skill-creator

Name: skill-creator
Author: Undertone0809

247stars30forks

How to install skill-creator?

undertone0809/rudder/skill-creator

$npx -y skills add Undertone0809/rudder --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, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's descr

Files · 1

View on GitHub

SKILL.md

1	# Skill Creator
2
3	A skill for creating new skills and iteratively improving them.
4
5	Before host-sensitive work, read exactly one compatibility guide from `references/compatibility/`: `claudecode.md`, `codex.md`, or `other.md`. Read more than one only when packaging or evaluating the same skill across multiple hosts.
6
7	When running inside Rudder, also read `references/rudder.md`. Rudder owns skill
8	installation and runtime enablement, while the host-specific guide still owns
9	evaluation and packaging mechanics for the underlying agent runtime.
10
11	At a high level, the process of creating a skill goes like this:
12
13	- Decide what you want the skill to do and roughly how it should do it
14	- Write a draft of the skill
15	- Create a few test prompts and run them in an agent session that has access to the skill
16	- Help the user evaluate the results both qualitatively and quantitatively
17	- While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
18	- Use the `eval-viewer/generate_review.py` script to show the user the results for them to look at, and also let them look at the quantitative metrics
19	- Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
20	- Repeat until you're satisfied
21	- Expand the test set and try again at larger scale
22
23	Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages. So for instance, maybe they're like "I want to make a skill for X". You can help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run all the prompts, and repeat.
24
25	On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop.
26
27	Of course, you should always be flexible and if the user is like "I don't need to run a bunch of evaluations, just vibe with me", you can do that instead.
28
29	Then after the skill is done (but again, the order is flexible), you can also run the skill description improver, which we have a whole separate script for, to optimize the triggering of the skill.
30
31	Cool? Cool.
32
33	## Communicating with the user
34
35	The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. There's a trend now where the power of modern agents is inspiring plumbers to open up their terminals, parents and grandparents to google "how to install npm". On the other hand, the bulk of users are probably fairly computer-literate.
36
37	So please pay attention to context cues to understand how to phrase your communication! In the default case, just to give you some idea:
38
39	- "evaluation" and "benchmark" are borderline, but OK
40	- for "JSON" and "assertion" you want to see serious cues from the user that they know what those things are before using them without explaining them
41
42	It's OK to briefly explain terms if you're in doubt, and feel free to clarify terms with a short definition if you're unsure if the user will get it.
43
44	---
45
46	## Creating a skill
47
48	### Capture Intent
49
50	Start by understanding the user's intent. The current conversation might already contain a workflow the user wants to capture (e.g., they say "turn this into a skill"). If so, extract answers from the conversation history first — the tools used, the sequence of steps, corrections the user made, input/output formats observed. The user may need to fill the gaps, and should confirm before proceeding to the next step.
51
52	1. What should this skill enable the agent to do?
53	2. When should this skill trigger? (what user phrases/contexts)
54	3. What's the expected output format?
55	4. Should we set up test cases to verify the skill works? Skills with objectively verifiable outputs (file transforms, data extraction, code generation, fixed workflow steps) benefit from test cases. Skills with subjective outputs (writing style, art) often don't need them. Suggest the appropriate default based on the skill type, but let the user decide.
56
57	### Interview and Research
58
59	Proactively ask questions about edge cases, input/output formats, example files, success criteria, and dependencies. Wait to write test prompts until you've got this part ironed out.
60
61	Check available MCPs - if useful for research (searching docs, finding similar skills, looking up best practices), research in par

People who liked this also viewed

6 picks

Type

skill-creator

247stars30forks

View on GitHub

How to install skill-creator?

undertone0809/rudder/skill-creator

$npx -y skills add Undertone0809/rudder --skill skill-creator

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Skill Creator
2
3	A skill for creating new skills and iteratively improving them.
4
5	Before host-sensitive work, read exactly one compatibility guide from `references/compatibility/`: `claudecode.md`, `codex.md`, or `other.md`. Read more than one only when packaging or evaluating the same skill across multiple hosts.
6
7	When running inside Rudder, also read `references/rudder.md`. Rudder owns skill
8	installation and runtime enablement, while the host-specific guide still owns
9	evaluation and packaging mechanics for the underlying agent runtime.
10
11	At a high level, the process of creating a skill goes like this:
12
13	- Decide what you want the skill to do and roughly how it should do it
14	- Write a draft of the skill
15	- Create a few test prompts and run them in an agent session that has access to the skill
16	- Help the user evaluate the results both qualitatively and quantitatively
17	- While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
18	- Use the `eval-viewer/generate_review.py` script to show the user the results for them to look at, and also let them look at the quantitative metrics
19	- Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
20	- Repeat until you're satisfied
21	- Expand the test set and try again at larger scale
22
23	Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages. So for instance, maybe they're like "I want to make a skill for X". You can help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run all the prompts, and repeat.
24
25	On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop.
26
27	Of course, you should always be flexible and if the user is like "I don't need to run a bunch of evaluations, just vibe with me", you can do that instead.
28
29	Then after the skill is done (but again, the order is flexible), you can also run the skill description improver, which we have a whole separate script for, to optimize the triggering of the skill.
30
31	Cool? Cool.
32
33	## Communicating with the user
34
35	The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. There's a trend now where the power of modern agents is inspiring plumbers to open up their terminals, parents and grandparents to google "how to install npm". On the other hand, the bulk of users are probably fairly computer-literate.
36
37	So please pay attention to context cues to understand how to phrase your communication! In the default case, just to give you some idea:
38
39	- "evaluation" and "benchmark" are borderline, but OK
40	- for "JSON" and "assertion" you want to see serious cues from the user that they know what those things are before using them without explaining them
41
42	It's OK to briefly explain terms if you're in doubt, and feel free to clarify terms with a short definition if you're unsure if the user will get it.
43
44	---
45
46	## Creating a skill
47
48	### Capture Intent
49
50	Start by understanding the user's intent. The current conversation might already contain a workflow the user wants to capture (e.g., they say "turn this into a skill"). If so, extract answers from the conversation history first — the tools used, the sequence of steps, corrections the user made, input/output formats observed. The user may need to fill the gaps, and should confirm before proceeding to the next step.
51
52	1. What should this skill enable the agent to do?
53	2. When should this skill trigger? (what user phrases/contexts)
54	3. What's the expected output format?
55	4. Should we set up test cases to verify the skill works? Skills with objectively verifiable outputs (file transforms, data extraction, code generation, fixed workflow steps) benefit from test cases. Skills with subjective outputs (writing style, art) often don't need them. Suggest the appropriate default based on the skill type, but let the user decide.
56
57	### Interview and Research
58
59	Proactively ask questions about edge cases, input/output formats, example files, success criteria, and dependencies. Wait to write test prompts until you've got this part ironed out.
60
61	Check available MCPs - if useful for research (searching docs, finding similar skills, looking up best practices), research in par

People who liked this also viewed

6 picks

Type