skill-master

Name: skill-master
Author: pavel-molyanov

241stars75forks

How to install skill-master?

pavel-molyanov/molyanov-ai-dev/skill-master

$npx -y skills add pavel-molyanov/molyanov-ai-dev --skill skill-master

Installs into the current project.

Summary

Guide for creating/updating skills with specialized knowledge and workflows. Use when: "создай скилл", "измени скилл", "гайд по скиллам", "обнови скилл", "улучши скилл", "create skill", "update skill", "skill guide", "new skill", "how to write a skill

Files · 1

View on GitHub

SKILL.md

1	<!-- Generated by sync-to-codex v1. Do not edit directly. -->
2
3	# Skill Creator
4
5	## Claude-to-Codex Autosync
6
7	Claude-side is the source of truth (`~/.claude/` for global methodology, or a project's `CLAUDE.md` + `.claude/`); Codex-side (`~/.codex/` / `AGENTS.md`) is generated runtime. After editing any `.claude/` methodology file (`skills/`, `agents/`, `commands/`, `shared/`), regenerate Codex:
8
9	```bash
10	~/.claude/scripts/sync-to-codex.sh --apply # global ~/.claude/**
11	~/.claude/scripts/sync-to-codex.sh --project "$PWD" --apply # project .claude/**
12	```
13
14	Commit the generated `.codex/**` / `AGENTS.md` changes together with the source. If sync reports a conflict or validation error, stop and report it.
15
16	Authoring a skill that edits `.claude/`? Paste the block above near the top of its `SKILL.md` so its changes reach Codex too. A skill that never touches `.claude/` (pure analysis, code-writing in a project's own source tree) does not need it.
17
18	Bundled resources and the sync: Markdown files (`SKILL.md`, `references/.md`) are text-adapted during sync (Claude tool names → Codex equivalents). Every other bundled file — `scripts/`, `assets/`, images, data — is copied byte-for-byte, unmodified. So a bundled script must be runtime-agnostic: don't hardcode `.claude` paths or Claude-only tool names, since neither is rewritten in the Codex copy. Reference files relative to the script's own location, and let the surrounding `SKILL.md` prose (which is* adapted) carry any runtime-specific instructions.
19
20	## About Skills
21
22	Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.
23
24	### What Skills Provide
25
26	1. Specialized workflows - Multi-step procedures for specific domains
27	2. Tool integrations - Instructions for working with specific file formats or APIs
28	3. Domain expertise - Company-specific knowledge, schemas, business logic
29	4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks
30
31	## Skill Types
32
33	There are two types of skills based on how they guide Claude's work.
34
35	### Procedural Skills
36
37	Use when the task requires a strict sequence of steps where order matters. Phase 2 depends on Phase 1 completing correctly. Skipping or reordering steps would break the workflow.
38
39	Examples: code-writing (Plan → TDD → Review), project-planning (Interview → Features → Roadmap), tech-spec-planning.
40
41	These skills have explicit phases with checkpoints after each phase to verify completion before proceeding.
42
43	Creating a procedural skill? Read [procedural-skills.md](references/procedural-skills.md) — phase structure, checkpoints, verification patterns.
44
45	### Informational Skills
46
47	Use when providing methodology, knowledge, or guidelines without a strict execution order. The agent reads relevant sections and applies them to the situation. There's no "Phase 1 must complete before Phase 2" — sections are independent.
48
49	Examples: security-auditor (what to check), testing (when to use which test type), company-info (domain knowledge), database-schemas.
50
51	These skills organize content into logical sections with decision frameworks (YES if / NO if) to help the agent choose what applies.
52
53	Creating an informational skill? Read [informational-skills.md](references/informational-skills.md) — section organization, knowledge structure.
54
55	## 1. Discovery
56
57	For new skills or major changes — run discovery interview:
58	- What problem does the skill solve?
59	- What phrases should trigger it?
60	- What should the skill NOT do?
61	- Concrete usage examples
62
63	When running user interview, read [interview-guide.md](references/interview-guide.md) — process overview, example questions for each phase, handling "I don't know" answers.
64
65	Checkpoint: Requirements gathered. Problem, triggers, scope, and examples documented.
66
67	## 2. Skill Structure
68
69	### Anatomy of a Skill
70
71	Every skill consists of a required SKILL.md file and optional bundled resources:
72
73	```
74	skill-name/
75	├── SKILL.md (required)
76	│ ├── YAML frontmatter metadata (required)
77	│ │ ├── name: (required)
78	│ │ └── description: (required)
79	│ └── Markdown instructions (required)
80	└── Bundled Resources (optional)
81	├── scripts/ - Executable code (Python/Bash/etc.)
82	├── references/ - Documentation intended to be loaded into context as needed
83	└── assets/ - Files used in output (templates, icons, fonts, etc.)
84	```
85
86	### Frontmatter
87
88	**`

