cm-skill-index

Name: cm-skill-index
Author: tody-agent

47stars23forks

How to install cm-skill-index?

tody-agent/codymaster/cm-skill-index

$npx -y skills add tody-agent/codymaster --skill cm-skill-index

Installs into the current project.

Summary

Progressive Disclosure skill index — efficient skill loading in 3 layers. Layer 1 (index, ~100 tokens) always loaded. Layer 2 (summary, ~300 tokens) loaded on context need. Layer 3 (full SKILL.md) loaded on execution only.

Files · 1

View on GitHub

SKILL.md

1	# Skill Index — Progressive Disclosure Engine
2
3	## TL;DR
4	- Use when searching for a CodyMaster or community skill
5	- Layered: L1 index (always loaded) → L2 summary → L3 full
6	- Includes: discovery, search, mastery (consolidated in v6)
7
8	> Save 90%+ tokens. Agents scan the index first, load full skills only when executing.
9	> Inspired by Loki Mode's 3-Layer Progressive Disclosure memory architecture.
10
11	## The Problem
12
13	Traditional approach: Load every SKILL.md to decide which skill to use.
14	- 30+ skills × ~3000 tokens each = 90,000+ tokens just for discovery
15	- Agent only needs ~500 tokens to make the choice
16	- 89,500 tokens wasted on reading full skills
17
18	## The Solution: 3-Layer Loading
19
20	```
21	┌────────────────────────────────────────────────┐
22	│ LAYER 1: INDEX (~100 tokens per skill) │
23	│ Always loaded. Quick scan. "What exists?" │
24	│ Name + Domain + Triggers + 1-line summary │
25	└─────────────────────┬──────────────────────────┘
26	│ (match found?)
27	v
28	┌────────────────────────────────────────────────┐
29	│ LAYER 2: SUMMARY (~300 tokens per skill) │
30	│ Load when choosing. "Is this the right one?" │
31	│ Description + When to use + Integration table │
32	└─────────────────────┬──────────────────────────┘
33	│ (confirmed?)
34	v
35	┌────────────────────────────────────────────────┐
36	│ LAYER 3: FULL SKILL.md (1500-5000 tokens) │
37	│ Load ONLY during execution. "How to use it." │
38	│ Complete instructions, examples, red flags │
39	└────────────────────────────────────────────────┘
40	```
41
42	## Layer 1: Skill Index
43
44	Always loaded by agents at session start. Maximum 100 tokens per skill.
45
46	### Engineering Swarm 🔧
47
48	\| Skill \| Triggers \| Summary \|
49	\|-------\|----------\|---------\|
50	\| `cm-tdd` \| test, TDD, red-green-refactor \| Red-Green-Refactor cycle before any implementation \|
51	\| `cm-debugging` \| bug, error, fix, debug, broken \| Root cause analysis before fixing. 5-phase investigation \|
52	\| `cm-quality-gate` \| deploy, ship, verify, quality, gate \| 6-gate verification: static analysis → blind review → ship \|
