creator/claudekit
1
0
Fork 0
mirror of https://github.com/duthaho/claudekit.git synced 2026-07-28 07:31:00 +03:00
Code Issues Packages Projects Releases Wiki Activity

feat: enhanced the writing skills

Browse Source
This commit is contained in:
duthaho
2026-04-18 18:50:39 +07:00
parent 7fa9a48c6c
commit 09538078e7
136 changed files with 10175 additions and 7947 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/agents/brainstormer.md
+1 -1
View File
@@ -277,7 +277,7 @@ Starting from fundamentals, what's the best way to solve this?
For enhanced interactive brainstorming, use the superpowers methodology:
**Reference**: `.claude/skills/methodology/brainstorming/SKILL.md`
**Reference**: `.claude/skills/brainstorming/SKILL.md`
Key principles from superpowers methodology:
- **One question per message**: Ask single questions, wait for response
.claude/agents/code-reviewer.md
+3 -3
View File
@@ -183,7 +183,7 @@ For enhanced code review workflows, use the superpowers methodology:
### Requesting Reviews
**Reference**: `.claude/skills/methodology/requesting-code-review/SKILL.md`
**Reference**: `.claude/skills/requesting-code-review/SKILL.md`
Include in review requests:
- Scope definition (files, lines changed)
@@ -193,7 +193,7 @@ Include in review requests:
### Receiving Reviews
**Reference**: `.claude/skills/methodology/receiving-code-review/SKILL.md`
**Reference**: `.claude/skills/receiving-code-review/SKILL.md`
Process feedback by category:
- **Critical**: Must fix before proceeding
@@ -204,7 +204,7 @@ Process feedback by category:
When using subagent-driven development:
**Reference**: `.claude/skills/methodology/executing-plans/SKILL.md`
**Reference**: `.claude/skills/executing-plans/SKILL.md`
- Review after each task completion
- Fresh agent for unbiased review
.claude/agents/debugger.md
+3 -3
View File
@@ -236,7 +236,7 @@ This agent works with:
For enhanced systematic debugging, use the superpowers methodology:
**Reference**: `.claude/skills/methodology/systematic-debugging/SKILL.md`
**Reference**: `.claude/skills/systematic-debugging/SKILL.md`
### Four-Phase Methodology
@@ -255,8 +255,8 @@ If 3+ consecutive fixes fail, STOP - this is an architectural problem.
### Additional Skills
- **Root cause tracing**: `.claude/skills/methodology/root-cause-tracing/SKILL.md`
- **Defense in depth**: `.claude/skills/methodology/defense-in-depth/SKILL.md`
- **Root cause tracing**: `.claude/skills/root-cause-tracing/SKILL.md`
- **Defense in depth**: `.claude/skills/defense-in-depth/SKILL.md`
<!-- CUSTOMIZATION POINT -->
## Project-Specific Overrides
.claude/agents/planner.md
+2 -2
View File
@@ -144,7 +144,7 @@ Implement JWT-based authentication with login, logout, and token refresh capabil
For enhanced detailed planning, use the superpowers methodology:
**Reference**: `.claude/skills/methodology/writing-plans/SKILL.md`
**Reference**: `.claude/skills/writing-plans/SKILL.md`
### Detailed Mode (2-5 min tasks)
@@ -161,7 +161,7 @@ After creating a detailed plan:
- **Subagent-driven**: Use `executing-plans` skill for automated execution
- **Manual**: Developer follows plan sequentially
**Reference**: `.claude/skills/methodology/executing-plans/SKILL.md`
**Reference**: `.claude/skills/executing-plans/SKILL.md`
<!-- CUSTOMIZATION POINT -->
## Project-Specific Overrides
.claude/agents/tester.md
+3 -3
View File
@@ -266,7 +266,7 @@ For enhanced testing practices, use the superpowers methodology:
### Test-Driven Development
**Reference**: `.claude/skills/methodology/test-driven-development/SKILL.md`
**Reference**: `.claude/skills/test-driven-development/SKILL.md`
Key principles:
- **NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST**
@@ -277,7 +277,7 @@ Key principles:
### Verification
**Reference**: `.claude/skills/methodology/verification-before-completion/SKILL.md`
**Reference**: `.claude/skills/verification-before-completion/SKILL.md`
Before claiming tests pass:
1. Identify the command that proves assertion
@@ -288,7 +288,7 @@ Before claiming tests pass:
### Testing Anti-Patterns
**Reference**: `.claude/skills/methodology/testing-anti-patterns/SKILL.md`
**Reference**: `.claude/skills/testing-anti-patterns/SKILL.md`
Avoid these mistakes:
1. Testing mock behavior instead of real code