Helder Burato Berto 介紹 AI 編碼工作流程 v3：將提示詞改為技能、提醒改為檢查

My AI coding workflow changes every few months, so I give it version numbers. New tools ship, models get better, and steps that needed hand-holding last spring now run on their own.

v1 was plan mode and a hand-written SPEC.md. v2 turned that into TracerKit. This post is v3: every step now lives in helderberto/agent-skills.

The idea of v3 fits in one line: each step that used to be a prompt is now a skill, and each "please remember to" is now a check that fails.

Why I moved off TracerKit (v2)

TracerKit worked, but it was a separate tool with its own release cycle. Every tweak to a step meant a change there, a release, and an update in each project. I wanted a simpler way to ship updates and add new skills.

I was already keeping my other skills in agent-skills. Moving the spec flow next to them put everything in one place. Now changing a step or adding a skill is one commit.

The ideas from TracerKit survived: interviews before specs, tracer-bullet tickets, verification before a task counts as done. They live in the same repo as the rest of my skills.

Standing on two repos

I didn't design v3 from scratch. Most of it comes from two repos, and I took what I think is the best of each.

From Matt Pocock's skills I took the shape of the flow:

grill-me, the interview that runs until a plan has no open branches
to-spec and to-tickets, with tracer-bullet tickets and blocking links
diagnosing-bugs, the phased debugging loop
tdd, prototype, domain-modeling, codebase-design and retro

From Addy Osmani's agent-skills I took the engineering depth inside each step:

frontend-ui-engineering, for decisions to make before writing a component
source-driven-development, so code follows the docs for the installed version
security-and-hardening and performance-optimization

Then I cut each one down to what changes the agent's behavior in my projects, and gave them one namespace: /hb:.

The flow at a glance

A feature moves through eight commands:

flowchart LR
  accTitle: The v3 flow
  accDescr: Plan with triage, grill, to-spec and to-tickets. Build with build and review. Ship with to-pr and retro. Small fixes skip from triage straight to build.
  subgraph Plan
    direction TB
    triage --> grill --> spec[to-spec] --> tickets[to-tickets]
  end
  subgraph Build
    direction TB
    build --> review
  end
  subgraph Ship
    direction TB
    pr[to-pr] --> retro
  end
  Plan --> Build --> Ship

Not every task needs all of them. /hb:triage sizes the work and names where to start. A small fix goes straight to /hb:build.

Skills replace prompts

I no longer write the prompts from v1. I wrote them once, as skills, and now I refine the skills. I made the case for this in Skills Are the New CLI.

Take the same dark mode toggle. In v1, I opened plan mode and wrote a paragraph asking Claude to discuss the approach and generate a spec. Now it starts with one command:

/hb:grill dark mode

The grill interviews me in rounds. Each round asks every question I can answer right now, each with a recommended answer, so a bare "yes" accepts it. Settled terms go to a glossary, and hard-to-reverse decisions become ADRs as they land.

Then the conversation becomes artifacts:

/hb:to-spec dark-mode
/hb:to-tickets dark-mode

The spec lands in .specs/specs/dark-mode.md. The tickets are thin vertical slices with blocking edges, so the agent knows which one is unblocked next. The v1 checklist is still there, but now it has an order.

Building is one command too:

/hb:build dark-mode

It takes the next unblocked ticket, works test-first, runs the project's checks and commits. With --all, it fans tickets out to parallel subagents after one approval.

Two commands close it out. /hb:review sends the diff to several reviewers and merges their findings into one ranked verdict. /hb:to-pr runs the checks, pushes, opens the PR and watches CI.

Guardrails over instructions

Instructions in a prompt get skipped under pressure. A check that fails does not. So most of my guardrails are things that exit with an error:

/hb:check runs the project's own lint, types and tests before every commit
Coverage limits fail the build, so "add tests" is never a request
hitl tickets stop /hb:build --all before work that needs a human
/hb:safe-repo --diff scans the branch for secrets before a PR goes up
harden lists changes that need my approval first: auth, PII, CORS, file uploads

The agent can be fast because it can't quietly skip these. I wrote more about why this matters in Code Got Cheap. Review Didn't.

When something breaks

/hb:debug has one rule I now follow without an agent too: no theory before a feedback loop.

Before reading code to guess a cause, the agent has to show one command that reproduces the bug. It must fail on the exact symptom, give the same result every run, and finish in seconds. A failing test, a curl, a headless browser script.

Only then does it list 3 to 5 ranked hypotheses, each with a prediction that could prove it wrong. That stops the agent from fixing the first plausible cause, which is the habit that wasted most of my debugging sessions.

flowchart TD
  accTitle: The debug loop
  accDescr: Build a feedback loop that fails, reproduce and minimize, list ranked hypotheses, test each one against the loop until it goes green, then fix and keep the loop as a regression test.
  loop[Failing loop] --> repro[Reproduce + minimize] --> hyp[3-5 ranked hypotheses]
  hyp --> test{Loop goes green?}
  test -- no, next hypothesis --> hyp
  test -- yes --> fix[Fix + regression test]

The flow improves itself

The last step is /hb:retro. It reads the session and suggests changes to the environment, not the code: a missing check, a rule in AGENTS.md that should be a lint rule, a file the agent took too long to find.

This is where moving off TracerKit pays off. A retro finding becomes a one-line edit in agent-skills, and every project picks it up on the next update.

Wrapping up

The spec is still at the center, as it was in v1. What changed is everything around it. The prompts I kept retyping are skills, and the reminders I kept giving are checks.

This flow will change again with the next tool or model. When it does, it will be a commit to agent-skills, and v4.

Related: