/SKILL.md
Maintain a per-repo guideline that tracks mistakes, corrections, and what works for Laravel/PHP work. Activates EVERY session, unconditionally. Read the guideline before doing anything. Write to it continuously as you work — not just at session boundaries. Log your own mistakes, not just user corrections. The guideline lives in the repo at `.ai/guidelines/`.
npx skillsauth add ivanfuhr/laravel-progressive-learning laravel-progressive-learningInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You maintain a per-repo markdown guideline that tracks mistakes, corrections, and patterns that work or don't. You read it before doing anything and update it continuously as you work — whenever you learn something worth recording.
This guideline is always active. Every session. No trigger required.
First thing, every session — read .ai/guidelines/learning.md before doing
anything else. Internalize what's there and apply it silently. Don't announce
that you read it. Just apply what you know.
If no guideline exists yet, create one at .ai/guidelines/learning.md:
# laravel-progressive-learning Guideline (Laravel/PHP)
## Corrections
| Date | Source | What Went Wrong | What To Do Instead |
|------|--------|----------------|-------------------|
## User Preferences
- (accumulate here as you learn them)
## Patterns That Work
- (approaches that succeeded)
## Patterns That Don't Work
- (approaches that failed and why)
## Domain Notes
- (project/domain context that matters)
## Laravel/PHP Notes
- (framework-specific rules, conventions, or gotchas)
Adapt the sections to fit the repo's domain. Design something you can usefully consume.
Update the guideline as you work, not just at session start and end. Write to it whenever you learn something worth recording:
The guideline is a living document. Treat it like working memory that persists across sessions, not a journal you write in once.
Log anything that would change your behavior if you read it next session:
Be specific. "Made an error" is useless. "Assumed the API returns a list but
it returns a paginated object with .items" is actionable.
str() and collect() instead of native functions.DB:: unless necessary; prefer Model::query() and transactions.vendor/bin/sail for all Artisan/Composer/PHP/Node commands.Every 5-10 sessions, or when the file exceeds ~150 lines, consolidate:
A 50-line guideline of hard-won rules beats a 500-line log of raw entries.
Early in a session — you misread a function signature and pass args in the wrong order. You catch it yourself. Log it:
| 2026-02-06 | self | Passed (name, id) to createUser but signature is (id, name) | Check function signatures before calling, this codebase doesn't follow conventional arg ordering |
Mid-session — user corrects your import style. Log it:
| 2026-02-06 | user | Used relative imports | This repo uses absolute imports from `src/` — always |
Later — you re-read the guideline before editing another file and use absolute imports without being told. That's the loop working.
IMPORTANT: Instead of creating a logs file, create a Boost guideline in
.ai/guidelines/ (see https://laravel.com/docs/12.x/boost#adding-custom-ai-guidelines)
and then run php artisan boost:update --ansi.
documentation
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]
documentation
Maintain the OpenClaw memory wiki vault with deterministic pages, managed blocks, and source-backed updates.
documentation
Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.
documentation
Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.