nullhack/temple8

Test-driven agent orchestration, templated. Tests authored as the contract, simulated before any source exists, built red→green under flowr state machines. Any LLM, any process, zero lock-in.

11Stars on the repository
41Mods indexed here, across every type
27d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

author-test-stubs

01

nullhack/temple8

Skill Claude CodeCodex

Author test stub files (.pyi) whose signatures express the domain, relationships, and compositions, as the first contract surface.

11 27d ago A 30 tokens original MIT

confirm-red-failure

02

nullhack/temple8

Skill Claude CodeCodex

Confirm the target contract's tests fail for the right reason before implementing — new work or rework, never a test defect.

11 27d ago A 30 tokens original MIT

nullhack/temple8

Skill Claude CodeCodex

End of session — replace running notes with the full synthesis across all three funnel levels and author the glossary of ubiquitous language.

11 27d ago A 30 tokens original MIT

derive-source-stubs

04

nullhack/temple8

Skill Claude CodeCodex

Derive the source stub files (.pyi) from the reviewed tests — every type the tests reference gets a definition.

11 27d ago A 29 tokens original MIT

design-interaction

05

nullhack/temple8

Skill Claude CodeCodex

Design the interaction + feedback + error flows for a user-facing surface (CLI, API, or web). On-demand — run when the ux-engineer is consulted on an interaction contract.

11 27d ago A 41 tokens original MIT

design-visual-asset

06

nullhack/temple8

Skill Claude CodeCodex

Produce a project visual asset — social card, README banner, logo/avatar, or favicon — as self-contained, accessible SVG. On-demand.

11 27d ago A 34 tokens original MIT

implement-from-stub

07

nullhack/temple8

Skill Claude CodeCodex

Write the minimum production code to turn the target's tests green, implementing the .py from its fixed .pyi.

11 27d ago A 29 tokens original MIT

instantiate-project

08

nullhack/temple8

Skill Claude CodeCodex

Create a new project instance from the temple8 template via copier, verify it, and initialise the first flowr session.

11 27d ago A 27 tokens original MIT

nullhack/temple8

Skill Claude CodeCodex

Funnel level 3 — identify building-block names and rough boundaries only, and run gap analysis.

11 27d ago A 26 tokens original MIT

nullhack/temple8

Skill Claude CodeCodex

Funnel level 2 — structure the domain into behaviour groups, bounded contexts, integration points, and lifecycle events.

11 27d ago A 29 tokens original MIT

interview-general

11

nullhack/temple8

Skill Claude CodeCodex

Funnel level 1 — establish the big picture with seven broad questions, applying CIT, Laddering, and CI Perspective throughout.

11 27d ago A 30 tokens original MIT

merge-to-dev

12

nullhack/temple8

Skill Claude CodeCodex

Squash-merge the feature commits into dev, regenerate docstrings, and verify the whole suite plus whole-suite stubtest are clean.

11 27d ago A 31 tokens original MIT

model-data-schema

13

nullhack/temple8

Skill Claude CodeCodex

Author the persistence schema as a binding contract from the captured external shapes and the interview — before any test stub is written.

11 27d ago A 28 tokens original MIT

publish-release

14

nullhack/temple8

Skill Claude CodeCodex

Publish the delivered batch as release notes, a PR to main, or a tagged release.

11 27d ago A 21 tokens original MIT

record-cassette

15

nullhack/temple8

Skill Claude CodeCodex

Execute the probe against the real service and record the exchange into a committed cassette, scrubbed of secrets and volatility.

11 27d ago A 28 tokens original MIT

record-decision

16

nullhack/temple8

Skill Claude CodeCodex

Author (or amend) an Architecture Decision Record for a load-bearing architectural decision, in place, with a change log.

11 27d ago A 28 tokens original MIT

refactor-green

17

nullhack/temple8

Skill Claude CodeCodex

Improve the source structure under green tests, with the .pyi fixed and the tests untouched.

11 27d ago A 23 tokens original MIT

refresh-cycle

18

nullhack/temple8

Skill Claude CodeCodex

Close the pipeline cycle: regenerate the living spec from current tests, summarize the carry-over cache files, regenerate source docstrings then strip all .py so the next cycle starts compact.

11 27d ago A 39 tokens original MIT

research-provider

19

nullhack/temple8

Skill Claude CodeCodex

Ground one external service in its real behaviour by reading the provider's official docs and determining its access shape, before any probe code is written.

11 27d ago A 31 tokens original MIT

nullhack/temple8

Skill Claude CodeCodex

Gate the implementation against its contract for correctness, quality, drift, and green tests.

11 27d ago A 21 tokens original MIT

review-test-stubs

21

nullhack/temple8

Skill Claude CodeCodex

Review the test stubs for coverage, scope, vacuous-assertion freedom, finding-grounded scope, and happy-path completeness against the interview and the modeled schema — not for code quality.

11 27d ago A 44 tokens original MIT

select-build-target

22

nullhack/temple8

Skill Claude CodeCodex

Pull the next source contract to build from the pending backlog, respecting outside-in dependency order.

11 27d ago A 22 tokens original MIT

nullhack/temple8

Skill Claude CodeCodex

Pick the next external service to probe by subtracting already-captured services from those the interview named.

11 27d ago A 25 tokens original MIT

ship-unit

24

nullhack/temple8

Skill Claude CodeCodex

Commit the built unit as one logical change with a descriptive imperative message.

11 27d ago A 17 tokens original MIT