chill/skills
1
0
Fork 0
mirror of https://github.com/anthropics/skills synced 2026-09-18 16:28:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

claude-api skill: Opus 5 effort bullet reserves xhigh-and-above, not high-and-above

Browse Source 
The "start at high, then sweep down" bullet ended with "reserve `high`
and above for tasks where your evals show a quality difference", which
contradicts its own opening. The sibling bullet and the checklist item
both say xhigh/max are the measured-wins tier; align this one.

No-Verification-Needed: markdown-only skill content, no runtime surface
This commit is contained in:
cj
2026-08-17 17:23:14 +00:00
parent 5213442459
commit 35d91f51fa
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
skills/claude-api/shared/model-migration.md
View File

@@ -1005,7 +1005,7 @@ The added tool must already be declared in `tools[]` with `"defer_loading": True
**Effort: the full ladder, and where to start.** Claude Opus 5 supports all five levels — `low`, `medium`, `high`, `xhigh`, `max` — with no beta header. The API default is `high`.
- **Start at `high` (the API default), then sweep down.** `low` and `medium` are unusually effective on this model — strong quality at a fraction of the tokens and latency on many workloads — so treat them as the primary cost/latency lever and reserve `high` and above for tasks where your evals show a quality difference. Effort defaults carried over from a prior model are usually not the right setting here; run a fresh sweep.
- **Start at `high` (the API default), then sweep down.** `low` and `medium` are unusually effective on this model — strong quality at a fraction of the tokens and latency on many workloads — so treat them as the primary cost/latency lever and reserve `xhigh` and above for tasks where your evals show a quality difference. Effort defaults carried over from a prior model are usually not the right setting here; run a fresh sweep.
- **`xhigh` and `max` are for measured wins, not a starting point.** `max` is the top tier for the deepest reasoning and worth testing where capability matters more than spend, but it can show diminishing returns and overthink simpler tasks.
At `xhigh` or `max`, **set a large `max_tokens`** so the model has room to think and act across tool calls and subagents. Start at 64K and tune.