superpowers-mcp 4.3.2 → 5.1.1
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.
- package/README.md +13 -2
- package/README.zh-TW.md +13 -2
- package/out/server.js +12 -12
- package/package.json +2 -2
- package/skills/brainstorming/SKILL.md +79 -11
- package/skills/brainstorming/scripts/frame-template.html +1 -1
- package/skills/brainstorming/scripts/helper.js +7 -12
- package/skills/brainstorming/scripts/server.cjs +1 -1
- package/skills/brainstorming/scripts/start-server.sh +1 -1
- package/skills/brainstorming/scripts/stop-server.sh +1 -1
- package/skills/brainstorming/spec-document-reviewer-prompt.md +1 -1
- package/skills/brainstorming/visual-companion.md +1 -1
- package/skills/dispatching-parallel-agents/SKILL.md +2 -0
- package/skills/executing-plans/SKILL.md +7 -21
- package/skills/finishing-a-development-branch/SKILL.md +93 -42
- package/skills/requesting-code-review/SKILL.md +8 -10
- package/skills/requesting-code-review/code-reviewer.md +107 -85
- package/skills/subagent-driven-development/SKILL.md +39 -2
- package/skills/subagent-driven-development/code-quality-reviewer-prompt.md +8 -3
- package/skills/subagent-driven-development/implementer-prompt.md +36 -1
- package/skills/systematic-debugging/CREATION-LOG.md +1 -1
- package/skills/systematic-debugging/root-cause-tracing.md +1 -1
- package/skills/using-git-worktrees/SKILL.md +95 -98
- package/skills/using-superpowers/SKILL.md +22 -0
- package/skills/using-superpowers/references/codex-tools.md +59 -0
- package/skills/using-superpowers/references/copilot-tools.md +42 -0
- package/skills/using-superpowers/references/gemini-tools.md +51 -0
- package/skills/writing-plans/SKILL.md +54 -18
- package/skills/writing-plans/plan-document-reviewer-prompt.md +49 -0
- package/skills/writing-skills/SKILL.md +2 -2
- package/skills/writing-skills/anthropic-best-practices.md +2 -2
|
@@ -0,0 +1,49 @@
|
|
|
1
|
+
# Plan Document Reviewer Prompt Template
|
|
2
|
+
|
|
3
|
+
Use this template when dispatching a plan document reviewer subagent.
|
|
4
|
+
|
|
5
|
+
**Purpose:** Verify the plan is complete, matches the spec, and has proper task decomposition.
|
|
6
|
+
|
|
7
|
+
**Dispatch after:** The complete plan is written.
|
|
8
|
+
|
|
9
|
+
```
|
|
10
|
+
Task tool (general-purpose):
|
|
11
|
+
description: "Review plan document"
|
|
12
|
+
prompt: |
|
|
13
|
+
You are a plan document reviewer. Verify this plan is complete and ready for implementation.
|
|
14
|
+
|
|
15
|
+
**Plan to review:** [PLAN_FILE_PATH]
|
|
16
|
+
**Spec for reference:** [SPEC_FILE_PATH]
|
|
17
|
+
|
|
18
|
+
## What to Check
|
|
19
|
+
|
|
20
|
+
| Category | What to Look For |
|
|
21
|
+
|----------|------------------|
|
|
22
|
+
| Completeness | TODOs, placeholders, incomplete tasks, missing steps |
|
|
23
|
+
| Spec Alignment | Plan covers spec requirements, no major scope creep |
|
|
24
|
+
| Task Decomposition | Tasks have clear boundaries, steps are actionable |
|
|
25
|
+
| Buildability | Could an engineer follow this plan without getting stuck? |
|
|
26
|
+
|
|
27
|
+
## Calibration
|
|
28
|
+
|
|
29
|
+
**Only flag issues that would cause real problems during implementation.**
|
|
30
|
+
An implementer building the wrong thing or getting stuck is an issue.
|
|
31
|
+
Minor wording, stylistic preferences, and "nice to have" suggestions are not.
|
|
32
|
+
|
|
33
|
+
Approve unless there are serious gaps — missing requirements from the spec,
|
|
34
|
+
contradictory steps, placeholder content, or tasks so vague they can't be acted on.
|
|
35
|
+
|
|
36
|
+
## Output Format
|
|
37
|
+
|
|
38
|
+
## Plan Review
|
|
39
|
+
|
|
40
|
+
**Status:** Approved | Issues Found
|
|
41
|
+
|
|
42
|
+
**Issues (if any):**
|
|
43
|
+
- [Task X, Step Y]: [specific issue] - [why it matters for implementation]
|
|
44
|
+
|
|
45
|
+
**Recommendations (advisory, do not block approval):**
|
|
46
|
+
- [suggestions for improvement]
|
|
47
|
+
```
|
|
48
|
+
|
|
49
|
+
**Reviewer returns:** Status, Issues (if any), Recommendations
|
|
@@ -93,7 +93,7 @@ skills/
|
|
|
93
93
|
## SKILL.md Structure
|
|
94
94
|
|
|
95
95
|
**Frontmatter (YAML):**
|
|
96
|
-
-
|
|
96
|
+
- Two required fields: `name` and `description` (see [agentskills.io/specification](https://agentskills.io/specification) for all supported fields)
|
|
97
97
|
- Max 1024 characters total
|
|
98
98
|
- `name`: Use letters, numbers, and hyphens only (no parentheses, special chars)
|
|
99
99
|
- `description`: Third-person, describes ONLY when to use (NOT what it does)
|
|
@@ -604,7 +604,7 @@ Deploying untested skills = deploying untested code. It's a violation of quality
|
|
|
604
604
|
|
|
605
605
|
**GREEN Phase - Write Minimal Skill:**
|
|
606
606
|
- [ ] Name uses only letters, numbers, hyphens (no parentheses/special chars)
|
|
607
|
-
- [ ] YAML frontmatter with
|
|
607
|
+
- [ ] YAML frontmatter with required `name` and `description` fields (max 1024 chars; see [spec](https://agentskills.io/specification))
|
|
608
608
|
- [ ] Description starts with "Use when..." and includes specific triggers/symptoms
|
|
609
609
|
- [ ] Description written in third person
|
|
610
610
|
- [ ] Keywords throughout for search (errors, symptoms, tools)
|
|
@@ -144,7 +144,7 @@ What works perfectly for Opus might need more detail for Haiku. If you plan to u
|
|
|
144
144
|
## Skill structure
|
|
145
145
|
|
|
146
146
|
<Note>
|
|
147
|
-
**YAML Frontmatter**: The SKILL.md frontmatter
|
|
147
|
+
**YAML Frontmatter**: The SKILL.md frontmatter requires two fields:
|
|
148
148
|
|
|
149
149
|
* `name` - Human-readable name of the Skill (64 characters maximum)
|
|
150
150
|
* `description` - One-line description of what the Skill does and when to use it (1024 characters maximum)
|
|
@@ -1092,7 +1092,7 @@ reader = PdfReader("file.pdf")
|
|
|
1092
1092
|
|
|
1093
1093
|
### YAML frontmatter requirements
|
|
1094
1094
|
|
|
1095
|
-
The SKILL.md frontmatter
|
|
1095
|
+
The SKILL.md frontmatter requires `name` (64 characters max) and `description` (1024 characters max) fields. See the [Skills overview](/en/docs/agents-and-tools/agent-skills/overview#skill-structure) for complete structure details.
|
|
1096
1096
|
|
|
1097
1097
|
### Token budgets
|
|
1098
1098
|
|