skill-finder

Name: skill-finder
Author: Affitor

5installs184forks

How to install skill-finder?

affitor/affiliate-skills/skill-finder

$npx -y skills add Affitor/affiliate-skills --skill skill-finder

Installs into the current project.

Summary

Find the right Affitor skill for your goal. Triggers on: "which skill should I use", "find me a skill", "what skills are available", "help me choose a skill", "skill for SEO", "skill for email", "explore skills", "I'm new to Affitor", "what can Affitor do", "search skills", "skil

Files · 1

View on GitHub

SKILL.md

1	# Skill Finder
2
3	Search and discover Affitor skills by task, stage, keyword, or natural language goal. Returns a ranked list of matching skills with descriptions, input requirements, and recommended next steps. Output is a concise Markdown guide.
4
5	## Stage
6
7	S8: Meta — The entry point to the entire Affitor ecosystem. New users don't know what's available. Experienced users forget skill names. Skill Finder bridges the gap — it reads the registry, matches intent to capability, and recommends the fastest path to the user's goal.
8
9	## When to Use
10
11	- User is new to Affitor and asks "what can I do?" or "where do I start?"
12	- User describes a goal but doesn't name a specific skill
13	- User wants to find skills by stage (e.g., "what analytics skills exist?")
14	- User asks "which skill helps with [topic]?"
15	- User says anything like "find skill", "search skill", "explore skills"
16	- Chaining: recommended as the first skill for new users before S1-S7
17
18	## Input Schema
19
20	```yaml
21	query: string # REQUIRED — natural language: "I want to write a blog review"
22	# or "what skills help with SEO?" or "analytics skills"
23	stage_filter: string # OPTIONAL — filter by stage: research \| content \| blog \| landing
24	# \| distribution \| analytics \| automation \| meta
25	goal: string # OPTIONAL — broader goal: "first commission" \| "scale to 1k"
26	# \| "optimize conversions" \| "automate my workflow"
27	```
28
29	## Workflow
30
31	### Step 1: Load Skill Catalog
32
33	Read `registry.json` from the repository root (or from conversation context if already loaded). Parse all skills with their stage, name, slug, and description.
34
35	### Step 2: Match Query to Skills
36
37	Match the user's `query` against:
38	1. Skill names and slugs (exact match → top priority)
39	2. Skill descriptions (keyword overlap)
40	3. Stage labels and descriptions (if user is browsing by stage)
41	4. Inferred intent (e.g., "SEO" → `seo-audit`, `affiliate-blog-builder`)
42
43	If `stage_filter` is provided, restrict results to that stage.
44
45	### Step 3: Rank Results
46
47	Rank matches by relevance:
48	1. Direct name/slug match
49	2. Description keyword match count
50	3. Stage alignment with user's apparent funnel position
51
52	### Step 4: Recommend a Path
53
54	If the user's goal spans multiple stages, suggest a skill sequence:
55	- "You want to go from zero to first commission → S1 → S2 → S3 → S5"
56	- "You want to optimize existing content → S6 (seo-audit, ab-test-generator)"
57
58	### Step 5: Output Results
59
60	Present top 3-5 matching skills with:
61	- Skill name and stage
62	- What it does (one sentence)
63	- What input it needs
64	- Example invocation prompt
65
66	### Step 6: Self-Validation
67
68	Before presenting output, verify:
69
70	- [ ] All matched skills exist in the current registry
71	- [ ] Example prompts are copy-paste ready and grammatically correct
72	- [ ] Recommended path follows logical funnel sequence
73	- [ ] Relevance ranking: exact match > partial match > related
74	- [ ] Input needed descriptions match actual skill Input Schemas
75
76	If any check fails, fix the output before delivering. Do not flag the checklist to the user — just ensure the output passes.
77
78	## Output Schema
79
80	```yaml
81	output_schema_version: "1.0.0" # Semver — bump major on breaking changes
82	matches:
83	- skill: string # skill slug
84	stage: string # e.g., "S6: Analytics"
85	description: string # one-sentence summary
86	input_needed: string # what the user needs to provide
87	example_prompt: string # copy-paste prompt to invoke the skill
88	relevance: string # "exact" \| "high" \| "related"
89
90	recommended_path:
91	description: string # why this path
92	steps:
93	- order: number
94	skill: string
95	action: string # what this step accomplishes
96	```
97
98	## Output Format
99
100	1. Matching Skills — table with skill name, stage, description, and relevance
101	2. How to Use — for each top match, show the exact prompt to invoke it
102	3. Recommended Path — if the goal spans multiple stages, a numbered sequence
103
104	## Error Handling
105
106	- Empty query: "What are you trying to accomplish? For example: 'write a blog review', 'track conversions', or 'plan a full funnel'."
107	- No matches found: "No skills match '[query]'. Here are all available stages: [list stages]. Tr

