add-journal

Name: add-journal
Author: Aperivue

208stars53forks

How to install add-journal?

aperivue/medsci-skills/add-journal

$npx -y skills add Aperivue/medsci-skills --skill add-journal

Installs into the current project.

Summary

Add a new journal to the MedSci Skills profile database. Extracts metadata from author guidelines, generates write-paper (detailed) and find-journal (compact) profiles in canonical format with quality gates.

Files · 1

View on GitHub

SKILL.md

1	# Add Journal Skill
2
3	You are helping a medical researcher add a new journal to the MedSci Skills profile database.
4	You generate two reference profiles per journal -- a detailed write-paper profile (~100-150 lines)
5	and a compact find-journal profile (~30 lines) -- using the journal's author guidelines as
6	the primary data source.
7
8	## Communication Rules
9
10	- Communicate with the user in their preferred language.
11	- Journal names, profile content, and URLs are always in English.
12	- Medical terminology and field names are always in English.
13	- Section headings within profiles must exactly match the canonical format defined below.
14
15	## Key Directories
16
17	Profiles live in one of two tiers — public (shipped with the skill) or user-local private
18	(per-user, never pushed to git). Pick the correct target in Phase 0 before any extraction.
19
20	### Public (shipped, must meet verification bar)
21	- Write-paper: `${CLAUDE_SKILL_DIR}/../write-paper/references/journal_profiles/`
22	- Find-journal: `${CLAUDE_SKILL_DIR}/../find-journal/references/journal_profiles/`
23
24	### User-local private (per-user override, optional)
25	- Write-paper: `$HOME/.claude/private-journal-profiles/write-paper/`
26	- Find-journal: `$HOME/.claude/private-journal-profiles/find-journal/`
27
28	Promotion workflow (private → public) is documented in
29	`${CLAUDE_SKILL_DIR}/../find-journal/POLICY.md`.
30
31	---
32
33	## Phase 0: Input Collection
34
35	### Required
36	1. Journal name -- full official name (e.g., "Journal of Clinical Oncology")
37	2. Target tier -- `public` (shipped) or `private` (user-local only)
38
39	### Strongly Encouraged
40	3. Author Guidelines URL -- primary data source for metadata extraction
41
42	### Optional
43	4. Field focus -- e.g., cardiology, oncology, surgery, general medicine, medical education, methodology
44	5. Tier estimate -- Q1 / Q2 / Q3 (user's best guess)
45	6. ISSN -- if known
46
47	If the user provides only a journal name without a URL, ask for the Author Guidelines URL
48	before proceeding. The guidelines page is the single most important data source for accurate
49	profile generation.
50
51	### Public vs. Private target selection
52
53	If the user does not state the target tier, ASK explicitly before proceeding. Use these
54	defaults and criteria to guide the question:
55
56	- Default to `private` for any journal outside the user's stated area of deep
57	expertise. Private profiles only live on the user's machine and do not need to clear
58	the public verification bar line-by-line — but the journal's Author Guidelines page
59	must still be the primary source (no inference from adjacent journals, no AI policy
60	copy-paste from the publisher family).
61	- `public` is appropriate only when all of the following hold:
62	1. The user intends to contribute the profile upstream for other researchers.
63	2. The user has opened the journal's homepage and author guidelines page and can
64	attest to each field against the live source, OR can paste the relevant sections.
65	3. AI policy wording is transcribed from the journal/publisher's own policy page,
66	not inferred from a sibling journal.
67	4. The user has completed or will complete the promotion checklist in
68	`../find-journal/POLICY.md` before commit.
69
70	If the target is `public` but the user cannot attest to (2) and (3), switch the target
71	to `private` and tell the user: promotion to public can happen later after the checklist
72	is cleared.
73
74	---
75
76	## Phase 1: Duplicate Check
77
78	Before any data extraction, check whether the journal already exists:
79
80	1. Glob all four directories (public + private across both skills):
81	```
82	${CLAUDE_SKILL_DIR}/../write-paper/references/journal_profiles/*.md
83	${CLAUDE_SKILL_DIR}/../find-journal/references/journal_profiles/*.md
84	$HOME/.claude/private-journal-profiles/write-paper/*.md
85	$HOME/.claude/private-journal-profiles/find-journal/*.md
86	```
87
88	2. Filename match: Normalize the journal name (spaces to underscores, remove special characters)
89	and check for an exact filename match.
90
91	3. Abbreviation match: Grep existing profiles for the journal's common abbreviation
92	(e.g., "JCO" for Journal of Clinical Oncology).
93
94	### If found:
95	- Report which directory/directories already have the profile, with file paths.
96	- If present in only one directory, offer to create the missing counterpart.
97	- If present in both, offer to update the existing profiles or abort.
98	- Do NOT proceed to Phase 2 without user direction.
99
100	### If not found:
101	- Confirm to user: "No existing profile found. Proceeding with data extraction."
102
103	---
104
105	## Phase 2: Data Extraction
106
107	### Path A: WebFetch Available
108
109	1. Attempt to fetch the Author Gui

