using-superjawn

Name: using-superjawn
Author: jamditis

336stars57forks

How to install using-superjawn?

jamditis/claude-skills-journalism/using-superjawn

$npx -y skills add jamditis/claude-skills-journalism --skill using-superjawn

Installs into the current project.

Summary

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Files · 1

View on GitHub

SKILL.md

1	<!--
2	Adapted from obra/superpowers using-superpowers skill (v5.0.7), MIT-licensed,
3	copyright 2025 Jesse Vincent. Modifications copyright 2026 Joe Amditis.
4	v0.6.0 ports as a renamed consumer skill: directory + frontmatter `name:` field
5	move from `using-superpowers` to `using-superjawn` so the bootstrap skill
6	matches the local plugin's identity. Two body references to the system name
7	("Superpowers skills") are rebranded to "superjawn skills" to match. The rename
8	makes byte-parity with upstream impossible by definition; `skill_md_parity` is
9	false in the manifest and `upstream_name` is set to `using-superpowers` so the
10	validator's parity + supporting-file checks resolve against the right upstream
11	directory.
12	See CREDITS.md.
13	-->
14
15	<SUBAGENT-STOP>
16	If you were dispatched as a subagent to execute a specific task, skip this skill.
17	</SUBAGENT-STOP>
18
19	<EXTREMELY-IMPORTANT>
20	If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.
21
22	IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
23
24	This is not negotiable. This is not optional. You cannot rationalize your way out of this.
25	</EXTREMELY-IMPORTANT>
26
27	## Instruction Priority
28
29	superjawn skills override default system prompt behavior, but user instructions always take precedence:
30
31	1. User's explicit instructions (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority
32	2. superjawn skills — override default system behavior where they conflict
33	3. Default system prompt — lowest priority
34
35	If CLAUDE.md, GEMINI.md, or AGENTS.md says "don't use TDD" and a skill says "always use TDD," follow the user's instructions. The user is in control.
36
37	## How to Access Skills
38
39	In Claude Code: Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.
40
41	In Copilot CLI: Use the `skill` tool. Skills are auto-discovered from installed plugins. The `skill` tool works the same as Claude Code's `Skill` tool.
42
43	In Gemini CLI: Skills activate via the `activate_skill` tool. Gemini loads skill metadata at session start and activates the full content on demand.
44
45	In other environments: Check your platform's documentation for how skills are loaded.
46
47	## Platform Adaptation
48
49	Skills use Claude Code tool names. Non-CC platforms: see `references/copilot-tools.md` (Copilot CLI), `references/codex-tools.md` (Codex) for tool equivalents. Gemini CLI users get the tool mapping loaded automatically via GEMINI.md.
50
51	# Using Skills
52
53	## The Rule
54
55	Invoke relevant or requested skills BEFORE any response or action. Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.
56
57	```dot
58	digraph skill_flow {
59	"User message received" [shape=doublecircle];
60	"About to EnterPlanMode?" [shape=doublecircle];
61	"Already brainstormed?" [shape=diamond];
62	"Invoke brainstorming skill" [shape=box];
63	"Might any skill apply?" [shape=diamond];
64	"Invoke Skill tool" [shape=box];
65	"Announce: 'Using [skill] to [purpose]'" [shape=box];
66	"Has checklist?" [shape=diamond];
67	"Create TodoWrite todo per item" [shape=box];
68	"Follow skill exactly" [shape=box];
69	"Respond (including clarifications)" [shape=doublecircle];
70
71	"About to EnterPlanMode?" -> "Already brainstormed?";
72	"Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
73	"Already brainstormed?" -> "Might any skill apply?" [label="yes"];
74	"Invoke brainstorming skill" -> "Might any skill apply?";
75
76	"User message received" -> "Might any skill apply?";
77	"Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
78	"Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
79	"Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
80	"Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
81	"Has checklist?" -> "Create TodoWrite todo per item" [label="yes"];
82	"Has checklist?" -> "Follow skill exactly" [label="no"];
83	"Create TodoWrite todo per item" -> "Follow skill exactly";
84	}
85	```
86
87	## Red Flags
88
89	These thoughts mean STOP—you're rationalizing:
90
91	\| Thought \| Reality \|
92	\|---------\|---------\|
93	\| "This is just a simple question" \| Questions are tasks. Check for skills. \|
94	\| "I need more context first" \| Skill check comes BEFORE clarifying questions. \|
95	\| "Let me explore the codebase first" \| Skills tell you HOW to explore. Check first. \|
96	\| "I can check git/files quickly" \| Files lack conversation context. Check for skills. \|
97	\| "Let me gather information first" \| Skills tell you HOW to gather information. \|
98	\| "This doesn't need a formal skill" \| If a skill ex

People who liked this also viewed

6 picks

Type

lark-openapi-explorer飞书/Lark 原生 OpenAPI 探索：从官方文档库中挖掘未经 CLI 封装的原生 OpenAPI 接口。当用户的需求无法被现有 lark-* skill 或 lark-cli 已注册命令满足，需要查找并调用原生飞书 OpenAPI 时使用。SkillsJul 2026378k16k
lark-skill-maker创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。SkillsJul 2026377k16k
azure-cost-optimizationOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.SkillsJul 2026209k1.3k
vercel-react-native-skillsVercel's official collection of agent skillsSkillsJul 2026172k29k
mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate externaSkillsJul 202693k163k
gws-sharedgws CLI: Shared patterns for authentication, global flags, and output formatting.SkillsJul 202653k30k

using-superjawn

336stars57forks

View on GitHub

How to install using-superjawn?

jamditis/claude-skills-journalism/using-superjawn

$npx -y skills add jamditis/claude-skills-journalism --skill using-superjawn

Installs into the current project.

