@plaited/development-skills 0.8.0 → 0.8.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/package.json +1 -1
  2. package/rules/skill-activation.md +12 -4
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@plaited/development-skills",
3
- "version": "0.8.0",
3
+ "version": "0.8.1",
4
4
  "description": "Development skills for Claude Code - TypeScript LSP, code documentation, and validation tools",
5
5
  "license": "ISC",
6
6
  "engines": {
package/rules/skill-activation.md CHANGED
@@ -1,14 +1,22 @@
1
1
  # Skill Activation
2
2
 
3
- **Evaluate before implementing** - Check available skills for relevance before starting work
3
+ **Evaluate on every prompt** - Before any response, tool call, or action, check available skills for relevance
4
4
 
5
5
  **Activation sequence:**
6
6
 
7
7
  1. **Evaluate** - For each skill in `<available_skills>`, assess: `[skill-name] - YES/NO - [reason]`
8
8
  2. **Activate** - Call `Skill(skill-name)` for each relevant skill before proceeding
9
- 3. **Implement** - Begin work only after activation is complete
9
+ 3. **Respond** - Begin response only after activation is complete
10
10
 
11
- *Verify:* Did you check available skills before starting implementation?
11
+ **Applies to all tasks** - Research, explanation, code changes, debugging, review — no exceptions
12
+
13
+ **Decision-point re-evaluation** - Re-evaluate skills at each planning or delegation step:
14
+ - Before entering plan mode
15
+ - Before launching subagents (Task tool)
16
+ - Before starting each task in a task list
17
+ - When the domain shifts mid-task (e.g., from code to evaluation, from schema to grading)
18
+
19
+ *Verify:* Every Task tool call and plan mode entry was preceded by skill evaluation
12
20
  *Fix:* Pause, evaluate skills, activate relevant ones, then continue
13
21
 
14
22
  **Example:**
@@ -21,6 +29,6 @@
21
29
  > Skill(documentation)
22
30
  ```
23
31
 
24
- **Activation before implementation** - Evaluating skills without calling `Skill()` provides no benefit
32
+ **Activation before action** - Evaluating skills without calling `Skill()` provides no benefit
25
33
  *Verify:* Check that `Skill()` was called for each YES evaluation
26
34
  *Fix:* Call `Skill(skill-name)` for skipped activations