hashintel

Author a completed-spec fixture — a seeded intent graph plus a believable four-phase interview transcript — for a brunch feature, so it can feed any downstream tooling that consumes a completed spec or dogfood the UI. Use when you need a real completed…

Review someone else's PR through an architectural/strategic lens — does it shift design, raise complexity, or quietly change precedent? Drives a brief reflective discussion with the user, then posts a concise review comment via `gh`. Defers line-level and…

Crystallize shared understanding into a reviewable spec, or update an existing one. Use when the problem needs a written specification, when assumptions or decisions have changed, or when the user says 'write a spec'.

Lightweight triage for the ln-* skill set. Use when unsure which ln skill to use next, starting work on something new, or when the user asks for guidance on their development process.

Explore radically different module shapes before committing to one. Use when choosing an API surface, deciding what a module hides vs exposes, or when the user says 'design it twice'.

Collapse meaningful ambiguity with contrastive examples. Use when a plan/design has several plausible meanings, requirements feel vague, examples would clarify intent faster than grilling, or the user asks to disambiguate, find ambiguity, use behavioral…

Audit code quality focusing on deep modules, naming, model hygiene, and architectural clarity. Use after a burst of development, when codebase structure needs assessment, or to make code more agent-navigable.

Refresh `memory/SPEC.md` and `memory/PLAN.md` in mature mode — restore canonical truth, archive retired plan history, delete stale derivative artifacts, and flag drift against code.

Acquire and improve an epistemically responsible source-side account through conversation and consulted material. Use before substantive interviewing, source consultation, consequential correction or conflict resolution, and when recording workpiece evidence.

Elicit or transcribe a target claim and the definitions and supporting claims its justification rests on, maintain a recoverable claims workpiece, prepare statement cards for an external claims ledger, and explain what the ledger's standing does and does not…

Stub. Elicit software correctness obligations, maintain a recoverable correctness workpiece, and author or review Dafny specifications with an honest account of what was stated, assumed, discharged, skipped, or trusted. Use for a correctness interview or a…

Elicit or revise software behavior, maintain a recoverable behavior workpiece, and author or review honest Gherkin feature documents. Use for a behavior-specification interview, Gherkin document, executable-specification draft, or review of any of them.

Elicit or revise an operational process model, maintain its recoverable workpiece, and construct a checked SDCPN when Petrinaut capabilities are available. Use for a process-modelling interview, Petri net, or analysis or revision of either artifact.

Conventions for publishing npm packages from this repository, including when a PR needs a changeset and how to write one. Use when adding or editing a changeset, versioning or releasing a package, or deciding whether a change to a publishable library needs a…

Elicit or revise software behavior, maintain a recoverable behavior workpiece, and author or review honest Gherkin feature documents. Use for a behavior-specification interview, Gherkin document, executable-specification draft, or review of any of them.

End-to-end procedure for shipping a change to the Petrinaut packages (libs/@hashintel/petrinaut, petrinaut-core, petrinaut-cli, apps/petrinaut-opt, apps/petrinaut-website): the verification gates per package, the changeset step, docs sync, pre-PR hygiene…

Read and write a Petri net (SDCPN) document by Automerge URL. Use when creating, editing, or querying Petri nets — adding or removing places, transitions, arcs, color types, differential equations, and parameters.

Create and maintain an Assumption Ledger — a persistent record of assumptions, their confidence, and validation status. Use when starting a new slice, resuming work in a new context window, or when implicit assumptions risk causing drift. Tracks requirements,…

Create or update a concept capsule — the conceptual anchor for a project or feature area. Use before writing code on a new project or feature, or when terms and boundaries feel unclear. Defines glossary, invariants, happy-path scenario, and non-goals.

Write a tracer-bullet card — a precise specification for one thin end-to-end slice of work. Use when scoping a new slice, defining what to build next, or breaking a feature into provable increments. Covers target behavior, boundary crossings, risks, and…

Create characterization tests (Golden Master) for existing code so you can refactor or replace safely. Use before refactoring, strangler-replacing, or modifying code with unclear behavior. Captures observable behavior with a minimal harness, producing tests,…

Methodology triage consultant for tracer-bullet development. Use when unsure which pragma skill to run next, when starting a new project, or when the current approach feels stuck. Interviews the user, assesses state, and recommends the next pragma skill.

Turn capsule invariants and boundary crossings into executable contracts. Use after creating a concept capsule, or when invariants need to be enforced in code. Covers preconditions, postconditions, constructor validation, domain types, and contract tests.

Design feedback loops and validation harnesses before starting implementation. Use when beginning any non-trivial development task, when the agent can't easily validate its own work, or when asked to set up a development harness, playground, or experiment…