c0nant Ask Skills
You don't remember every skill, so ask.
A flow is a path through the skills. Most paths run along one main flow, and an on-ramp merges onto it. Everything else is standalone.
The main flow: idea → ship
The route most work travels. You have an idea and want it built.
/grill-with-docssharpens the idea by interview. Start here whenever you are working in a working directory: it's stateful, retaining what it learns inCONTEXT.mdand ADRs. (No working directory? Use/grill-meinstead, covered under Standalone. Both run the same/grillingprimitive;grill-with-docsis the one that leaves a paper trail, which makes it the better of the two whenever a repo is there to leave it in.)Branch: can you settle every question in conversation? If a question needs a runnable answer (state, business logic, a UI you have to see), detour through a prototype, bridged by
/handoffin both directions (a prototype lives in its own directory, which is exactly what/handoffis for; see Phase boundaries):/handoffout, then open a fresh session against that file,/prototypeto answer the question with throwaway code,/handoffback what you learned, and reference it from the original idea thread.
Branch: is this a multi-session build?
Yes →
/to-spec(turn the thread into a spec), then/to-ticketsto split it into tracer-bullet tickets, each declaring its blocking edges. On a local tracker that's one file per ticket under.scratch/<feature>/issues/, worked blockers-first by hand; on a real tracker the edges become native blocking links, so any ticket whose blockers are done can be grabbed: kick off/implementper ticket,/clearing context between each one. Each ticket is self-contained, so the last one's context is disposable.No →
/implementright here, in the same context window.
Either way,
/implementbuilds each issue by driving/tddinternally: one red-green slice at a time, then closes out by running/review-axes, a two-axis review (Standards + Spec) of the diff, before committing. Reach for/tddon its own when you just want to build a concrete behaviour test-first without a full spec, and/review-axeson its own whenever you want to review a branch against a fixed point./review-axesis for your own work, it judges the diff against the standards you follow and the spec you were given. Reviewing someone else's merge request is a different job: see/review-mrunder Standalone.
Context hygiene
Keep steps 1–3 in one unbroken context window (don't compact or clear until after /to-tickets) so the grilling, spec, and tickets all build on the same thinking. Each /implement then starts fresh, working from the ticket.
The limit on this is the smart zone: the window (~150k tokens on state-of-the-art models) within which the model still reasons sharply. If a session approaches it before /to-tickets, don't push on degraded; /compact at the nearest phase boundary and carry on (see Phase boundaries).
On-ramps
A starting situation that generates work, then merges onto the main flow.
Something's broken →
/diagnosing-bugs. For the hard ones: the bug that resists a first glance, the intermittent flake, the regression that crept in between two known-good states. It refuses to theorise until it has a tight feedback loop (one command that already goes red on this bug), then fixes with a regression test. When it reports that no good seam exists to lock the bug down, that absence is the finding: take it to/improve-codebase-architectureyourself, after the fix is in.A huge, foggy effort: a greenfield project or a huge feature build, too big for one session →
/wayfinder, the most cognitively demanding flow here. When the way from here to the destination isn't visible yet, it charts a shared map of decision tickets on the issue tracker and resolves them one at a time, producing decisions, not deliverables, until the fog is pushed back and the way is clear. Where/grill-with-docssharpens an idea you can hold in one session, wayfinder is for the idea you can't, and it's slower and denser, so save it for exactly that, never a well-scoped feature.When the map clears, it hands off, it doesn't build: merge onto the main flow at
/to-spec, which collapses the map's linked decisions into a buildable plan, then/to-ticketsand/implementas usual. Looping the map straight into/implementskips that collapse and throws the linked detail away, so go straight to/implementonly when the effort turned out genuinely small.
Codebase health
Not feature work, just upkeep.
/improve-codebase-architecture: run whenever you have a spare moment to keep the codebase good for agents to operate in. It surfaces deepening opportunities; picking one generates an idea you can take into the main flow at/grill-with-docs./tech-debt-map: the wider, colder survey. Sweeps a codebase that grew organically across every axis (architecture, code, business rules, maintainability, testability, performance, security) and leaves a debt map: at most 15 evidence-backed findings ranked by payoff-per-effort, then a four-phase incremental plan. It is a diagnosis, not a refactor, and changes no code. Where/improve-codebase-architecturehunts one class of problem and ends in a grilling session about a single candidate, this one ends in a file you work through over weeks and re-run against to see what moved. Its top rows feed/to-tickets; its structural rows feed/improve-codebase-architecture.
Phase boundaries
A phase is a chunk of work inside a session: the grilling, the implementation, the QA. At the boundary between two of them you have five options, and picking between them is the fuzziest decision in this whole map:
- Continue: stay put. Costs nothing, loses nothing.
