revision-escalation

Name: revision-escalation
Author: yha9806

24stars3forks

How to install revision-escalation?

yha9806/academic-writing-toolkit/revision-escalation

$npx -y skills add yha9806/academic-writing-toolkit --skill revision-escalation

Installs into the current project.

Summary

Stop repeated failed writing, coding, manuscript, rebuttal, or restructuring revisions when the same issue has gone through 3+ unsatisfactory edits, vague feedback such as still wrong/weird/unclear/weak/越改越乱, version contamination, or possible gap/claim/evidence/venue-fit drift.

Files · 1

View on GitHub

SKILL.md

1	# /revision-escalation - 3-Strike Revision Control
2
3	## Purpose
4
5	Prevent repeated local patches from making a draft or code path more inconsistent. Use this when the issue may no longer be wording or implementation detail, but specification, structure, evidence, or version-control drift.
6
7	## Trigger Words
8
9	This skill activates on: `revision escalation`, `3-strike`, `three strikes`, `stop and diagnose`, `still wrong`, `still weird`, `unclear`, `weak`, `越改越乱`, `还是不对`, `还是怪`, `不够清楚`, `逻辑还是混乱`, `/revision-escalation`.
10
11	## Core Rule
12
13	If the same issue remains unresolved after 3 revision attempts, treat it as a specification or structure problem before treating it as another local editing task.
14
15	Do not make a fourth patch immediately.
16
17	## Revision Escalation Check
18
19	Before editing again, classify the problem:
20
21	\| Category \| Meaning \| Next action \|
22	\| --- \| --- \| --- \|
23	\| Underspecified request \| Target, constraint, audience, venue, or expected output is missing. \| Ask for a concrete target before editing. \|
24	\| Ambiguous feedback \| Feedback is evaluative but not operational: "weird", "weak", "unclear", "not good enough". \| Ask what should change. \|
25	\| Local execution problem \| The goal is clear, but the previous patch implemented it incorrectly. \| Make one small targeted patch. \|
26	\| Structural mismatch \| The issue affects the research question, gap, contribution, evidence chain, section structure, module boundary, or venue framing. \| Propose a restructure plan before editing. \|
27	\| Evidence gap \| The desired claim is unsupported by available data, experiments, citations, or files. \| Downgrade the claim or request evidence. \|
28	\| Version contamination \| Repeated patches have mixed old assumptions with new requirements, causing inconsistency, duplication, or bloat. \| Recommend a new version, branch, or consolidated brief. \|
29
30	## Required Response
31
32	When triggered, respond in this structure before any patch:
33
34	```md
35	I should pause before making another patch.
36
37	This issue has already gone through several revision rounds and may not be a local wording or implementation problem anymore.
38
39	Current diagnosis:
40
41	* Category:
42	* Why:
43	* What is missing or conflicting:
44	* Recommended next action:
45
46	Options:
47	A. Clarify the concrete target and continue a local patch.
48	B. Consolidate all current requirements into a single brief, then retry.
49	C. Create a new version or branch and restructure the section/module.
50	D. Reframe the paper/project from the research question, gap, and evidence chain.
51	```
52
53	## Academic Writing Rule
54
55	Classify manuscript work before editing:
56
57	- Local patch: wording, grammar, citation format, figure caption, table formatting, or one paragraph.
58	- Section-level restructure: one section changes, but the research question, contribution, and evidence chain stay stable.
59	- Full reframing: title, abstract, introduction, research question, gap, contribution, methods-results alignment, discussion, or venue framing changes.
60
61	For full reframing, do not directly rewrite the manuscript. First produce a reframing brief with target venue, research question, gap, core claim, available evidence, claims that must not be made, and proposed new structure.
62
63	## Red Flags
64
65	Stop and diagnose when thinking:
66
67	- "One more patch should fix it."
68	- "The user is still dissatisfied, but I can just rewrite harder."
69	- "The wording is awkward" while the evidence chain or contribution boundary is unstable.
70	- "The current version is messy, but I can keep accumulating edits."
71
72	Never continue accumulating edits on a structurally inconsistent manuscript, rebuttal, or code path.