53	\| `cm-test-gate` \| test setup, CI, test infrastructure \| Setup 4-layer test gate for any project type \|
54	\| `cm-code-review` \| review, PR, feedback, branch \| Request reviews, handle feedback, complete branches \|
55	\| `cm-codeintell` \| understand codebase, call graph, impact, architecture, what calls X, what breaks \| AST knowledge graph + architecture diagrams + smart context (30% fewer tokens) \|
56	\| `cm-reactor` \| rewrite, pivot, migrate, direction change, architecture wrong, restructure \| TRIZ-powered strategic codebase re-direction — 5-phase incremental migration \|
57	\| `cm-clean-code` \| clean, dead code, refactor, code smell, DRY, SOLID, naming, messy \| 7-point hygiene gate: dead code, imports, naming, SRP, DRY, nesting \|
58
59	### Operations Swarm ⚙️
60
61	\| Skill \| Triggers \| Summary \|
62	\|-------\|----------\|---------\|
63	\| `cm-safe-deploy` \| deploy, staging, production, release \| Multi-gate deploy pipeline with rollback strategy \|
64	\| `cm-identity-guard` \| git push, deploy, Cloudflare, Supabase, account \| Verify identity before any push/deploy to prevent wrong-account \|
65	\| `cm-git-worktrees` \| branch, isolate, worktree, parallel \| Isolated git worktrees for feature work \|
66	\| `cm-terminal` \| command, terminal, run, execute \| Safe terminal execution with progress logging \|
67
68	### Security Swarm 🔒
69
70	\| Skill \| Triggers \| Summary \|
71	\|-------\|----------\|---------\|
72	\| `cm-secret-shield` \| secret, token, leak, security, scan, pre-commit, gitleaks, rotate \| Defense-in-depth: pre-commit hooks, repo scanning, token lifecycle \|
73
74	### Product Swarm 🎨
75
76	\| Skill \| Triggers \| Summary \|
77	\|-------\|----------\|---------\|
78	\| `cm-brainstorm-idea` \| analyze, enhance, improve, initiative, evaluate, review product \| Strategic analysis gate: 9 Windows + Double Diamond → 2-3 qualified options \|
79	\| `cm-planning` \| plan, design, brainstorm, feature \| Brainstorm intent → write implementation plan → then code \|
80	\| `cm-ux-master` \| UI, UX, design, interface, usability \| 48 UX Laws + 37 Design Tests + Figma/Stitch integration \|
81	\| `cm-ui-preview` \| preview, visual, mockup, render UI, wireframe \| Live UI concept generation via Google Stitch or Pencil MCP \|
82	\| `cm-dockit` \| docs, documentation, knowledge base, SOP \| Generate complete knowledge base from codebase \|
83	\| `cm-project-bootstrap` \| new project, init, bootstrap, setup \| Full project setup: design system → staging → CI → deploy \|
84	\| `cm-jtbd` \| customer discovery, JTBD, jobs to be done, product-market fit, why users churn \| JTBD canvas: Switch Interview → Outcome Metrics → Opportunity Scoring \|
85
86	### Growt