/clear: empty the window, when nothing here matters to what's next./handoffwrites a portable markdown file. Narrow: only for a new harness, a new directory, a colleague, or forking a side task mid-phase. What it buys is portability.- Subagent: send a tightly-scoped task to its own window and get a report back.
/compactcompresses this context and seeds a fresh session with it. The default, at the bottom of the tree rather than the first reach.
Read PHASE-BOUNDARIES.md for the ordered tree: the five questions, the reasoning behind each branch, and why the primary-source cost makes Continue the one to rule out first. Make the decision at a boundary; mid-phase, continue or split the rest into subagents.
Standalone
Off the main flow entirely.
/grill-me: the same relentless interview as/grill-with-docs, but stateless: it saves nothing locally and builds noCONTEXT.md. Reach for it when you are not working in a working directory (sharpening a plan, a design, a piece of writing, anything with no repo under it). If you are in a working directory, use/grill-with-docsinstead: it runs the same interview and leaves a paper trail, so it is strictly the better one./grilling: the interview primitive itself: rounds, the frontier, facts are the agent's job and decisions are yours./grill-meand/grill-with-docsare the two named ways in, and/wayfinderand/improve-codebase-architectureall run it internally. Reach for it directly only when you want the interview with no wrapper around it./resolving-merge-conflicts: work an in-progress merge or rebase conflict hunk by hunk, resolving by intent traced to each side's primary source rather than by picking lines, then finish the operation. It never runs--abort. Standalone and off every flow: reach for it when you are already mid-conflict./prototype: a small, throwaway program that answers one design question: does this state model feel right, or what should this UI look like. Throwaway is a constraint on how the code is written, not a promise to destroy it: the answer folds into the real code, and the prototype itself is kept as a primary source on aprototype/<name>branch out of main, pointed at from the implementation issue. It's the detour in step 2 of the main flow, but reach for it any time a design question is hard to settle on paper./research: delegate reading legwork to a background agent: it investigates a question against primary sources, then leaves a cited Markdown file in the repo. Keep working while it reads. The file it produces is something to take into the main flow at/grill-with-docs, research feeds the thinking, it doesn't replace it./frontend-handoff: the change is shipped and another team consumes it. Reads the spec and diff, then emits a pasteable block whose verdict, must change / should change / nothing required, is the one thing the frontend dev needs first. Runs after/implement, and answers "does the front have to touch anything?" without a meeting. It hands over context only; the frontend work itself is a separate task in their repo./to-questionnaire: when the thing blocking you isn't in your head or the codebase but in someone else's, this writes them a questionnaire to fill in. It's the inverse of/grill-me: instead of interviewing you about the subject, it interviews you about the send, who it's going to, what you need back, and aims the questions at the gap. What comes back is material for/grill-with-docsor/to-spec./wizard: for the steps only a human can take: provisioning infrastructure, setting up credentials or CI secrets, clicking through an unfamiliar third-party dashboard, running a one-off migration or cutover. It generates an interactive bash script that opens each URL, captures each value, and writes it into.envand GitHub secrets, so the procedure stops being something you re-explain to an agent every time. Model-invoked, so the agent reaches for it the moment it hits a wall only you can pass. If the agent could just do it itself, it should; this is for where a human is genuinely in the loop./wait-what: the corrective for a message that didn't land. Use it mid-conversation, inside any other skill, and the agent re-pitches what it just said with the context you were missing, in plain English, using theCONTEXT.mdvocabulary. It works after the fact;/grill-with-docsis the upfront cure, because a shared language agreed early is what stops the jargon arriving at all./writing-for-agents: reference for writing documents agents consume: skills, AGENTS.md, pointed-at docs./review-mr: review someone else's merge request (GitLab, GitHub, or two local branches) for bugs, security, performance and design, check it against the task's acceptance criteria, and write a verdict (approve or request changes, and why) plus the findings to a local markdown file. It asks you what the diff can't answer before it judges. Where/review-axesjudges your own diff against the repo's standards and spec, this judges someone else's./delegate-tickets: orchestrate sequential ticket implementation through fresh subagents, one ticket at a time, each required to run/implement. Reach for it once/to-ticketshas produced the tickets and you want the build to run unattended across all of them,/clearing context between each.
Precondition
/setup-skills: run before your first engineering flow to configure the issue tracker, triage labels, doc layout, and project.claude/settings.jsondeny rules for destructive git. Custom issue trackers also work./setup-solid: optional, once per repo. Writes a SOLID section intoCLAUDE.mdthat binds every later flow: architecture-level, language-agnostic, and scoped by the boy scout rule, SOLID lands on new code and on the code a change already touches, so the codebase converges a change at a time. Where/improve-codebase-architecturefinds a refactor to do, this sets the standard the code is written to.