Refresh pstack to 0.15.30 from cursor/plugins

Import the pstack subtree of cursor/plugins commit 9b93e81fb2921b9263d9463c15bafeabfe3903aa. Preserve the standalone repository history and upstream file bytes. Adds statechart support.

Kris Yotam committed 2 weeks agomain

Commit 21774ee1 parent eef436c21 files · +7343 −11Browse files

Showing the changes to docs (3 of 21 files). Show all

Unified · Split

3 files

docs/guide/02-poteto-mode.md +2 −2
docs/guide/06-verify-and-ship.md +14 −0
docs/guide/10-recipes-and-pitfalls.md +2 −2

docs/guide/02-poteto-mode.md+2−2

@@ -66,13 +66,13 @@ For a noisy report, such as a long thread or a vague bug, make the restatement t · 65 unmodified lines
66	66
67	67	A misreading shows up in the restatement, before any code exists. Correct it there, and it costs you one message instead of one wrong fix. For the restatement alone, with no playbook, run [`/in-your-own-words`](../../skills/in-your-own-words/SKILL.md). It restates what the agent thinks your goals are and what problem you're trying to solve.
68	68
69		−When you're unsure whether a task is aimed right, put [`/sharpen`](../../skills/sharpen/SKILL.md) in front of it:
	69	+When you're unsure whether a prompt is aimed right, run [`/sharpen`](../../skills/sharpen/SKILL.md) on it before you send it:
70	70
71	71	```text
72	72	/sharpen write a migration guide for the v2 config format.
73	73	```
74	74
75		−Before it starts, the agent asks how a top expert would do the task, what you're really after, and whether the ask is over- or underspecified. It drops constraints that don't serve the goal as readily as it adds ones that do, leaves your choices open, and keeps one outside check that the result is right. Then it does the work.
	75	+The agent says what a top professional would do that you didn't ask for, the rawest material they would start from, the methods and tools they would use, and what other than you or the agent would show the result is right. Then it rewrites your prompt to ask for exactly that, deeper but not bigger, and leaves your choices open. It doesn't do the task. Read the rewrite, then send it, for example with `/poteto-mode`.
76	76
77	77	## Follow up short
78	78

docs/guide/06-verify-and-ship.md+14−0

@@ -115,6 +115,20 @@ It writes a project-local skill that tells the next agent whether a change touch · 114 unmodified lines
115	115
116	116	The skill also records which code each check covers and the commit where the check last matched it. Merges and refactors that skip the skill can leave the check passing on a description of code that's gone. After them, run [`/maintain-formal-verification-skill`](../../skills/maintain-formal-verification-skill/SKILL.md). It updates the verification from the code, reruns it, shows that each updated check can still fail, and tells you whether each failure is drift in the verification or a bug in the code.
117	117
	118	+## Show the behavior as a statechart
	119	+
	120	+A counterexample in model terms convinces you. The PM or designer who owns the behavior needs to see it in their terms. Run:
	121	+
	122	+```text
	123	+/statechart what the user sees when they edit a note offline
	124	+```
	125	+
	126	+[`/statechart`](../../skills/statechart/SKILL.md) draws a Mermaid statechart of what the user sees, generated from a TLA+ model, so the picture and the checked model can't drift apart. The reader's rules ("you never see Synced while you're offline") become invariants. Each bug TLC finds is a numbered path in the reader's words, and each state is marked works, still wrong, or fixed by your open PR. Before the hand-off, the agent reproduces each bug path in the real code, so a modeling error doesn't reach the reader as a bug.
	127	+
	128	+It also runs the other way. Sketch the behavior as a chart, agree on it with the reader, and the skill writes a TLA+ skeleton from it. TLC checks the agreed chart's rules before any code exists. As guards from the real code go into the spec, each place the code departs from the chart shows up as a difference for the reader to decide.
	129	+
	130	+When the code already has a TLA+ spec, the skill can audit the code against it. The agent models what the code does and checks that model next to the unchanged spec. The chart marks the steps where the two differ, and each rule either one breaks is a numbered path.
	131	+
118	132	## Open the PR
119	133
120	134	```text

docs/guide/10-recipes-and-pitfalls.md+2−2

@@ -20,13 +20,13 @@ Mechanics first, history second. Each skill's report tells you which sources it · 19 unmodified lines
20	20
21	21	A misreading shows up in the restatement, where it costs one message to correct. Keep your own theory to yourself until the agent has stated its own. `/in-your-own-words` asks for the restatement alone, with no playbook.
22	22
23		−## Aim a task before it starts
	23	+## Sharpen a prompt before you send it
24	24
25	25	```text
26	26	/sharpen write the onboarding doc for the new billing service.
27	27	```
28	28
29		−The agent asks how an expert would do the task, what you're really after, and whether the ask says too much or too little. It keeps one outside check that the result is right, then does the work.
	29	+The agent names what an expert would do that you didn't ask for, the raw material they'd start from, their methods and tools, and an outside check that the result is right. It hands back your prompt rewritten to ask for that and doesn't do the task. Send the rewrite when it reads right.
30	30
31	31	## Prototype before you pick
32	32