflects state from all devices, then loads open items, clusters by Type, presents one theme at a time as a numbered batch (≤5 items, adaptive — 3 for heavy types, 5 for light), reminds full situation + verbatim quotes already stored in the file, pre-checks values-bearing items against the constitution, proposes resolution with labelled options, applies confirmed actions (silent for archival ops, diff-first for content edits), archives resolved items and re-prioritises deferred ones. After resolutions, refreshes derived views (/ztn:regen-constitution if principle accepts; /ztn:maintain if registries / hubs touched) and reminds owner to run /ztn:save when the working tree is dirty. Manual, owner-driven — never dumps the whole queue, never asks the owner to recall meeting context unaided.

Repository SourceNeeds Review

-0S1lash

General

Wilma Triage

Daily triage of Wilma school notifications for Finnish parents. Fetches exams, messages, news, schedules, homework, and lesson notes (merkinnät) — filters fo...

Registry SourceRecently Updated

1.1K0aikarjal