Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →code-yeongyu/init-deep
(builtin) Initialize hierarchical AGENTS.md knowledge base
Passed 6 of 12 test cases with the skill, and 2 of 12 without it.
and 14 more in the full report
10 fixed1 passed either way8 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
The script needs to update an existing AGENTS.md in src/components. Should it call the Write tool or the Edit tool?
| Checked | Without skill | With skill |
|---|---|---|
| Selects Edit tool when modifying pre-existing documentation files | Passed | Passed |
| Prohibits Write tool usage when target file already exists on filesystem | Missed | Passed |
The instructions your model reads when the skill loads.
Generate hierarchical AGENTS.md files: root + complexity-scored subdirectories, produced by a size-formula-driven dag map-reduce (quick scanners -> unspecified-high writers) so the main session's context stays flat at any repo size.
/init-deep # Update mode: modify existing + create new where warranted
/init-deep --create-new # Read existing → remove all → regenerate from scratch
/init-deep --max-depth=2 # Limit directory depth (default: 3)
quick scanner nodes extract per-chunk facts into bounded file reports.unspecified-high writer nodes own disjoint subtrees: score, write AGENTS.md files, emit digests.todo init the five phases; start/done each transition in real time.
Measure and compute in ONE eval cell - code, not mental arithmetic:
# Measure (tracked files minus vendored/generated: node_modules, .git, dist,
# build, out, vendor, target, coverage, lockfiles, minified and binary files)
S = total source bytes after exclusions
per_dir = source bytes per directory # bin-packing input
depth = max directory depth # respect --max-depth (default 3)
test cases passed, vs 2 / 12 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.