squid

Bootstrap a new repo or component from the opinionated spec library (mode=create), or audit an existing scaffolded repo for drift against the scaffold rules (mode=evaluate, report-only).

Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals `/squid-refactor` can consume directly.

Plan a refactor as an ordered, commit-grain Tasks Plan with structural acceptance criteria (suite green at every step, no behaviour diff) that `/squid-implement-night` can execute end-to-end.

Bug intake — localise the suspected code, capture a deterministic reproducer, and emit a groomed bug task with a regression-test acceptance criterion, ready for /squid-implement-task or the full pipeline.

Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan, or when the user says "/squid-implement-night".

Implement one task — or a whole list / an approved Tasks Plan — via the inner SWE↔Tester loop, committing each task on PASS. Use when one or more GROOMED tasks are ready to build, or the user says "/squid-implement-task". To plan a feature first use /squid-plan; for the full end-to-end pipeline use /squid-implement-night.

Turn a raw feature spec into an approved Tasks Plan — grill the spec, have the Product Architect groom draft tasks (+ optional ADR and glossary additions), then run ONE human gate that decides everything touching the repo: tasks + storage, ADR, glossary, worktree, and which build to run.

Push the committed feature branch, create or update its PR, then run Product Architect acceptance and PR-Reviewer on it. Output: a clean PR with no blockers, or ONE rollup task. Trigger after a feature's tasks are implemented and committed, or when the user says "/squid-review".

Analyze developer corrections from the current coding session and persist lessons learned as rules in AGENTS.md files or memory. Use at the end of a session after the developer corrected your work, when they say "squid-self-improve", ask to capture what was learned, or ask you to reflect on mistakes and extract patterns from their edits.

Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage.

Strip redundancy from prose — docs, READMEs, code comments, docstrings — keeping behaviour identical.

Shrink the memory files sessions load — the root AGENTS.md plus every nested AGENTS.md / CLAUDE.md — to the minimum words that state the same rules: compress wording, delete duplicates and harness-enforced claims, merge fragments.

Drive CI green on a pushed, review-clean feature PR — On-Call diagnoses failures and hands fix tasks to the SWE. Output: a CI-validated feature PR. Trigger after /squid-review passes, or when the user says "/squid-review-ci".

Shrink an agent harness (.agents/ skills + resources) to the minimum tokens that keep the exact same logic. Never touches resources/datasets/.

Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.