plannotator-setup-goal

Name: plannotator-setup-goal
Author: backnotprop

7.2kstars517forks

How to install plannotator-setup-goal?

backnotprop/plannotator/plannotator-setup-goal

$npx -y skills add backnotprop/plannotator --skill plannotator-setup-goal

Installs into the current project.

Summary

Turn an idea or objective into a goal package for /goal. Interviews the user, builds a reviewed fact sheet via Plannotator, then explores the codebase to produce an execution plan.

Files · 1

View on GitHub

SKILL.md

1	# Setup Goal
2
3	Turn an idea into a goal package at `goals/<slug>/` through structured discovery, user interview, and codebase exploration.
4
5	## Phases
6
7	### 1. Rearticulate
8
9	State back what the user wants in your own words. If the conversation already has rich context, summarize it. If the goal is bare or vague, do minimal shallow exploration of the codebase to ground your understanding. Keep it to 2-3 sentences. Wait for the user to confirm or correct before continuing.
10
11	Create the goal directory once the slug is clear:
12
13	```bash
14	mkdir -p goals/<slug>
15	```
16
17	Use `goals/<slug>/` for both working JSON files and final docs. The JSON files are provenance and iteration state; the markdown files are the human-readable authoritative goal package.
18
19	Browser session patience rule: Plannotator goal setup is a user-driven browser session. After launching an interview or facts command, be absolutely patient and keep waiting on the user until they submit, dismiss, or explicitly ask you to stop. Do not close, kill, restart, refresh, or open a second copy just because the UI is idle or the user is taking time. Never close and reopen the session as a way to update state; if a rerun is needed after the prior session ends, update the working JSON file and launch a new command from that file.
20
21	Optional: grill first (deep, one-at-a-time interview). Before building the compact interview bundle, suggest a grilling pass whenever the goal is vague or carries many interdependent decisions — and run one whenever the user asks for it ("grill me first"). This is opt-in: for a clear, well-scoped goal, skip it and go straight to the bundle, so grilling never fights the bundle's "fewer, higher-leverage questions" philosophy. When you grill, run the protocol below verbatim, then fold the resolved decisions forward into a higher-quality interview bundle (Phase 2) — or, if grilling fully resolves scope, straight into the fact sheet (Phase 3).
22
23	<!-- Grilling protocol below adapted verbatim from the /grill-me skill by Matt Pocock (MIT-licensed):
24	https://github.com/mattpocock/skills/blob/main/skills/productivity/grill-me/SKILL.md -->
25
26	> Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
27	>
28	> Ask the questions one at a time.
29	>
30	> If a question can be answered by exploring the codebase, explore the codebase instead.
31
32	### 2. Interview Bundle
33
34	Build a compact bundle of questions that can derive every "fact" this goal should produce. Package the questions together so the user can answer them quickly in the Plannotator goal setup UI. For each question, include your recommended answer and use options when they make answering faster.
35
36	Do not ask obvious confirmation questions. If the answer can be inferred from the user's request, from the conversation, or from shallow codebase exploration, infer it and move on. If an obvious area has meaningful nuance, present the inferred answer as a recommendation with options or a custom "add/correct this" path rather than asking the user to restate the obvious.
37
38	Question areas that usually matter:
39
40	- What the feature/change is
41	- Who it's for
42	- What problem it solves
43	- What behavior changes
44	- What success looks like
45	- What's in and out of scope (the most important area to determine facts)
46	- What edge cases to consider
47	- What constraints or precedent apply
48
49	If a question can be answered by exploring the codebase, explore the codebase instead of asking. Only include questions where the user's judgment is actually needed. Prefer fewer, higher-leverage questions over exhaustive obvious ones.
50
51	Write the interview bundle before showing it to the user:
52
53	`goals/<slug>/interview.json`
54
55	```json
56	{
57	"stage": "interview",
58	"title": "Short human-readable title",
59	"goalSlug": "<slug>",
60	"questions": [
61	{
62	"id": "scope",
63	"prompt": "What should be in scope?",
64	"description": "Optional clarification.",
65	"answerMode": "multi-custom",
66	"recommendedAnswer": "Your recommended answer.",
67	"recommendedOptionIds": ["ui", "server"],
68	"options": [
69	{ "id": "ui", "label": "UI" },
70	{ "id": "server", "label": "Server" }
71	],
72	"required": true
73	}
74	]
75	}
76	```
77
78	Supported `answerMode` values: `text`, `single`, `multi`, `custom`, `single-custom`, `multi-custom`.
79
80	Run this as a monitored foreground process and wait patiently for the browser session to finish. The command may appear idle while the user is reading, editing, or asking questions; leave it running:
81
82	```bash
83	plannotator setup-goal interview goals/<slug>/interview.js

People who liked this also viewed

6 picks

Type

plannotator-setup-goal

7.2kstars517forks

View on GitHub

How to install plannotator-setup-goal?

backnotprop/plannotator/plannotator-setup-goal

$npx -y skills add backnotprop/plannotator --skill plannotator-setup-goal

Installs into the current project.

