b200-flash-attention4-planner
b200-flash-attention4-planner is a Model training & evaluation skill for AI agents, published by mirage-project in the mirage repository on GitHub. Skillspace rates b200-flash-attention4-planner D (66/100) and it passed the safety scan; the rating is based on static analysis only.
Use when the user wants to design or extend a FlashAttention-style forward kernel on B200/Blackwell, involving the two MMAs QKᵀ and PV, online softmax, S/P/O in TMEM, warp roles, causal mask, GQA, tile scheduling, or final normalization. Outputs the algorithm state, tile graph, barrier graph, and validation plan. Not for cases that only use off-the-shelf framework operators, where the full backward is not yet defined, or for ordinary dense GEMM.
- Grade
- D
- Quality
- 66 / 100
- Safety
- Passed
- GitHub stars
- 2,490
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 84 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.