Skip to content

Update skills README with new command names, workflow diagram, and tracking description #1772

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
preinlein wants to merge 1 commit into from
Closed

Update skills README with new command names, workflow diagram, and tracking description #1772

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 14 additions & 34 deletions .claude/skills/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,22 +14,22 @@ Run preflight first. It validates your environment and tells you what to do next

| Skill | Purpose |
|-------|---------|
| `/lading:preflight` | Environment validation - run first every session |
| `/lading:optimize:hunt` | Find optimization targets using profiling data |
| `/lading:optimize:review` | 5-persona peer review before merge |
| `/lading:optimize:validate` | Bug validation with Kani proofs or property tests |
| `/lading:optimize:rescue` | Salvage optimization work lacking benchmarks |
| `/lading-preflight` | Environment validation - run first every session |
| `/lading-optimize-hunt` | Find optimization targets using profiling data |
| `/lading-optimize-review` | 5-persona peer review before merge |
| `/lading-optimize-validate` | Bug validation with Kani proofs or property tests |
| `/lading-optimize-rescue` | Salvage optimization work lacking benchmarks |

## Workflow

```
preflight --> hunt --> [success] --> review --> [approved] --> merge
| |
v v
[bug found] [rejected]
| |
v v
validate record lesson
preflight --> hunt --> [implement] --> review --> submit
| |
v v
[bug found] [approved / rejected]
| |
v v
validate record lesson
```

## Critical Context for LLMs
Expand Down Expand Up @@ -60,35 +60,15 @@ Changes below these thresholds are noise, not optimization.

## Tracking Results

Each skill maintains its own `assets/db.yaml` index with detailed entries in `assets/db/*.yaml`:
Hunt maintains `assets/db.yaml` as the central index with detailed entries in `assets/db/*.yaml`. Review owns the report templates (in `lading-optimize-review/assets/`) and returns filled-in YAML reports; hunt persists them verbatim to `assets/db/`.

```
lading:optimize:hunt/
├── SKILL.md # Instructions
└── assets/
├── db.yaml # Index of all hunts
└── db/
└── payload-prealloc.yaml # Detailed hunt record
```

**assets/db.yaml** (index):
```yaml
entries:
- target: lading_payload::block
technique: prealloc
status: failure
file: assets/db/payload-prealloc.yaml
```

**assets/db/*.yaml** (detail):
```yaml
target: lading_payload::block
technique: prealloc
status: failure
date: 2026-01-14
reason: cold path
lessons: |
Block construction not in hot path for JSON payloads.
└── payload-prealloc.yaml # Detailed hunt report
```

Query past results:
Expand Down
Loading