@skilly-hand/skilly-hand 0.10.5 → 0.11.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/catalog/README.md CHANGED
@@ -9,6 +9,7 @@ Published portable skills consumed by the `skilly-hand` CLI.
9
9
  | `angular-guidelines` | Guide Angular code generation and review using latest stable Angular verification and modern framework best practices. | angular, frontend, workflow, best-practices | all |
10
10
  | `figma-mcp-0to1` | Guide users from Figma MCP installation and authentication through first canvas creation, with function-level tool coverage and operational recovery patterns. | figma, mcp, workflow, design | all |
11
11
  | `frontend-design` | Project-aware frontend design skill that detects the existing tech stack, UI libraries, CSS variables, and design tokens before proposing any UI work. | frontend, design, workflow, ui | all |
12
+ | `project-teacher` | Scan the active project and teach any concept, code path, or decision using verified information, interactive questions, and simple explanations. | core, workflow, education | all |
12
13
  | `react-guidelines` | Guide React code generation and review using latest stable React verification and modern framework best practices. | react, frontend, workflow, best-practices | all |
13
14
  | `review-rangers` | Review code, decisions, and artifacts through a multi-perspective committee and a domain expert safety guard, then synthesize a structured verdict. | core, workflow, review, quality | all |
14
15
  | `skill-creator` | Create and standardize AI skills with reusable structure, metadata rules, and templates. | core, workflow, authoring | all |
@@ -4,6 +4,7 @@
4
4
  "angular-guidelines",
5
5
  "figma-mcp-0to1",
6
6
  "frontend-design",
7
+ "project-teacher",
7
8
  "react-guidelines",
8
9
  "review-rangers",
9
10
  "skill-creator",
@@ -0,0 +1,143 @@
1
+ # Project Teacher Guide
2
+
3
+ ## When to Use
4
+
5
+ Use this skill when:
6
+
7
+ - The user asks to explain, understand, or clarify anything — code, architecture, decisions, or concepts.
8
+ - The user asks "what is", "why does", "how does", "what happens when", or similar questions.
9
+ - Clarification is needed during an SDD planning session before writing a spec.
10
+ - A concept needs to be broken down into simpler terms before implementation begins.
11
+ - The user wants to understand the reasoning or history behind a decision in the codebase.
12
+
13
+ Do not use this skill for:
14
+
15
+ - Writing, generating, or modifying code.
16
+ - Creating specs, plans, or implementation tasks.
17
+ - Running tests or build commands.
18
+
19
+ ---
20
+
21
+ ## Core Teaching Loop
22
+
23
+ Every explanation follows this 4-step loop:
24
+
25
+ 1. **Scan** — Read the relevant parts of the project before answering.
26
+ 2. **Clarify** — Ask 1–2 targeted questions to understand what the user already knows and what depth they need.
27
+ 3. **Explain** — Deliver the explanation using verified facts, citing file paths where relevant.
28
+ 4. **Check Understanding** — Ask if the explanation landed or if any part needs to go deeper.
29
+
30
+ Never skip the Scan step. Never state something as fact without verifying it in the code first.
31
+
32
+ ---
33
+
34
+ ## Scan Protocol
35
+
36
+ Before answering any question, scan the project:
37
+
38
+ ```text
39
+ 1. Identify the entry points (e.g., index.ts, main.ts, App.tsx, package.json).
40
+ 2. Find the files most relevant to the question (use Glob + Grep).
41
+ 3. Read the relevant sections — functions, imports, config, comments.
42
+ 4. Note the actual behavior, not assumed behavior.
43
+ 5. Only then compose the explanation.
44
+ ```
45
+
46
+ Scan rules:
47
+
48
+ - Never explain from memory alone; always verify against the current code.
49
+ - If the answer requires understanding a dependency, read it or look it up.
50
+ - If the codebase contradicts a general best practice, explain what the code actually does.
51
+
52
+ ---
53
+
54
+ ## Interaction Patterns
55
+
56
+ Before explaining, ask 1–2 focused questions to calibrate:
57
+
58
+ | Situation | Question to Ask |
59
+ | --- | --- |
60
+ | Unclear what level of detail is needed | "Would you like a quick overview or a deeper walkthrough?" |
61
+ | Unclear what the user already knows | "Are you familiar with [concept X], or should I start from scratch?" |
62
+ | Multiple possible angles | "Are you more interested in how it works internally or why it was designed this way?" |
63
+ | SDD context | "Is this to clarify requirements before writing a spec, or to understand existing behavior?" |
64
+
65
+ Rules:
66
+
67
+ - Ask at most 2 questions before explaining — do not interrogate.
68
+ - If the question is already crystal clear, skip directly to explanation.
69
+ - After explaining, always close with: "Does this make sense, or would you like me to go deeper on any part?"
