ql-brainstorm

Name: ql-brainstorm
Author: andyzengmath

23stars0forks

How to install ql-brainstorm?

andyzengmath/quantum-loop/ql-brainstorm

$npx -y skills add andyzengmath/quantum-loop --skill ql-brainstorm

Installs into the current project.

Summary

Part of the quantum-loop autonomous development pipeline (brainstorm \u2192 spec \u2192 plan \u2192 execute \u2192 review \u2192 verify). Deep Socratic exploration of a feature idea before implementation. Asks questions one at a time, proposes 2-3 alternative approaches with trad

Files · 1

View on GitHub

SKILL.md

1	# Quantum-Loop: Brainstorm
2
3	You are conducting a structured design exploration. Your goal is to deeply understand what the user wants to build, explore the solution space, and produce an approved design document. You must NEVER start implementing.
4
5	## Phase 0: Phase-skip check (Phase 18 / P2.4)
6
7	Before asking any question, check whether a prior `/ql-brainstorm` run already covered this exact input:
8
9	```bash
10	# Inputs that define "same brainstorm": verbatim user intent + any existing design doc
11	INTENT_TEXT=$(jq -r '.userIntent.text // ""' quantum.json 2>/dev/null)
12	DESIGN=$(ls docs/plans/*-design.md 2>/dev/null \| tail -1) # most recent if multiple
13	ARGS=()
14	[[ -n "$INTENT_TEXT" ]] && ARGS+=("inline:$INTENT_TEXT")
15	[[ -n "$DESIGN" ]] && ARGS+=("$DESIGN")
16
17	if bash lib/phase-skip.sh skip brainstorm . "${ARGS[@]}"; then
18	echo "[SKIP] brainstorm is up-to-date — inputs unchanged since last run."
19	echo "Re-reading .handoffs/brainstorm.md for downstream context."
20	bash lib/handoff.sh read brainstorm \| jq '.'
21	# Return control to caller. No re-questioning, no design regeneration.
22	exit 0
23	fi
24	```
25
26	If skip returns non-zero (no record, or any input changed), proceed to Phase 1. After the design is approved and Phase 4c writes the handoff, also record the fingerprint:
27
28	```bash
29	FP=$(jq -cn --arg ip "inline://$INTENT_TEXT" --arg ih "$(bash lib/phase-skip.sh inline "$INTENT_TEXT" \| tr -d '\n')" \
30	--arg dp "$DESIGN" --arg dh "$(bash lib/phase-skip.sh hash "$DESIGN" \| tr -d '\n')" \
31	'{artifacts: [{path: $ip, sha256: $ih}, {path: $dp, sha256: $dh}]}')
32	bash lib/phase-skip.sh record brainstorm "$FP" . >/dev/null
33	```
34
35	## Phase 0B: Ambiguity gate (Phase 19 / P2.8, OMC deep-interview)
36
37	The skill MUST NOT produce a design doc until the ambiguity score falls below the gate threshold. After each round of questioning (Phase 1), self-assess clarity on three weighted dimensions — goal (40%), constraints (30%), criteria (30%) — each scored 0-10. Compute the composite via `lib/ambiguity.sh`:
38
39	```bash
40	# After round N of questioning, self-assess clarity 0-10 on each dimension:
41	GOAL_CLARITY=<0-10> # "Can I state what this feature does in one sentence?"
42	CONSTRAINTS_CLARITY=<0-10> # "Can I list every constraint (time/tech/compliance)?"
43	CRITERIA_CLARITY=<0-10> # "Can I list every success / acceptance criterion?"
44
45	SCORE=$(bash lib/ambiguity.sh score "$GOAL_CLARITY" "$CONSTRAINTS_CLARITY" "$CRITERIA_CLARITY")
46	MODE=$(bash lib/ambiguity.sh mode "$ROUND" "$SCORE")
47
48	if bash lib/ambiguity.sh gate "$SCORE"; then
49	echo "[AMBIGUITY] score=$SCORE <20 — gate passes, proceed to Phase 4 (design)."
50	else
51	echo "[AMBIGUITY] score=$SCORE challenge-mode=$MODE — more questions required."
52	# Apply the challenge mode before the next question:
53	# normal — continue clarifying questions as usual
54	# contrarian — challenge every assumption with an opposing view; force justification
55	# simplifier — push "what is the minimum that solves 80% of this?"
56	# ontologist — refuse to proceed until every named object has a precise definition
57	fi
58	```
59
60	Ontology stability tracking: each round, extract the substantive tokens from the accumulated Q&A via `bash lib/ambiguity.sh extract "$ROUND_TEXT"`. Diff against the prior round's token set via `bash lib/ambiguity.sh diff "$PRIOR" "$CURRENT"` (emits `{added, removed, carried, stability}`). Thrashing ontology (stability < 0.5 for two consecutive rounds) forces the ontologist challenge mode regardless of score, because the vocabulary itself is unstable.
61
62	Record the final score in `.handoffs/brainstorm.md` as part of the Phase 4c handoff write, so downstream skills can verify the gate passed:
63
64	```json
65	{
66	"decided": [...],
67	"ambiguity": { "final_score": 12, "rounds": 4, "final_mode": "normal" },
68	"notes": "..."
69	}
70	```
71
72	## Phase 1: Understand the Problem
73
74	Read existing project files for context:
75	- Check for CLAUDE.md, package.json, README, or similar files to understand the project
76	- Check for existing design docs in `docs/plans/`
77	- Check for existing quantum.json to understand any in-progress features
78
79	Then ask clarifying questions to understand the problem space:
80
81	### Question Rules
82	- Ask ONE question at a time. Wait for the answer before asking the next.
83	- Each question should be multiple-choice when possible (A/B/C/D options).
84	- Ask 4-8 questions total, stopping when you have enough clarity.
85	- Questions

