tkstack

Learn from user corrections, frustrations, workflow outcomes, and temporary .tkstack sessions. Use for /learn, help, repeated instructions, a rejected approach, session consolidation, report-only audits, or direct skillify/hookify/instructify/flowify/lintify/reusify/codify subcommands. Preserve provenance, extract scoped reasoning rules, and turn verified procedural lessons into reviewable reusable artifacts shared across harnesses.

8 skills · 16 commands

Run the BDD/contract lifecycle or scoped planning, architecture, verification, review, delivery, and handoff. Invoke only when the user explicitly asks for /sdlc or one of those modes. Coordinate durable SQLite task DAGs with fenced leases and explicit development-to-requirements/ADR revisions. Full mode retains sparse COW worktrees, independent evidence review, and squash-merged stacked PRs.

1 skill · 15 commands

Identify and correct AI slop in writing, code, tests, websites, images, video, and audio. Use for /unslop, output grading, anti-slop review, or whenever the user identifies a slop pattern. Record actual corrections in the shared steering ledger, extract a scoped reusable criterion, and grade against the evolving catalog with artifact evidence and legitimate exceptions.

1 skill · 7 commands

Run a bounded, evidence-driven improvement loop for code, prompts, skills, websites, or generated media. Invoke only when the user explicitly asks for /hill-climb or a measured improvement loop. Freeze a sensitive evaluation, measure baseline noise, change one hypothesis at a time, keep or revert from evidence, and confirm the winner on untouched cases.

1 skill · 5 commands

Create or maintain source-grounded repository documentation, a knowledge wiki, a glossary, an ADR, or a resumable task handoff. Use for documentation maintenance and knowledge capture. Agent policy belongs in instructify; UI design-system capture belongs in open-design; ordinary articles belong in write.

1 skill · 4 commands

Plan and produce images, video, audio, brand assets, and product media with explicit deliverables and actual output inspection. Use for fal.ai or a provider-neutral media production brief. Preserve explicit Higgsfield or other provider selections and use their real adapters.

1 skill · 4 commands

Use Headroom for explicit reversible context compression, CCR retrieval, or agent wrapping. Verify original-context fidelity and actual runtime readiness while preserving provider and account routing.

1 skill · 4 commands

Investigate how a system works, why a decision was made, an unfamiliar API, or the cause of a bug or performance regression. Use for source-grounded explanations, research, diagnosis, and captured-trace analysis. Produces cited findings and explicit unknowns; a diagnosis request alone does not authorize fixes.

1 skill · 4 commands

Design or refine interfaces, prototypes, slides, and design systems using a portable brief and artifact-review workflow. Use for UI/UX creation, redesign, critique, or OpenDesign work. Explicit OpenDesign requests retain that provider and its actual runtime.

1 skill · 4 commands

Use Rust Token Killer to filter shell output, inspect measured token savings, or configure RTK integration. Preserve command semantics, native permissions, and an unfiltered route for exact evidence.

1 skill · 4 commands

Apply tkstack's personal engineering principles when designing, implementing, or reviewing code, skills, hooks, rules, workflows, and harness configuration. Prefer deterministic code and explicit rules, then narrowly scoped decision models or APIs, with LLMs and agents as the last resort. Design all code for safe bounded concurrency and parallel composition.

1 skill · 4 commands

Develop a human-facing article, explanation, proposal, or narrative from supplied ideas or source material. Use for drafting, shaping an argument, or a collaborative writing session. Not for ordinary file writes, agent instructions, repository reference maintenance, or anti-slop grading alone.

1 skill · 4 commands