70
+
71
+ ---
72
+
73
+ ## Explanation Modes
74
+
75
+ Choose the mode that fits the question and the user's answer to your calibration questions:
76
+
77
+ | Mode | When to Use | Format |
78
+ | --- | --- | --- |
79
+ | **Quick Overview** | User wants orientation, not depth | 3–5 bullet points + 1 example |
80
+ | **Deep Dive** | User wants to fully understand | Step-by-step prose + code references + file:line citations |
81
+ | **Analogy** | Abstract or unfamiliar concept | Real-world comparison + 1 short code example |
82
+ | **Trace-Through** | User wants to follow execution | Numbered steps tracing the code path from trigger to outcome |
83
+
84
+ Mix modes when helpful — for example, start with an Analogy then transition to a Trace-Through for complex topics.
85
+
86
+ ---
87
+
88
+ ## Decision Tree
89
+
90
+ ```text
91
+ What kind of question is this?
92
+
93
+ "What is X?" or "What does X do?"
94
+ -> Quick Overview or Deep Dive based on user preference
95
+
96
+ "Why does X work this way?" or "Why was X chosen?"
97
+ -> Deep Dive + cite relevant code comments, config, or git context if available
98
+
99
+ "How does X flow / execute / work internally?"
100
+ -> Trace-Through mode
101
+
102
+ "I don't understand X at all"
103
+ -> Analogy first, then offer a follow-up Trace-Through
104
+
105
+ Clarifying requirements before writing a spec?
106
+ -> Deep Dive focused on constraints and behavior; hand off to spec-driven-development when done
107
+ ```
108
+
109
+ ---
110
+
111
+ ## SDD Companion Rules
112
+
113
+ When `project-teacher` is invoked during a `spec-driven-development` session:
114
+
115
+ 1. Pause the SDD workflow to answer the clarifying question.
116
+ 2. Use Deep Dive or Trace-Through — shallow answers during planning create bad specs.
117
+ 3. After explaining, summarize what was clarified in one sentence the user can paste directly into the spec's `Why` or `Constraints` section.
118
+ 4. Return control to the SDD workflow explicitly: "Ready to continue with the spec?"
119
+
120
+ ---
121
+
122
+ ## Quality Rules
123
+
124
+ - **Only state verified facts.** If you haven't read the file, don't claim to know what it does.
125
+ - **Cite sources.** Reference `file.ts:42` or `config/settings.json` when making specific claims.
126
+ - **Separate fact from inference.** If you're reasoning about intent rather than reading it directly, say so: "Based on the code, it looks like..." vs. "The code does...".
127
+ - **No hallucinated APIs.** If an external API or library behavior is in question, use WebFetch or WebSearch to verify before explaining.
128
+ - **Keep it simple by default.** Use plain language first. Introduce jargon only when it adds precision, and always define it when you do.
129
+
130
+ ---
131
+
132
+ ## Commands
133
+
134
+ ```bash
135
+ # Find entry points to scan
136
+ ls package.json tsconfig.json src/index.* src/main.* src/App.*
137
+
138
+ # Search for a concept across the project
139
+ grep -r "conceptName" src/ --include="*.ts" -l
140
+
141
+ # Read a specific file section
142
+ cat -n src/path/to/file.ts | head -60
143
+ ```
@@ -0,0 +1,24 @@
1
+ {
2
+ "id": "project-teacher",
3
+ "title": "Project Teacher",
4
+ "description": "Scan the active project and teach any concept, code path, or decision using verified information, interactive questions, and simple explanations. Trigger: user asks to explain, understand, clarify, or learn about anything in the project or codebase.",
5
+ "portable": true,
6
+ "tags": ["core", "workflow", "education"],
7
+ "detectors": ["always"],
8
+ "detectionTriggers": ["always"],
9
+ "installsFor": ["all"],
10
+ "agentSupport": ["codex", "claude", "cursor", "gemini", "copilot", "antigravity", "windsurf", "trae"],
11
+ "skillMetadata": {
12
+ "author": "skilly-hand",
13
+ "last-edit": "2026-04-04",
14
+ "license": "Apache-2.0",
15
+ "version": "1.0.0",
16
+ "changelog": "Initial release of project-teacher skill; provides interactive, project-grounded teaching for any concept or code path; affects education and clarification workflows across all projects",
17
+ "auto-invoke": "User needs to understand, explain, or learn about any aspect of the project or codebase",
18
+ "allowed-tools": ["Read", "Glob", "Grep", "Bash", "WebFetch", "WebSearch"]
19
+ },
20
+ "files": [
21
+ { "path": "SKILL.md", "kind": "instruction" }
22
+ ],
23
+ "dependencies": []
24
+ }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@skilly-hand/skilly-hand",
3
- "version": "0.10.5",
3
+ "version": "0.11.0",
4
4
  "license": "CC-BY-NC-4.0",
5
5
  "type": "module",
6
6
  "publishConfig": {