kris/afv-library
1
0
Fork 0
mirror of https://github.com/forcedotcom/afv-library.git synced 2026-07-30 11:19:27 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: skill selection rule

Browse Source
This commit is contained in:
Jose David Rodriguez Velasco 2026-03-27 10:25:32 -04:00
parent c1cfb9f672
commit 5129e6a4dc
No known key found for this signature in database
GPG Key ID: 92B747E95BDABF79
2 changed files with 31 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
rules/a4v-expert-global-rule.md
View File

@ -17,6 +17,17 @@ Enforce: **skill load -> API context -> file generation** for all Salesforce met
- Search available skills and load the best-matching app-level skill first when the request asks for a Lightning app, end-to-end solution, or a business app spanning multiple metadata types.
- Search available skills and load the best-matching per-type metadata skill first when the request targets individual metadata components.
## Task Planning and Skill Re-evaluation
Before starting metadata generation, create a short plan with clearly separated, atomic tasks.
- Each task must include `task=<name> selected_skill=<exact-skill-name|none>`.
- Determine the most appropriate skill before each task.
- Prefer specialized skills over general skills when both are available.
- Re-evaluate the selected skill after each task completes.
- Switch skills when a different skill is better suited.
- Do not reuse the same skill across unrelated tasks unless it is still the best match.
## Initial Gate
Never create files or generate metadata before completing skill selection.
@ -83,6 +94,7 @@ For each metadata type in scope, whether identified by an app-level skill or req
| Never skip the API context attempt for any type | No schema for those types | Attempt API context for EVERY type |
| Never write using API context alone without a loaded skill | Missing platform constraints | Stop and ask for guidance when no skill exists |
| Never write without recorded `mcp_tools` or `mcp=unavailable` | No evidence of MCP gate completion | Record MCP tool usage before any write |
| Never keep one skill for unrelated tasks | Poor task-skill fit | Re-evaluate and switch skills at each task boundary |
| Never ask more than 1 clarifying question | Token waste | Max 1 question |
| Never skip any gate in the loop (skill load, API context, pre-write, checkpoint) | Wrong artifacts | Follow all mandatory gates in the loop (a-e) |
| Never write with a missing checkpoint | Aware violation | Stop and complete missing step |

19
rules/skill-selection-rule.md Normal file
View File

@ -0,0 +1,19 @@
# SKILL SELECTION RULE
## Task-First Planning
- Create a plan with clearly separated tasks.
- Each task must be small and atomic.
- For each task, explicitly state the skill to use (for example: typescript, api, testing, performance).
- Execute each task with the most appropriate skill.
## Execution Rules
- Re-evaluate the skill before every task.
- Switch skills when needed.
- Do not reuse the same skill across unrelated tasks.
## Selection Behavior
- Before each task, determine the most appropriate skill.
- Do not stay locked into a single skill for the entire plan.
- Switch skills when a different skill is better suited.
- Prefer specialized skills over general ones.
- Re-evaluate skill choice after completing each task.