reflect
Turn what this session learned into durable changes to the repository: a lint rule, a test, a check, a skill edit, AGENTS.md or docs/DECISIONS.md. Use when wrapping up a task, after a mistake or a correction, or when the person says reflect or remember this.
How do I install this agent skill?
npx skills add https://github.com/hachej/boring-stack --skill reflectIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill provides a structured process for an agent to reflect on a session and record learnings into the repository. It facilitates maintenance by updating lint rules, architecture documents, and skills. No malicious patterns were detected.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Reflect
Adapted from Poteto's brainmaxxing reflect (MIT, see THIRD_PARTY.md). This
repository has no separate memory vault: what the next agent must know lives in
the repository itself, where it is reviewed like code.
Process
- Scan the session for:
- mistakes made and corrections received;
- the product owner's preferences (how they want the app to behave or read);
- codebase knowledge gained (gotchas, why something is the way it is);
- library or tool quirks (
vendor/boring/, Flue, the model provider); - friction in a skill (boring-app-template, build-app) or in the app's checks;
- repeated manual steps.
- Skip anything trivial or already written down (grep AGENTS.md, docs/, the skills).
- Route each learning (below), smallest durable form first.
- Put the changes in the current branch, or a new one, and say what you changed.
Routing, in this order
- Structure (principle-encode-lessons-in-structure): can it be a lint rule
(
.oxlintrc.json), an architecture rule (scripts/verify/ARCHITECTURE.json), a unit test, averify checkstep, a validator in an agent'sindex.mjs, a law with its evidence (docs/INVARIANTS.md+scripts/verify/VERIFY.json) or a model (formal/)? Then encode it there and write no prose. A mistake an agent repeats becomes a rule inscripts/verify/ARCHITECTURE.json, with the law or decision it enforces, a fix hint, and a fixture intest/unit/architecture.test.mjsproving it fires; better still, make the mistake impossible (a type, a single helper, a constraint) so no rule is needed. - A skill (a pull request on hachej/boring-stack,
skills/<skill>/SKILL.md): the learning is about how a skill's procedure works: fix the procedure. - The feature map (
docs/verify/<area>.md): a gotcha about driving a feature. - docs/DECISIONS.md: a decision and its reason ("we do X because Y; not Z because W").
- AGENTS.md: a rule every agent needs on every task. Keep it short: move detail to a skill.
- Upstream: a gap in
@boring/agent,@boring/filesor@boring/chatgoes to hachej/boring-ui-v3 as an issue or a pull request, never as an edit ofvendor/. - The template (hachej/boring-app): a lesson every new app needs. Say so, so it lands in the template; existing apps take it by a normal pull request.
Summary
## Reflect summary
- Structural: [rules, tests, checks added]
- Skills: [skill files changed, one line each]
- Docs: [DECISIONS / AGENTS / feature map entries]
- Upstream or template: [issues or PRs to open]
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/hachej/boring-stack/reflect">View reflect on skillZs</a>