fix(sf): move add-tests.md skillActivation from dangling end to step 0
Same pattern fixed in scan.md last fire. The {{skillActivation}}
placeholder was the very last line of add-tests.md, after the
'Report sf-internal observations' section, so the default activation
sentence the prompt-loader injects landed where the agent only reads
it AFTER finishing test generation. Move to Instructions step 0 so
skills are activated before code reading begins.
Confirmed via sweep: no more prompts have a dangling {{skillActivation}}
at end-of-file.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
ba4bab1034
commit
416eaf8d12
1 changed files with 1 additions and 2 deletions
|
|
@ -16,6 +16,7 @@ You are generating tests for recently completed SF work.
|
|||
|
||||
## Instructions
|
||||
|
||||
0. {{skillActivation}}
|
||||
1. Read the slice summary above to understand what was built
|
||||
2. Identify the source files that were created or modified for this slice
|
||||
3. Read the implementation code to understand behavior, edge cases, and error paths
|
||||
|
|
@ -35,5 +36,3 @@ You are generating tests for recently completed SF work.
|
|||
### Report sf-internal observations
|
||||
|
||||
If during this unit you observe sf-the-tool friction — ambiguous prompts, missing context, misleading instructions, surprising behavior, prompt-quality issues, or improvement ideas — file them via `sf_self_report` before sealing the unit. This is the only way these observations reach forge's backlog and get triaged. Over-reporting is preferred to under-reporting; dedup happens later. Do NOT use this to file bugs in the user's project; only sf-the-tool itself. Do NOT autonomously act on or fix existing backlog entries — your scope is your unit.
|
||||
|
||||
{{skillActivation}}
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue