skill-creator

Name: skill-creator
Author: himself65

1.2kinstalls351forks

How to install skill-creator?

himself65/finance-skills/skill-creator

$npx -y skills add himself65/finance-skills --skill skill-creator

Installs into the current project.

Summary

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or iterate on skill quali

Files · 1

View on GitHub

SKILL.md

1	# Skill Creator
2
3	Create, evaluate, and iterate on high-quality agent skills. This skill guides the entire lifecycle: planning what the skill should do, writing SKILL.md and reference files, scoring quality against a rubric, and iterating until the skill meets production standards.
4
5	Philosophy: A great skill is not a long skill. It is a precise skill: exhaustive triggers, explicit defaults, clear steps with exit gates, deferred complexity via reference files, and a structured output template.
6
7	Core rule — always dynamic, never static: Skills MUST detect what tools, libraries, and auth are available at runtime and adapt their behavior accordingly. Never hardcode a single method. Always provide a detection flow with a decision tree and fallback paths. See `references/dynamic-calling.md` for the complete pattern catalog.
8
9	---
10
11	## Step 1: Understand What the User Wants
12
13	Classify the request into one of these modes:
14
15	\| User Intent \| Mode \| Jump To \|
16	\|---\|---\|---\|
17	\| Create a brand-new skill \| Create \| Step 2 \|
18	\| Improve / fix an existing skill \| Improve \| Step 6 \|
19	\| Evaluate / score a skill's quality \| Evaluate \| Step 7 \|
20
21	If ambiguous, ask: "Do you want to create a new skill, improve an existing one, or evaluate one?"
22
23	### Gather Requirements (for Create mode)
24
25	Before writing anything, answer these questions (ask the user if unclear):
26
27	\| Question \| Why it matters \|
28	\|---\|---\|
29	\| What task does the skill automate? \| Defines the core workflow \|
30	\| Who is the target user? \| Determines complexity and terminology level \|
31	\| What tools/APIs/CLIs does it use? \| Determines dependencies and platform restrictions \|
32	\| What does the user provide as input? \| Defines parameters and defaults \|
33	\| What should the output look like? \| Defines the response template \|
34	\| Does it need API keys or credentials? \| Determines `required_environment_variables` \|
35	\| Should it work on Claude.ai or only CLI? \| Determines platform field and dynamic commands \|
36
37	---
38
39	## Step 2: Plan the Skill Architecture
40
41	Before writing SKILL.md, plan the structure. Read `references/architecture-patterns.md` for detailed guidance on each pattern.
42
43	### Choose a Structural Pattern
44
45	\| Pattern \| When to use \| Steps \| Example \|
46	\|---\|---\|---\|---\|
47	\| Linear \| Single workflow, no branching \| 5-7 \| earnings-preview, etf-premium \|
48	\| Router \| Multiple sub-tasks under one umbrella \| 3 + sub-skills \| stock-correlation (4 sub-skills) \|
49	\| Methodology \| Complex domain framework with sequential gates \| 7-9 \| sepa-strategy (9-step trading methodology) \|
50	\| Widget \| Generates interactive UI output \| 4-5 \| options-payoff (extract + compute + render) \|
51	\| API Wrapper \| Wraps an external API with many endpoints \| 3-5 + heavy references \| funda-data (5 steps, 8 reference files) \|
52
53	### Plan the Step Outline
54
55	Write out the step names before writing content. Every skill should have:
56
57	1. Detection flow (Step 1) -- dynamically detect available tools, auth state, and runtime environment; build a decision tree for which method to use
58	2. Core methodology (Steps 2-N) -- the actual work, with pass/fail gates; each step that calls an external tool should have method alternatives based on what Step 1 detected
59	3. Respond to user (Final step) -- structured output template
60
61	Target 5-9 steps total. More than 9 means the skill should be split or use a router pattern.
62
63	### Plan the Detection Flow
64
65	Every skill that touches external tools MUST start with a runtime detection flow. Read `references/dynamic-calling.md` for all patterns. The detection flow answers:
66
67	\| Question \| How to detect \| Decision \|
68	\|---\|---\|---\|
69	\| Is the CLI tool installed? \| `command -v tool` \| CLI path vs Python fallback \|
70	\| Is the user authenticated? \| `tool auth status` / `echo $API_KEY` \| Skip auth setup vs guide through it \|
71	\| Which runtime has the library? \| `import lib` in terminal vs execute_code \| Route to correct runtime \|
72	\| Is a richer tool available? \| `gh --version` vs `git --version` \| Rich path vs minimal path \|
73	\| Is live data re

himself65Publisher · 29 listings

Preview

himself65/finance-skills

# Skill Creator

Create, evaluate, and iterate on high-quality agent skills. This skill guides the entire lifecycle: planning what the skill should do, writing SKILL.md and refe

**Philosophy:** A great skill is not a long skill. It is a *precise* skill: exhaustive triggers, explicit defaults, clear steps with exit gates, deferred comple

**Core rule — always dynamic, never static:** Skills MUST detect what tools, libraries, and auth are available at runtime and adapt their behavior accordingly.

Repohimself65/finance-skills

LicenseMIT

TypeSkills

CategoryFinance

UpdatedJul 2026

Repo stars3.0k

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type

skill-creator

1.2kinstalls351forks

View on GitHub

How to install skill-creator?

himself65/finance-skills/skill-creator

$npx -y skills add himself65/finance-skills --skill skill-creator

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Skill Creator
2
3	Create, evaluate, and iterate on high-quality agent skills. This skill guides the entire lifecycle: planning what the skill should do, writing SKILL.md and reference files, scoring quality against a rubric, and iterating until the skill meets production standards.
4
5	Philosophy: A great skill is not a long skill. It is a precise skill: exhaustive triggers, explicit defaults, clear steps with exit gates, deferred complexity via reference files, and a structured output template.
6
7	Core rule — always dynamic, never static: Skills MUST detect what tools, libraries, and auth are available at runtime and adapt their behavior accordingly. Never hardcode a single method. Always provide a detection flow with a decision tree and fallback paths. See `references/dynamic-calling.md` for the complete pattern catalog.
8
9	---
10
11	## Step 1: Understand What the User Wants
12
13	Classify the request into one of these modes:
14
15	\| User Intent \| Mode \| Jump To \|
16	\|---\|---\|---\|
17	\| Create a brand-new skill \| Create \| Step 2 \|
18	\| Improve / fix an existing skill \| Improve \| Step 6 \|
19	\| Evaluate / score a skill's quality \| Evaluate \| Step 7 \|
20
21	If ambiguous, ask: "Do you want to create a new skill, improve an existing one, or evaluate one?"
22
23	### Gather Requirements (for Create mode)
24
25	Before writing anything, answer these questions (ask the user if unclear):
26
27	\| Question \| Why it matters \|
28	\|---\|---\|
29	\| What task does the skill automate? \| Defines the core workflow \|
30	\| Who is the target user? \| Determines complexity and terminology level \|
31	\| What tools/APIs/CLIs does it use? \| Determines dependencies and platform restrictions \|
32	\| What does the user provide as input? \| Defines parameters and defaults \|
33	\| What should the output look like? \| Defines the response template \|
34	\| Does it need API keys or credentials? \| Determines `required_environment_variables` \|
35	\| Should it work on Claude.ai or only CLI? \| Determines platform field and dynamic commands \|
36
37	---
38
39	## Step 2: Plan the Skill Architecture
40
41	Before writing SKILL.md, plan the structure. Read `references/architecture-patterns.md` for detailed guidance on each pattern.
42
43	### Choose a Structural Pattern
44
45	\| Pattern \| When to use \| Steps \| Example \|
46	\|---\|---\|---\|---\|
47	\| Linear \| Single workflow, no branching \| 5-7 \| earnings-preview, etf-premium \|
48	\| Router \| Multiple sub-tasks under one umbrella \| 3 + sub-skills \| stock-correlation (4 sub-skills) \|
49	\| Methodology \| Complex domain framework with sequential gates \| 7-9 \| sepa-strategy (9-step trading methodology) \|
50	\| Widget \| Generates interactive UI output \| 4-5 \| options-payoff (extract + compute + render) \|
51	\| API Wrapper \| Wraps an external API with many endpoints \| 3-5 + heavy references \| funda-data (5 steps, 8 reference files) \|
52
53	### Plan the Step Outline
54
55	Write out the step names before writing content. Every skill should have:
56
57	1. Detection flow (Step 1) -- dynamically detect available tools, auth state, and runtime environment; build a decision tree for which method to use
58	2. Core methodology (Steps 2-N) -- the actual work, with pass/fail gates; each step that calls an external tool should have method alternatives based on what Step 1 detected
59	3. Respond to user (Final step) -- structured output template
60
61	Target 5-9 steps total. More than 9 means the skill should be split or use a router pattern.
62
63	### Plan the Detection Flow
64
65	Every skill that touches external tools MUST start with a runtime detection flow. Read `references/dynamic-calling.md` for all patterns. The detection flow answers:
66
67	\| Question \| How to detect \| Decision \|
68	\|---\|---\|---\|
69	\| Is the CLI tool installed? \| `command -v tool` \| CLI path vs Python fallback \|
70	\| Is the user authenticated? \| `tool auth status` / `echo $API_KEY` \| Skip auth setup vs guide through it \|
71	\| Which runtime has the library? \| `import lib` in terminal vs execute_code \| Route to correct runtime \|
72	\| Is a richer tool available? \| `gh --version` vs `git --version` \| Rich path vs minimal path \|
73	\| Is live data re

himself65Publisher · 29 listings

Preview

himself65/finance-skills

# Skill Creator

Create, evaluate, and iterate on high-quality agent skills. This skill guides the entire lifecycle: planning what the skill should do, writing SKILL.md and refe

**Philosophy:** A great skill is not a long skill. It is a *precise* skill: exhaustive triggers, explicit defaults, clear steps with exit gates, deferred comple

**Core rule — always dynamic, never static:** Skills MUST detect what tools, libraries, and auth are available at runtime and adapt their behavior accordingly.

Repohimself65/finance-skills

LicenseMIT

TypeSkills

CategoryFinance

UpdatedJul 2026

Repo stars3.0k

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type