People who liked this also viewed

6 picks

Type

cm-skill-index

47stars23forks

View on GitHub

How to install cm-skill-index?

tody-agent/codymaster/cm-skill-index

$npx -y skills add tody-agent/codymaster --skill cm-skill-index

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Skill Index — Progressive Disclosure Engine
2
3	## TL;DR
4	- Use when searching for a CodyMaster or community skill
5	- Layered: L1 index (always loaded) → L2 summary → L3 full
6	- Includes: discovery, search, mastery (consolidated in v6)
7
8	> Save 90%+ tokens. Agents scan the index first, load full skills only when executing.
9	> Inspired by Loki Mode's 3-Layer Progressive Disclosure memory architecture.
10
11	## The Problem
12
13	Traditional approach: Load every SKILL.md to decide which skill to use.
14	- 30+ skills × ~3000 tokens each = 90,000+ tokens just for discovery
15	- Agent only needs ~500 tokens to make the choice
16	- 89,500 tokens wasted on reading full skills
17
18	## The Solution: 3-Layer Loading
19
20	```
21	┌────────────────────────────────────────────────┐
22	│ LAYER 1: INDEX (~100 tokens per skill) │
23	│ Always loaded. Quick scan. "What exists?" │
24	│ Name + Domain + Triggers + 1-line summary │
25	└─────────────────────┬──────────────────────────┘
26	│ (match found?)
27	v
28	┌────────────────────────────────────────────────┐
29	│ LAYER 2: SUMMARY (~300 tokens per skill) │
30	│ Load when choosing. "Is this the right one?" │
31	│ Description + When to use + Integration table │
32	└─────────────────────┬──────────────────────────┘
33	│ (confirmed?)
34	v
35	┌────────────────────────────────────────────────┐
36	│ LAYER 3: FULL SKILL.md (1500-5000 tokens) │
37	│ Load ONLY during execution. "How to use it." │
38	│ Complete instructions, examples, red flags │
39	└────────────────────────────────────────────────┘
40	```
41
42	## Layer 1: Skill Index
43
44	Always loaded by agents at session start. Maximum 100 tokens per skill.
45
46	### Engineering Swarm 🔧
47
48	\| Skill \| Triggers \| Summary \|
49	\|-------\|----------\|---------\|
50	\| `cm-tdd` \| test, TDD, red-green-refactor \| Red-Green-Refactor cycle before any implementation \|
51	\| `cm-debugging` \| bug, error, fix, debug, broken \| Root cause analysis before fixing. 5-phase investigation \|
52	\| `cm-quality-gate` \| deploy, ship, verify, quality, gate \| 6-gate verification: static analysis → blind review → ship \|
53	\| `cm-test-gate` \| test setup, CI, test infrastructure \| Setup 4-layer test gate for any project type \|
54	\| `cm-code-review` \| review, PR, feedback, branch \| Request reviews, handle feedback, complete branches \|
55	\| `cm-codeintell` \| understand codebase, call graph, impact, architecture, what calls X, what breaks \| AST knowledge graph + architecture diagrams + smart context (30% fewer tokens) \|
56	\| `cm-reactor` \| rewrite, pivot, migrate, direction change, architecture wrong, restructure \| TRIZ-powered strategic codebase re-direction — 5-phase incremental migration \|
57	\| `cm-clean-code` \| clean, dead code, refactor, code smell, DRY, SOLID, naming, messy \| 7-point hygiene gate: dead code, imports, naming, SRP, DRY, nesting \|
58
59	### Operations Swarm ⚙️
60
61	\| Skill \| Triggers \| Summary \|
62	\|-------\|----------\|---------\|
63	\| `cm-safe-deploy` \| deploy, staging, production, release \| Multi-gate deploy pipeline with rollback strategy \|
64	\| `cm-identity-guard` \| git push, deploy, Cloudflare, Supabase, account \| Verify identity before any push/deploy to prevent wrong-account \|
65	\| `cm-git-worktrees` \| branch, isolate, worktree, parallel \| Isolated git worktrees for feature work \|
66	\| `cm-terminal` \| command, terminal, run, execute \| Safe terminal execution with progress logging \|
67
68	### Security Swarm 🔒
69
70	\| Skill \| Triggers \| Summary \|
71	\|-------\|----------\|---------\|
72	\| `cm-secret-shield` \| secret, token, leak, security, scan, pre-commit, gitleaks, rotate \| Defense-in-depth: pre-commit hooks, repo scanning, token lifecycle \|
73
74	### Product Swarm 🎨
75
76	\| Skill \| Triggers \| Summary \|
77	\|-------\|----------\|---------\|
78	\| `cm-brainstorm-idea` \| analyze, enhance, improve, initiative, evaluate, review product \| Strategic analysis gate: 9 Windows + Double Diamond → 2-3 qualified options \|
79	\| `cm-planning` \| plan, design, brainstorm, feature \| Brainstorm intent → write implementation plan → then code \|
80	\| `cm-ux-master` \| UI, UX, design, interface, usability \| 48 UX Laws + 37 Design Tests + Figma/Stitch integration \|
81	\| `cm-ui-preview` \| preview, visual, mockup, render UI, wireframe \| Live UI concept generation via Google Stitch or Pencil MCP \|
82	\| `cm-dockit` \| docs, documentation, knowledge base, SOP \| Generate complete knowledge base from codebase \|
83	\| `cm-project-bootstrap` \| new project, init, bootstrap, setup \| Full project setup: design system → staging → CI → deploy \|
84	\| `cm-jtbd` \| customer discovery, JTBD, jobs to be done, product-market fit, why users churn \| JTBD canvas: Switch Interview → Outcome Metrics → Opportunity Scoring \|
85
86	### Growt

People who liked this also viewed

6 picks

Type