@aayushchugh/skills 0.1.3 → 0.1.4

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/skills/cases-to-run/SKILL.md +12 -7
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@aayushchugh/skills",
3
- "version": "0.1.3",
3
+ "version": "0.1.4",
4
4
  "description": "The agent skills I use while building real products.",
5
5
  "author": "Ayush Chugh <hey@ayushchugh.com>",
6
6
  "license": "MIT",
package/skills/cases-to-run/SKILL.md CHANGED
@@ -34,17 +34,22 @@ Cover the relevant happy path, failure, boundary, state change, permission, and
34
34
 
35
35
  Test one invalid condition at a time. Combine inputs only when they change the outcome together. One behavior is one case, even when the spec and the code both mention it.
36
36
 
37
- Skip a behavior the spec lists as a non-goal. A missing P0 behavior gets a case, or an open question that says why it cannot be tested yet.
37
+ Skip a behavior the spec lists as a non-goal. A missing behavior that loses data, money, access, or the main flow gets a case, or an open question that says why it cannot be tested yet.
38
38
 
39
- A bug gets one regression case: it fails on the current behavior and passes once the expected behavior is true. A state flow gets the valid path plus the invalid transitions a person can actually attempt.
39
+ A bug gets one case: it fails now and passes once the expected behavior is true. A flow gets the valid path plus the invalid steps a person can actually try.
40
+
41
+ These rules stay inside the skill. Do not print them as labels on a case.
40
42
 
41
43
  ## The list
42
44
 
43
- The default is a bullet list to verify by hand. Order it P0, then P1, then P2. Each bullet is the behavior and the expected result.
45
+ Each case has these parts, in this order, in plain language a person can follow without the codebase:
46
+
47
+ - **Case:** a short name of the behavior.
48
+ - **Prerequisites:** only when the case needs a starting state. Leave this out when there is none.
49
+ - **Description:** one or two sentences of what should happen, including the result a person can see.
50
+ - **Steps to verify:** numbered actions. The last step says what to look at and what should be true.
44
51
 
45
- - P0: data loss, money, access, a broken primary flow, or an existing caller that would regress.
46
- - P1: a common failure or a boundary.
47
- - P2: a rare edge.
52
+ No priority, no tags, no source line, and no separate test-data or expected-result field. Do not use a word such as journal or handler unless the product shows that word on screen.
48
53
 
49
54
  ## Code tests
50
55
 
@@ -52,7 +57,7 @@ Write code tests only when the user asks for them. Name the behaviors. `no-slop`
52
57
 
53
58
  ## Summary
54
59
 
55
- Counts by priority, and anything left uncovered. Do not claim complete coverage when the source is ambiguous.
60
+ Say what is still uncovered. Do not claim complete coverage when the source is ambiguous.
56
61
 
57
62
  ## Replies
58
63