People who liked this also viewed

6 picks

Type

add-journal

208stars53forks

View on GitHub

How to install add-journal?

aperivue/medsci-skills/add-journal

$npx -y skills add Aperivue/medsci-skills --skill add-journal

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Add Journal Skill
2
3	You are helping a medical researcher add a new journal to the MedSci Skills profile database.
4	You generate two reference profiles per journal -- a detailed write-paper profile (~100-150 lines)
5	and a compact find-journal profile (~30 lines) -- using the journal's author guidelines as
6	the primary data source.
7
8	## Communication Rules
9
10	- Communicate with the user in their preferred language.
11	- Journal names, profile content, and URLs are always in English.
12	- Medical terminology and field names are always in English.
13	- Section headings within profiles must exactly match the canonical format defined below.
14
15	## Key Directories
16
17	Profiles live in one of two tiers — public (shipped with the skill) or user-local private
18	(per-user, never pushed to git). Pick the correct target in Phase 0 before any extraction.
19
20	### Public (shipped, must meet verification bar)
21	- Write-paper: `${CLAUDE_SKILL_DIR}/../write-paper/references/journal_profiles/`
22	- Find-journal: `${CLAUDE_SKILL_DIR}/../find-journal/references/journal_profiles/`
23
24	### User-local private (per-user override, optional)
25	- Write-paper: `$HOME/.claude/private-journal-profiles/write-paper/`
26	- Find-journal: `$HOME/.claude/private-journal-profiles/find-journal/`
27
28	Promotion workflow (private → public) is documented in
29	`${CLAUDE_SKILL_DIR}/../find-journal/POLICY.md`.
30
31	---
32
33	## Phase 0: Input Collection
34
35	### Required
36	1. Journal name -- full official name (e.g., "Journal of Clinical Oncology")
37	2. Target tier -- `public` (shipped) or `private` (user-local only)
38
39	### Strongly Encouraged
40	3. Author Guidelines URL -- primary data source for metadata extraction
41
42	### Optional
43	4. Field focus -- e.g., cardiology, oncology, surgery, general medicine, medical education, methodology
44	5. Tier estimate -- Q1 / Q2 / Q3 (user's best guess)
45	6. ISSN -- if known
46
47	If the user provides only a journal name without a URL, ask for the Author Guidelines URL
48	before proceeding. The guidelines page is the single most important data source for accurate
49	profile generation.
50
51	### Public vs. Private target selection
52
53	If the user does not state the target tier, ASK explicitly before proceeding. Use these
54	defaults and criteria to guide the question:
55
56	- Default to `private` for any journal outside the user's stated area of deep
57	expertise. Private profiles only live on the user's machine and do not need to clear
58	the public verification bar line-by-line — but the journal's Author Guidelines page
59	must still be the primary source (no inference from adjacent journals, no AI policy
60	copy-paste from the publisher family).
61	- `public` is appropriate only when all of the following hold:
62	1. The user intends to contribute the profile upstream for other researchers.
63	2. The user has opened the journal's homepage and author guidelines page and can
64	attest to each field against the live source, OR can paste the relevant sections.
65	3. AI policy wording is transcribed from the journal/publisher's own policy page,
66	not inferred from a sibling journal.
67	4. The user has completed or will complete the promotion checklist in
68	`../find-journal/POLICY.md` before commit.
69
70	If the target is `public` but the user cannot attest to (2) and (3), switch the target
71	to `private` and tell the user: promotion to public can happen later after the checklist
72	is cleared.
73
74	---
75
76	## Phase 1: Duplicate Check
77
78	Before any data extraction, check whether the journal already exists:
79
80	1. Glob all four directories (public + private across both skills):
81	```
82	${CLAUDE_SKILL_DIR}/../write-paper/references/journal_profiles/*.md
83	${CLAUDE_SKILL_DIR}/../find-journal/references/journal_profiles/*.md
84	$HOME/.claude/private-journal-profiles/write-paper/*.md
85	$HOME/.claude/private-journal-profiles/find-journal/*.md
86	```
87
88	2. Filename match: Normalize the journal name (spaces to underscores, remove special characters)
89	and check for an exact filename match.
90
91	3. Abbreviation match: Grep existing profiles for the journal's common abbreviation
92	(e.g., "JCO" for Journal of Clinical Oncology).
93
94	### If found:
95	- Report which directory/directories already have the profile, with file paths.
96	- If present in only one directory, offer to create the missing counterpart.
97	- If present in both, offer to update the existing profiles or abort.
98	- Do NOT proceed to Phase 2 without user direction.
99
100	### If not found:
101	- Confirm to user: "No existing profile found. Proceeding with data extraction."
102
103	---
104
105	## Phase 2: Data Extraction
106
107	### Path A: WebFetch Available
108
109	1. Attempt to fetch the Author Gui

People who liked this also viewed

6 picks

Type