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.
Plugin learn from marketplace tkstack in Tyler-R-Kendrick/tkstack. Commands read from the repo's manifest — 8 days ago.
learnLearn 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 prov
codifyCompile a prompt, Markdown procedure, or skill into a verified executable workflow lock artifact. Use for /codify, transpile this prompt, compile Markdown to code, or cache a procedure so subsequent runs execute code with minimal inference. Owns the shared workflow templates and Vercel AI SDK runtim
flowifyTurn a demonstrated procedure or explicit request into a reusable executable workflow using an existing DSL. Use for /flowify, automate this workflow, MAF declarative YAML, or Grok-style Rhai definitions. Prefer deterministic code bindings, explicit dataflow and failure gates, bounded concurrency, r
hookifyTurn an explicit rule or confirmed recurring correction into a deterministic tool-event hook or workflow gate. Use for /hookify, create a command hook, or prevent this tool behavior. Route native CLI lint-rule authoring to lintify when available. Define precise predicates, replay cases, preserve con
instructifyCreate, adapt, audit, and update scoped agent instructions from explicit preferences or verified workflows. Use for /instructify, turn this into agent instructions, maintain AGENTS.md or CLAUDE.md, and generate native instruction rules. Preserve existing content, choose the right durable layer, and
lintifyCreate, adapt, or configure a rule for a real CLI linter from an explicit standard or correction. Use for /lintify, turn this into a lint rule, enforce this with a linter, or author a Markdown prompt rule. Reuse native checks first, compile Markdown intent into deterministic rules when possible, and
reusifyTurn repeated code into reusable snippets, templates, macros, code generators, modules, libraries, or components. Use /reusify init to bootstrap deterministic code production from an existing codebase, or /reusify for a targeted pattern, repeated boilerplate, T4-style templates, Roslyn incremental g
skillifyCompile a skill or demonstrated procedure into an executable workflow in the skill's scripts folder. Use for /skillify, convert a skill to a tool, capture a workflow, or create/adapt/update an owned skill. Treat Markdown as an intermediary code-mode prompt and invocation index. Prefer deterministic
/learn:codify/learn:flowify/learn:help/learn:hookify/learn:instructify/learn:lintify/learn:model/learn:native_capture/learn:native_experience/learn:native_rule/learn:native_sessions_review/learn:native_show/learn:reusify/learn:skillify/learn:verify/learn:versionRun 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
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.