suggesting-skills

Name: suggesting-skills
Author: spencerpauly

15stars4forks

How to install suggesting-skills?

spencerpauly/skills-repo/suggesting-skills

$npx -y skills add spencerpauly/skills-repo --skill suggesting-skills

Installs into the current project.

Summary

Look at what the user keeps re-explaining to the agent and propose new SKILL.md files that would replace those repeated explanations. Use when the user says "what skills should I have", "suggest skills", "audit my skills", or when you notice you're being asked the same kind of ta

Files · 1

View on GitHub

SKILL.md

1	# Suggesting Skills
2
3	Find the gaps in the user's skill library. Skills are most valuable when they capture the things the user would otherwise have to explain to the agent every time.
4
5	## When to use
6
7	- The user explicitly asks "what skills am I missing", "what should I add", "audit my skills".
8	- You notice the same kind of request happening repeatedly in a session — that's a skill waiting to be written.
9	- After a long session, before the user closes the chat, offer to extract any reusable playbook from the work just done.
10
11	## Steps
12
13	1. Inventory what's already there. Read every `SKILL.md` in the repo. Note for each: name, the trigger phrase in the description, and the one-line goal. If two existing skills overlap, flag the duplication.
14
15	2. Look for the pattern of "I keep telling you to…". Strong candidates for new skills are:
16	- Repeated workflow — the user has asked for the same multi-step task at least twice.
17	- Repeated correction — the user has had to fix the same kind of mistake the agent makes (formatting, voice, missing a step).
18	- Tribal knowledge — facts about this user's stack, team, or product that aren't in the codebase but the user keeps having to restate.
19	- External tool wiring — the user has an MCP, CLI, or API the agent could be using but isn't.
20
21	3. Propose 3–5 candidate skills, each as a one-paragraph pitch:
22	```
23	Name: kebab-case-name
24	Trigger: when the user says "..." or asks to "..."
25	What it does: one sentence
26	Why it's worth a skill: the repeated thing it replaces
27	```
28
29	4. Rank them. Sort by frequency × annoyance: how often does the situation come up, and how painful is it when it's not automated?
30
31	5. Ask the user which 1–2 to actually write. Don't auto-generate all of them. Skills that aren't trusted get ignored, which is worse than not having them.
32
33	6. For each chosen skill, scaffold a `SKILL.md` in `skills/<name>/` with:
34	- Frontmatter (`name`, `description` with trigger phrases, `license`).
35	- "When to use" — the trigger conditions, in plain English.
36	- "Steps" — numbered, imperative.
37	- "Don't" — the failure modes you've seen.
38
39	## Output format
40
41	```markdown
42	## Existing skills (N)
43	- skill-name — what it does, when it fires.
44
45	## Suggested additions
46	1. <name> — <pitch> _(seen X times this session)_
47	2. ...
48
49	## Candidate skill files
50	<scaffolded SKILL.md(s) for the chosen ones>
51	```
52
53	## Don't
54
55	- Don't suggest a skill for something the agent already does well by default. Skills are for the cases where the un-prompted behavior is wrong.
56	- Don't propose 20 skills. The repo gets noisy and the agent's skill-selection routing degrades. 5–15 well-trusted skills > 50 mediocre ones.
57	- Don't write the SKILL.md without the user's go-ahead. Half the value of a skill is that the user trusts it; that requires their hand on the design.

People who liked this also viewed

6 picks

Type

suggesting-skills

15stars4forks

View on GitHub

How to install suggesting-skills?

spencerpauly/skills-repo/suggesting-skills

$npx -y skills add spencerpauly/skills-repo --skill suggesting-skills

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Suggesting Skills
2
3	Find the gaps in the user's skill library. Skills are most valuable when they capture the things the user would otherwise have to explain to the agent every time.
4
5	## When to use
6
7	- The user explicitly asks "what skills am I missing", "what should I add", "audit my skills".
8	- You notice the same kind of request happening repeatedly in a session — that's a skill waiting to be written.
9	- After a long session, before the user closes the chat, offer to extract any reusable playbook from the work just done.
10
11	## Steps
12
13	1. Inventory what's already there. Read every `SKILL.md` in the repo. Note for each: name, the trigger phrase in the description, and the one-line goal. If two existing skills overlap, flag the duplication.
14
15	2. Look for the pattern of "I keep telling you to…". Strong candidates for new skills are:
16	- Repeated workflow — the user has asked for the same multi-step task at least twice.
17	- Repeated correction — the user has had to fix the same kind of mistake the agent makes (formatting, voice, missing a step).
18	- Tribal knowledge — facts about this user's stack, team, or product that aren't in the codebase but the user keeps having to restate.
19	- External tool wiring — the user has an MCP, CLI, or API the agent could be using but isn't.
20
21	3. Propose 3–5 candidate skills, each as a one-paragraph pitch:
22	```
23	Name: kebab-case-name
24	Trigger: when the user says "..." or asks to "..."
25	What it does: one sentence
26	Why it's worth a skill: the repeated thing it replaces
27	```
28
29	4. Rank them. Sort by frequency × annoyance: how often does the situation come up, and how painful is it when it's not automated?
30
31	5. Ask the user which 1–2 to actually write. Don't auto-generate all of them. Skills that aren't trusted get ignored, which is worse than not having them.
32
33	6. For each chosen skill, scaffold a `SKILL.md` in `skills/<name>/` with:
34	- Frontmatter (`name`, `description` with trigger phrases, `license`).
35	- "When to use" — the trigger conditions, in plain English.
36	- "Steps" — numbered, imperative.
37	- "Don't" — the failure modes you've seen.
38
39	## Output format
40
41	```markdown
42	## Existing skills (N)
43	- skill-name — what it does, when it fires.
44
45	## Suggested additions
46	1. <name> — <pitch> _(seen X times this session)_
47	2. ...
48
49	## Candidate skill files
50	<scaffolded SKILL.md(s) for the chosen ones>
51	```
52
53	## Don't
54
55	- Don't suggest a skill for something the agent already does well by default. Skills are for the cases where the un-prompted behavior is wrong.
56	- Don't propose 20 skills. The repo gets noisy and the agent's skill-selection routing degrades. 5–15 well-trusted skills > 50 mediocre ones.
57	- Don't write the SKILL.md without the user's go-ahead. Half the value of a skill is that the user trusts it; that requires their hand on the design.

People who liked this also viewed

6 picks

Type