People who liked this also viewed

6 picks

Type

skill-master

241stars75forks

View on GitHub

How to install skill-master?

pavel-molyanov/molyanov-ai-dev/skill-master

$npx -y skills add pavel-molyanov/molyanov-ai-dev --skill skill-master

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	<!-- Generated by sync-to-codex v1. Do not edit directly. -->
2
3	# Skill Creator
4
5	## Claude-to-Codex Autosync
6
7	Claude-side is the source of truth (`~/.claude/` for global methodology, or a project's `CLAUDE.md` + `.claude/`); Codex-side (`~/.codex/` / `AGENTS.md`) is generated runtime. After editing any `.claude/` methodology file (`skills/`, `agents/`, `commands/`, `shared/`), regenerate Codex:
8
9	```bash
10	~/.claude/scripts/sync-to-codex.sh --apply # global ~/.claude/**
11	~/.claude/scripts/sync-to-codex.sh --project "$PWD" --apply # project .claude/**
12	```
13
14	Commit the generated `.codex/**` / `AGENTS.md` changes together with the source. If sync reports a conflict or validation error, stop and report it.
15
16	Authoring a skill that edits `.claude/`? Paste the block above near the top of its `SKILL.md` so its changes reach Codex too. A skill that never touches `.claude/` (pure analysis, code-writing in a project's own source tree) does not need it.
17
18	Bundled resources and the sync: Markdown files (`SKILL.md`, `references/.md`) are text-adapted during sync (Claude tool names → Codex equivalents). Every other bundled file — `scripts/`, `assets/`, images, data — is copied byte-for-byte, unmodified. So a bundled script must be runtime-agnostic: don't hardcode `.claude` paths or Claude-only tool names, since neither is rewritten in the Codex copy. Reference files relative to the script's own location, and let the surrounding `SKILL.md` prose (which is* adapted) carry any runtime-specific instructions.
19
20	## About Skills
21
22	Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.
23
24	### What Skills Provide
25
26	1. Specialized workflows - Multi-step procedures for specific domains
27	2. Tool integrations - Instructions for working with specific file formats or APIs
28	3. Domain expertise - Company-specific knowledge, schemas, business logic
29	4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks
30
31	## Skill Types
32
33	There are two types of skills based on how they guide Claude's work.
34
35	### Procedural Skills
36
37	Use when the task requires a strict sequence of steps where order matters. Phase 2 depends on Phase 1 completing correctly. Skipping or reordering steps would break the workflow.
38
39	Examples: code-writing (Plan → TDD → Review), project-planning (Interview → Features → Roadmap), tech-spec-planning.
40
41	These skills have explicit phases with checkpoints after each phase to verify completion before proceeding.
42
43	Creating a procedural skill? Read [procedural-skills.md](references/procedural-skills.md) — phase structure, checkpoints, verification patterns.
44
45	### Informational Skills
46
47	Use when providing methodology, knowledge, or guidelines without a strict execution order. The agent reads relevant sections and applies them to the situation. There's no "Phase 1 must complete before Phase 2" — sections are independent.
48
49	Examples: security-auditor (what to check), testing (when to use which test type), company-info (domain knowledge), database-schemas.
50
51	These skills organize content into logical sections with decision frameworks (YES if / NO if) to help the agent choose what applies.
52
53	Creating an informational skill? Read [informational-skills.md](references/informational-skills.md) — section organization, knowledge structure.
54
55	## 1. Discovery
56
57	For new skills or major changes — run discovery interview:
58	- What problem does the skill solve?
59	- What phrases should trigger it?
60	- What should the skill NOT do?
61	- Concrete usage examples
62
63	When running user interview, read [interview-guide.md](references/interview-guide.md) — process overview, example questions for each phase, handling "I don't know" answers.
64
65	Checkpoint: Requirements gathered. Problem, triggers, scope, and examples documented.
66
67	## 2. Skill Structure
68
69	### Anatomy of a Skill
70
71	Every skill consists of a required SKILL.md file and optional bundled resources:
72
73	```
74	skill-name/
75	├── SKILL.md (required)
76	│ ├── YAML frontmatter metadata (required)
77	│ │ ├── name: (required)
78	│ │ └── description: (required)
79	│ └── Markdown instructions (required)
80	└── Bundled Resources (optional)
81	├── scripts/ - Executable code (Python/Bash/etc.)
82	├── references/ - Documentation intended to be loaded into context as needed
83	└── assets/ - Files used in output (templates, icons, fonts, etc.)
84	```
85
86	### Frontmatter
87
88	**`

People who liked this also viewed

6 picks

Type