Summary

Turn an idea or objective into a goal package for /goal. Interviews the user, builds a reviewed fact sheet via Plannotator, then explores the codebase to produce an execution plan.

Files · 1

View on GitHub

SKILL.md

1	# Setup Goal
2
3	Turn an idea into a goal package at `goals/<slug>/` through structured discovery, user interview, and codebase exploration.
4
5	## Phases
6
7	### 1. Rearticulate
8
9	State back what the user wants in your own words. If the conversation already has rich context, summarize it. If the goal is bare or vague, do minimal shallow exploration of the codebase to ground your understanding. Keep it to 2-3 sentences. Wait for the user to confirm or correct before continuing.
10
11	Create the goal directory once the slug is clear:
12
13	```bash
14	mkdir -p goals/<slug>
15	```
16
17	Use `goals/<slug>/` for both working JSON files and final docs. The JSON files are provenance and iteration state; the markdown files are the human-readable authoritative goal package.
18
19	Browser session patience rule: Plannotator goal setup is a user-driven browser session. After launching an interview or facts command, be absolutely patient and keep waiting on the user until they submit, dismiss, or explicitly ask you to stop. Do not close, kill, restart, refresh, or open a second copy just because the UI is idle or the user is taking time. Never close and reopen the session as a way to update state; if a rerun is needed after the prior session ends, update the working JSON file and launch a new command from that file.
20
21	Optional: grill first (deep, one-at-a-time interview). Before building the compact interview bundle, suggest a grilling pass whenever the goal is vague or carries many interdependent decisions — and run one whenever the user asks for it ("grill me first"). This is opt-in: for a clear, well-scoped goal, skip it and go straight to the bundle, so grilling never fights the bundle's "fewer, higher-leverage questions" philosophy. When you grill, run the protocol below verbatim, then fold the resolved decisions forward into a higher-quality interview bundle (Phase 2) — or, if grilling fully resolves scope, straight into the fact sheet (Phase 3).
22
23	<!-- Grilling protocol below adapted verbatim from the /grill-me skill by Matt Pocock (MIT-licensed):
24	https://github.com/mattpocock/skills/blob/main/skills/productivity/grill-me/SKILL.md -->
25
26	> Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
27	>
28	> Ask the questions one at a time.
29	>
30	> If a question can be answered by exploring the codebase, explore the codebase instead.
31
32	### 2. Interview Bundle
33
34	Build a compact bundle of questions that can derive every "fact" this goal should produce. Package the questions together so the user can answer them quickly in the Plannotator goal setup UI. For each question, include your recommended answer and use options when they make answering faster.
35
36	Do not ask obvious confirmation questions. If the answer can be inferred from the user's request, from the conversation, or from shallow codebase exploration, infer it and move on. If an obvious area has meaningful nuance, present the inferred answer as a recommendation with options or a custom "add/correct this" path rather than asking the user to restate the obvious.
37
38	Question areas that usually matter:
39
40	- What the feature/change is
41	- Who it's for
42	- What problem it solves
43	- What behavior changes
44	- What success looks like
45	- What's in and out of scope (the most important area to determine facts)
46	- What edge cases to consider
47	- What constraints or precedent apply
48
49	If a question can be answered by exploring the codebase, explore the codebase instead of asking. Only include questions where the user's judgment is actually needed. Prefer fewer, higher-leverage questions over exhaustive obvious ones.
50
51	Write the interview bundle before showing it to the user:
52
53	`goals/<slug>/interview.json`
54
55	```json
56	{
57	"stage": "interview",
58	"title": "Short human-readable title",
59	"goalSlug": "<slug>",
60	"questions": [
61	{
62	"id": "scope",
63	"prompt": "What should be in scope?",
64	"description": "Optional clarification.",
65	"answerMode": "multi-custom",
66	"recommendedAnswer": "Your recommended answer.",
67	"recommendedOptionIds": ["ui", "server"],
68	"options": [
69	{ "id": "ui", "label": "UI" },
70	{ "id": "server", "label": "Server" }
71	],
72	"required": true
73	}
74	]
75	}
76	```
77
78	Supported `answerMode` values: `text`, `single`, `multi`, `custom`, `single-custom`, `multi-custom`.
79
80	Run this as a monitored foreground process and wait patiently for the browser session to finish. The command may appear idle while the user is reading, editing, or asking questions; leave it running:
81
82	```bash
83	plannotator setup-goal interview goals/<slug>/interview.js

People who liked this also viewed

6 picks

Type