People who liked this also viewed

6 picks

Type

revision-escalation

24stars3forks

View on GitHub

How to install revision-escalation?

yha9806/academic-writing-toolkit/revision-escalation

$npx -y skills add yha9806/academic-writing-toolkit --skill revision-escalation

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# /revision-escalation - 3-Strike Revision Control
2
3	## Purpose
4
5	Prevent repeated local patches from making a draft or code path more inconsistent. Use this when the issue may no longer be wording or implementation detail, but specification, structure, evidence, or version-control drift.
6
7	## Trigger Words
8
9	This skill activates on: `revision escalation`, `3-strike`, `three strikes`, `stop and diagnose`, `still wrong`, `still weird`, `unclear`, `weak`, `越改越乱`, `还是不对`, `还是怪`, `不够清楚`, `逻辑还是混乱`, `/revision-escalation`.
10
11	## Core Rule
12
13	If the same issue remains unresolved after 3 revision attempts, treat it as a specification or structure problem before treating it as another local editing task.
14
15	Do not make a fourth patch immediately.
16
17	## Revision Escalation Check
18
19	Before editing again, classify the problem:
20
21	\| Category \| Meaning \| Next action \|
22	\| --- \| --- \| --- \|
23	\| Underspecified request \| Target, constraint, audience, venue, or expected output is missing. \| Ask for a concrete target before editing. \|
24	\| Ambiguous feedback \| Feedback is evaluative but not operational: "weird", "weak", "unclear", "not good enough". \| Ask what should change. \|
25	\| Local execution problem \| The goal is clear, but the previous patch implemented it incorrectly. \| Make one small targeted patch. \|
26	\| Structural mismatch \| The issue affects the research question, gap, contribution, evidence chain, section structure, module boundary, or venue framing. \| Propose a restructure plan before editing. \|
27	\| Evidence gap \| The desired claim is unsupported by available data, experiments, citations, or files. \| Downgrade the claim or request evidence. \|
28	\| Version contamination \| Repeated patches have mixed old assumptions with new requirements, causing inconsistency, duplication, or bloat. \| Recommend a new version, branch, or consolidated brief. \|
29
30	## Required Response
31
32	When triggered, respond in this structure before any patch:
33
34	```md
35	I should pause before making another patch.
36
37	This issue has already gone through several revision rounds and may not be a local wording or implementation problem anymore.
38
39	Current diagnosis:
40
41	* Category:
42	* Why:
43	* What is missing or conflicting:
44	* Recommended next action:
45
46	Options:
47	A. Clarify the concrete target and continue a local patch.
48	B. Consolidate all current requirements into a single brief, then retry.
49	C. Create a new version or branch and restructure the section/module.
50	D. Reframe the paper/project from the research question, gap, and evidence chain.
51	```
52
53	## Academic Writing Rule
54
55	Classify manuscript work before editing:
56
57	- Local patch: wording, grammar, citation format, figure caption, table formatting, or one paragraph.
58	- Section-level restructure: one section changes, but the research question, contribution, and evidence chain stay stable.
59	- Full reframing: title, abstract, introduction, research question, gap, contribution, methods-results alignment, discussion, or venue framing changes.
60
61	For full reframing, do not directly rewrite the manuscript. First produce a reframing brief with target venue, research question, gap, core claim, available evidence, claims that must not be made, and proposed new structure.
62
63	## Red Flags
64
65	Stop and diagnose when thinking:
66
67	- "One more patch should fix it."
68	- "The user is still dissatisfied, but I can just rewrite harder."
69	- "The wording is awkward" while the evidence chain or contribution boundary is unstable.
70	- "The current version is messy, but I can keep accumulating edits."
71
72	Never continue accumulating edits on a structurally inconsistent manuscript, rebuttal, or code path.

People who liked this also viewed

6 picks

Type