all publishers

juxt

@juxt source repo

16 published skills

  1. ▌
    Glance · juxt
    Use when about to run commands with potentially long output (>40 lines) — builds, tests, logs, kubectl, docker, grep, find. Pipes output through glance for token-efficient summaries instead of reading all tokens.
    4 installs
  2. ▌
    Pr · juxt
    Create a pull request with a description that captures the intent and reasoning behind the change, in the chalk voice. Use when the user says "create a PR", "open a PR", "submit a PR", "raise a PR", "make a PR", "PR this", "/chalk:pr"; OR is about to compose, draft, write or update any pull request title or body (e.g. "write a PR description", "draft the PR body", "update the PR description", "let's put that in the PR"). Load this skill BEFORE drafting any such prose — it carries the voice guidance the PR body needs.
    5 installs
  3. ▌
    Issue · juxt
    Create a GitHub issue, or update an existing issue's description, with a body that captures the problem and why it matters, in the chalk voice. Use when the user says "open an issue", "file a bug", "raise an issue", "create an issue", "file a ticket", "write up a feature request", "/chalk:issue"; OR is about to compose, draft, write or update any GitHub issue title, issue body or issue description (e.g. "write up an issue for this", "update the issue description", "put the analysis on the ticket"). Load this skill BEFORE drafting any such prose — it carries the voice guidance the body needs.
    4 installs
  4. ▌
    Voice · juxt bundle
    Shared Chalk writing voice — the audience for Chalk artefacts, the specification register, the mindmap structure that followable content MUST take, and the layout rules. The chalk:issue, chalk:commit, chalk:pr and chalk:sitrep skills load this before drafting any prose, and the weed-prose agent loads it to review one.
    3 installs
  5. ▌
    Chill · juxt
    Interrupt forward momentum and step back to reassess
    4 installs
  6. ▌
    Commit · juxt
    Create a commit with a contextual body explaining the why, in the chalk voice. Use when the user says "commit this", "commit", "make a commit", "/chalk:commit"; OR is about to compose, draft, write or amend any git commit message body (e.g. "write a commit message", "draft the commit body", "amend the commit message"). Load this skill BEFORE drafting any such prose — it carries the voice guidance the commit body needs.
    5 installs
  7. ▌
    Sitrep · juxt
    Report where the current session has got to as a mindmap — what has landed, what is still open as ID'd ideas, decisions and questions, and a tl;dr. Use when the user says "/sitrep", "where are we", "where were we", "recap the session", "what's still open", or is picking a session back up after a break, a compaction or a handover.
    4 installs
  8. ▌
    Goal Tree · juxt
    Structure a goal as a tree whose children accomplish their parent rather than argue for it, and test each node for sufficiency. Load whenever writing something with a goal structure in it — the direction or target end state of a piece of work, an issue's Potential approach section, the shape of a problem, or a plan. Covers the sufficiency test, the three kinds of leaf, and the named moves for closing a gap. The chalk:issue skill loads it alongside chalk:voice.
    6 installs
  9. ▌
    Code Map · juxt bundle
    Build or query a code-only symbol and call-graph map of the current project, via LSP. Use when exploring an unfamiliar codebase, locating a symbol's definition, tracing what calls or is called by a function, assessing the blast radius of a proposed change, or navigating code beyond what grep alone can reveal. Produces a JSON map under .codemap/ at the project root. Skip for trivial lookups and single-file edits.
    4 installs
  10. ▌
    Code Comments · juxt
    What earns a code comment, and what to delete — interface versus implementation comments, the pinned readers, the triggers and the test, and where rejected material goes instead. Load early in any session that touches code, before writing or editing any comment, docstring or kdoc, and again when reviewing a diff, where weeding the comments is part of the review.
    2 installs
  11. ▌
    Tend · juxt
    Tend the Allium garden. Use when the user wants to write, edit, update, add to, improve, clarify, refine, restructure, fix or migrate Allium specs. Covers adding entities, rules, triggers, surfaces and contracts, fixing syntax or validation errors, renaming or refactoring within specs, migrating specs to a new language version, and translating requirements into well-formed specifications. Pushes back on vague requirements.
    3 installs
  12. ▌
    Weed · juxt
    Weed the Allium garden. Find where Allium specifications and implementation code have diverged, and help resolve the divergences. Use when the user wants to check spec-code alignment, compare specs against implementation, audit for spec drift or violations, sync specs with code or code with specs, or verify whether the implementation matches what the spec says.
    6 installs
  13. ▌
    Allium · juxt bundle
    Give your AI agents something more useful than a prompt. Velocity through clarity.
    5 installs
  14. ▌
    Distill · juxt bundle
    Extract an Allium specification from an existing codebase. Use when the user has existing code and wants to distil behaviour into a spec, reverse engineer a specification from implementation, generate a spec from code, turn implementation into a behavioural specification, or document what a codebase does in Allium terms.
    6 installs
  15. ▌
    Witness · juxt
    Independently witness that an Allium loop's convergence claim is true and was reached honestly. Use when the user wants to verify a loop's self-report, confirm tests really pass and no generated test was weakened, produce a convergence certificate or witness record, gate CI on a trustworthy signal, or check that an autonomous run did not cheat its way to green.
    4 installs
  16. ▌
    Propagate · juxt
    Generate tests from Allium specifications. Use when the user wants to propagate tests, generate test files from a spec, write tests for a specification, create property-based tests, produce state machine tests, check test coverage against spec obligations, or understand what tests a specification requires.
    5 installs