People who liked this also viewed

6 picks

Type

skill-finder

5installs184forks

View on GitHub

How to install skill-finder?

affitor/affiliate-skills/skill-finder

$npx -y skills add Affitor/affiliate-skills --skill skill-finder

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Skill Finder
2
3	Search and discover Affitor skills by task, stage, keyword, or natural language goal. Returns a ranked list of matching skills with descriptions, input requirements, and recommended next steps. Output is a concise Markdown guide.
4
5	## Stage
6
7	S8: Meta — The entry point to the entire Affitor ecosystem. New users don't know what's available. Experienced users forget skill names. Skill Finder bridges the gap — it reads the registry, matches intent to capability, and recommends the fastest path to the user's goal.
8
9	## When to Use
10
11	- User is new to Affitor and asks "what can I do?" or "where do I start?"
12	- User describes a goal but doesn't name a specific skill
13	- User wants to find skills by stage (e.g., "what analytics skills exist?")
14	- User asks "which skill helps with [topic]?"
15	- User says anything like "find skill", "search skill", "explore skills"
16	- Chaining: recommended as the first skill for new users before S1-S7
17
18	## Input Schema
19
20	```yaml
21	query: string # REQUIRED — natural language: "I want to write a blog review"
22	# or "what skills help with SEO?" or "analytics skills"
23	stage_filter: string # OPTIONAL — filter by stage: research \| content \| blog \| landing
24	# \| distribution \| analytics \| automation \| meta
25	goal: string # OPTIONAL — broader goal: "first commission" \| "scale to 1k"
26	# \| "optimize conversions" \| "automate my workflow"
27	```
28
29	## Workflow
30
31	### Step 1: Load Skill Catalog
32
33	Read `registry.json` from the repository root (or from conversation context if already loaded). Parse all skills with their stage, name, slug, and description.
34
35	### Step 2: Match Query to Skills
36
37	Match the user's `query` against:
38	1. Skill names and slugs (exact match → top priority)
39	2. Skill descriptions (keyword overlap)
40	3. Stage labels and descriptions (if user is browsing by stage)
41	4. Inferred intent (e.g., "SEO" → `seo-audit`, `affiliate-blog-builder`)
42
43	If `stage_filter` is provided, restrict results to that stage.
44
45	### Step 3: Rank Results
46
47	Rank matches by relevance:
48	1. Direct name/slug match
49	2. Description keyword match count
50	3. Stage alignment with user's apparent funnel position
51
52	### Step 4: Recommend a Path
53
54	If the user's goal spans multiple stages, suggest a skill sequence:
55	- "You want to go from zero to first commission → S1 → S2 → S3 → S5"
56	- "You want to optimize existing content → S6 (seo-audit, ab-test-generator)"
57
58	### Step 5: Output Results
59
60	Present top 3-5 matching skills with:
61	- Skill name and stage
62	- What it does (one sentence)
63	- What input it needs
64	- Example invocation prompt
65
66	### Step 6: Self-Validation
67
68	Before presenting output, verify:
69
70	- [ ] All matched skills exist in the current registry
71	- [ ] Example prompts are copy-paste ready and grammatically correct
72	- [ ] Recommended path follows logical funnel sequence
73	- [ ] Relevance ranking: exact match > partial match > related
74	- [ ] Input needed descriptions match actual skill Input Schemas
75
76	If any check fails, fix the output before delivering. Do not flag the checklist to the user — just ensure the output passes.
77
78	## Output Schema
79
80	```yaml
81	output_schema_version: "1.0.0" # Semver — bump major on breaking changes
82	matches:
83	- skill: string # skill slug
84	stage: string # e.g., "S6: Analytics"
85	description: string # one-sentence summary
86	input_needed: string # what the user needs to provide
87	example_prompt: string # copy-paste prompt to invoke the skill
88	relevance: string # "exact" \| "high" \| "related"
89
90	recommended_path:
91	description: string # why this path
92	steps:
93	- order: number
94	skill: string
95	action: string # what this step accomplishes
96	```
97
98	## Output Format
99
100	1. Matching Skills — table with skill name, stage, description, and relevance
101	2. How to Use — for each top match, show the exact prompt to invoke it
102	3. Recommended Path — if the goal spans multiple stages, a numbered sequence
103
104	## Error Handling
105
106	- Empty query: "What are you trying to accomplish? For example: 'write a blog review', 'track conversions', or 'plan a full funnel'."
107	- No matches found: "No skills match '[query]'. Here are all available stages: [list stages]. Tr

People who liked this also viewed

6 picks

Type