Summary

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Files · 1

View on GitHub

SKILL.md

1	<!--
2	Adapted from obra/superpowers using-superpowers skill (v5.0.7), MIT-licensed,
3	copyright 2025 Jesse Vincent. Modifications copyright 2026 Joe Amditis.
4	v0.6.0 ports as a renamed consumer skill: directory + frontmatter `name:` field
5	move from `using-superpowers` to `using-superjawn` so the bootstrap skill
6	matches the local plugin's identity. Two body references to the system name
7	("Superpowers skills") are rebranded to "superjawn skills" to match. The rename
8	makes byte-parity with upstream impossible by definition; `skill_md_parity` is
9	false in the manifest and `upstream_name` is set to `using-superpowers` so the
10	validator's parity + supporting-file checks resolve against the right upstream
11	directory.
12	See CREDITS.md.
13	-->
14
15	<SUBAGENT-STOP>
16	If you were dispatched as a subagent to execute a specific task, skip this skill.
17	</SUBAGENT-STOP>
18
19	<EXTREMELY-IMPORTANT>
20	If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.
21
22	IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
23
24	This is not negotiable. This is not optional. You cannot rationalize your way out of this.
25	</EXTREMELY-IMPORTANT>
26
27	## Instruction Priority
28
29	superjawn skills override default system prompt behavior, but user instructions always take precedence:
30
31	1. User's explicit instructions (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority
32	2. superjawn skills — override default system behavior where they conflict
33	3. Default system prompt — lowest priority
34
35	If CLAUDE.md, GEMINI.md, or AGENTS.md says "don't use TDD" and a skill says "always use TDD," follow the user's instructions. The user is in control.
36
37	## How to Access Skills
38
39	In Claude Code: Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.
40
41	In Copilot CLI: Use the `skill` tool. Skills are auto-discovered from installed plugins. The `skill` tool works the same as Claude Code's `Skill` tool.
42
43	In Gemini CLI: Skills activate via the `activate_skill` tool. Gemini loads skill metadata at session start and activates the full content on demand.
44
45	In other environments: Check your platform's documentation for how skills are loaded.
46
47	## Platform Adaptation
48
49	Skills use Claude Code tool names. Non-CC platforms: see `references/copilot-tools.md` (Copilot CLI), `references/codex-tools.md` (Codex) for tool equivalents. Gemini CLI users get the tool mapping loaded automatically via GEMINI.md.
50
51	# Using Skills
52
53	## The Rule
54
55	Invoke relevant or requested skills BEFORE any response or action. Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.
56
57	```dot
58	digraph skill_flow {
59	"User message received" [shape=doublecircle];
60	"About to EnterPlanMode?" [shape=doublecircle];
61	"Already brainstormed?" [shape=diamond];
62	"Invoke brainstorming skill" [shape=box];
63	"Might any skill apply?" [shape=diamond];
64	"Invoke Skill tool" [shape=box];
65	"Announce: 'Using [skill] to [purpose]'" [shape=box];
66	"Has checklist?" [shape=diamond];
67	"Create TodoWrite todo per item" [shape=box];
68	"Follow skill exactly" [shape=box];
69	"Respond (including clarifications)" [shape=doublecircle];
70
71	"About to EnterPlanMode?" -> "Already brainstormed?";
72	"Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
73	"Already brainstormed?" -> "Might any skill apply?" [label="yes"];
74	"Invoke brainstorming skill" -> "Might any skill apply?";
75
76	"User message received" -> "Might any skill apply?";
77	"Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
78	"Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
79	"Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
80	"Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
81	"Has checklist?" -> "Create TodoWrite todo per item" [label="yes"];
82	"Has checklist?" -> "Follow skill exactly" [label="no"];
83	"Create TodoWrite todo per item" -> "Follow skill exactly";
84	}
85	```
86
87	## Red Flags
88
89	These thoughts mean STOP—you're rationalizing:
90
91	\| Thought \| Reality \|
92	\|---------\|---------\|
93	\| "This is just a simple question" \| Questions are tasks. Check for skills. \|
94	\| "I need more context first" \| Skill check comes BEFORE clarifying questions. \|
95	\| "Let me explore the codebase first" \| Skills tell you HOW to explore. Check first. \|
96	\| "I can check git/files quickly" \| Files lack conversation context. Check for skills. \|
97	\| "Let me gather information first" \| Skills tell you HOW to gather information. \|
98	\| "This doesn't need a formal skill" \| If a skill ex

People who liked this also viewed

6 picks

Type