distributions/claude/skills/prompt-atom-formalization/SKILL.md
Scan rough markdown, session exports, or pasted prose and isolate each core intent into a structured prompt atom — classified as law, value, directive, constraint, question, or branch-vector — then rewrite it into machine-readable YAML frontmatter per the RAW → CLEANED/FORMALIZED → ELEVATED doctrine. Triggers on "prompt atom extraction pass", "atomize this", "formalize these prompts", or converting loose operator text into registry-grade atoms.
npx skillsauth add organvm-iv-taxis/a-i--skills prompt-atom-formalizationInstall 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.
Convert loose operator prose into atoms: minimal, classified, machine-readable units of intent that registries can store, pipelines can route, and future sessions can execute without re-interpreting the original wall of text.
Operator intent arrives packed — one dense paragraph can carry a standing law, two directives, a constraint, and an open question. Left as prose, that intent is executable only by whoever re-reads and re-derives it. Atomized, each unit gets an ID, a class, a lifecycle state, and provenance — it becomes governable. The doctrine: atoms are permanent; extraction is additive; nothing in the source is destroyed by being formalized.
| Class | Nature | Lifetime | Example | |-------|--------|----------|---------| | law | standing rule; governs all future behavior | permanent until amended | "nothing local-only — every artifact git-tracked AND pushed" | | value | weighting/preference; shapes choices without mandating one | durable | "prefer user coinages over standard vocabulary" | | directive | one concrete executable action | until DONE | "register the 5 bench agents in fleet.yaml" | | constraint | boundary on how any action may be done | scoped or permanent | "never chezmoi add over existing source without diffing" | | question | open decision owned by a human | until answered | "GCP_SA_KEY provisioning — enable CI deploys?" | | branch-vector | a fork in possible futures; options held in superposition | until collapsed | "skills live in domus OR a-i--skills — decide before next install" |
Every atom records which state it is in; an extraction pass may legitimately stop at CLEANED.
{file, line-range} or {session-id, message-index}.- id: ATM-NNNNNN # mint from the registry's counter — never invent ranges
class: constraint
state: CLEANED
text: "Never `chezmoi add` over existing source without `chezmoi diff` first."
raw: "…also for god's sake diff before you chezmoi add anything again…"
provenance: {session: 8bb8f846, message: 41}
captured: 2026-06-07
status: OPEN # OPEN | DONE | ANSWERED | COLLAPSED | SUPERSEDED-BY:{id}
links: [ATM-013811] # related atoms; liberal linking
tags: [chezmoi, destructive-ops]
Rules:
raw is mandatory: the verbatim or span-referenced source. Formalization without provenance is paraphrase, not extraction.text field needs "and", split it.For laws/values/constraints that recur across ≥2 independent sources:
state: ELEVATED and route to the appropriate standing surface (constitution tier, reliquary, registry) by pointer — the atom stays in the registry; the surface cites it.SUPERSEDED-BY back-link).development
Dry-run audit + targeted cleanup for shell command history. Currently wraps atuin (stats today, prune, dedup with dated preview artifacts); extensible to zsh/bash/mcfly backends. Always previews before applying — apply commands are echoed for the human to run, never auto-executed. Triggers on "/shell-history-hygiene", "audit atuin", "audit shell history", "clean shell history", "atuin prune", "atuin dedup", "shell history hygiene", "history cleanup". Replaces ad-hoc one-liners (e.g. `... | tee cmd > file.txt` which wrote two files, swallowed dedup output, and left a junk `cmd` file).
tools
Guided Cowork setup — install role-matched plugins, connect your tools, try a skill.
development
Manage AI agent session lifecycles with structured phases (FRAME, SHAPE, BUILD, PROVE), context preservation across sessions, handoff protocols, and session metadata tracking. Triggers on session management, agent lifecycle, or multi-session workflow requests.
tools
Parse a session transcript into a structured Session Governance Index — an annotated bibliography of every file modified and commit made, internal-energy accounting (tool uses, estimated tokens), shipped-vs-tasked atom tally, and classification of missing items as Gaps or Vacuums. Triggers on "visibility-schema-substrate-sweep", "session cascade audit", "session governance audit", or any request to summarize what a session actually produced versus what it was asked to produce.