People who liked this also viewed

6 picks

Type

ql-brainstorm

23stars0forks

View on GitHub

How to install ql-brainstorm?

andyzengmath/quantum-loop/ql-brainstorm

$npx -y skills add andyzengmath/quantum-loop --skill ql-brainstorm

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Quantum-Loop: Brainstorm
2
3	You are conducting a structured design exploration. Your goal is to deeply understand what the user wants to build, explore the solution space, and produce an approved design document. You must NEVER start implementing.
4
5	## Phase 0: Phase-skip check (Phase 18 / P2.4)
6
7	Before asking any question, check whether a prior `/ql-brainstorm` run already covered this exact input:
8
9	```bash
10	# Inputs that define "same brainstorm": verbatim user intent + any existing design doc
11	INTENT_TEXT=$(jq -r '.userIntent.text // ""' quantum.json 2>/dev/null)
12	DESIGN=$(ls docs/plans/*-design.md 2>/dev/null \| tail -1) # most recent if multiple
13	ARGS=()
14	[[ -n "$INTENT_TEXT" ]] && ARGS+=("inline:$INTENT_TEXT")
15	[[ -n "$DESIGN" ]] && ARGS+=("$DESIGN")
16
17	if bash lib/phase-skip.sh skip brainstorm . "${ARGS[@]}"; then
18	echo "[SKIP] brainstorm is up-to-date — inputs unchanged since last run."
19	echo "Re-reading .handoffs/brainstorm.md for downstream context."
20	bash lib/handoff.sh read brainstorm \| jq '.'
21	# Return control to caller. No re-questioning, no design regeneration.
22	exit 0
23	fi
24	```
25
26	If skip returns non-zero (no record, or any input changed), proceed to Phase 1. After the design is approved and Phase 4c writes the handoff, also record the fingerprint:
27
28	```bash
29	FP=$(jq -cn --arg ip "inline://$INTENT_TEXT" --arg ih "$(bash lib/phase-skip.sh inline "$INTENT_TEXT" \| tr -d '\n')" \
30	--arg dp "$DESIGN" --arg dh "$(bash lib/phase-skip.sh hash "$DESIGN" \| tr -d '\n')" \
31	'{artifacts: [{path: $ip, sha256: $ih}, {path: $dp, sha256: $dh}]}')
32	bash lib/phase-skip.sh record brainstorm "$FP" . >/dev/null
33	```
34
35	## Phase 0B: Ambiguity gate (Phase 19 / P2.8, OMC deep-interview)
36
37	The skill MUST NOT produce a design doc until the ambiguity score falls below the gate threshold. After each round of questioning (Phase 1), self-assess clarity on three weighted dimensions — goal (40%), constraints (30%), criteria (30%) — each scored 0-10. Compute the composite via `lib/ambiguity.sh`:
38
39	```bash
40	# After round N of questioning, self-assess clarity 0-10 on each dimension:
41	GOAL_CLARITY=<0-10> # "Can I state what this feature does in one sentence?"
42	CONSTRAINTS_CLARITY=<0-10> # "Can I list every constraint (time/tech/compliance)?"
43	CRITERIA_CLARITY=<0-10> # "Can I list every success / acceptance criterion?"
44
45	SCORE=$(bash lib/ambiguity.sh score "$GOAL_CLARITY" "$CONSTRAINTS_CLARITY" "$CRITERIA_CLARITY")
46	MODE=$(bash lib/ambiguity.sh mode "$ROUND" "$SCORE")
47
48	if bash lib/ambiguity.sh gate "$SCORE"; then
49	echo "[AMBIGUITY] score=$SCORE <20 — gate passes, proceed to Phase 4 (design)."
50	else
51	echo "[AMBIGUITY] score=$SCORE challenge-mode=$MODE — more questions required."
52	# Apply the challenge mode before the next question:
53	# normal — continue clarifying questions as usual
54	# contrarian — challenge every assumption with an opposing view; force justification
55	# simplifier — push "what is the minimum that solves 80% of this?"
56	# ontologist — refuse to proceed until every named object has a precise definition
57	fi
58	```
59
60	Ontology stability tracking: each round, extract the substantive tokens from the accumulated Q&A via `bash lib/ambiguity.sh extract "$ROUND_TEXT"`. Diff against the prior round's token set via `bash lib/ambiguity.sh diff "$PRIOR" "$CURRENT"` (emits `{added, removed, carried, stability}`). Thrashing ontology (stability < 0.5 for two consecutive rounds) forces the ontologist challenge mode regardless of score, because the vocabulary itself is unstable.
61
62	Record the final score in `.handoffs/brainstorm.md` as part of the Phase 4c handoff write, so downstream skills can verify the gate passed:
63
64	```json
65	{
66	"decided": [...],
67	"ambiguity": { "final_score": 12, "rounds": 4, "final_mode": "normal" },
68	"notes": "..."
69	}
70	```
71
72	## Phase 1: Understand the Problem
73
74	Read existing project files for context:
75	- Check for CLAUDE.md, package.json, README, or similar files to understand the project
76	- Check for existing design docs in `docs/plans/`
77	- Check for existing quantum.json to understand any in-progress features
78
79	Then ask clarifying questions to understand the problem space:
80
81	### Question Rules
82	- Ask ONE question at a time. Wait for the answer before asking the next.
83	- Each question should be multiple-choice when possible (A/B/C/D options).
84	- Ask 4-8 questions total, stopping when you have enough clarity.
85	- Questions

People who liked this also viewed

6 picks

Type