lit-review

Name: lit-review
Author: neuromechanist

37stars7forks

How to install lit-review?

neuromechanist/research-skills/lit-review

$npx -y skills add neuromechanist/research-skills --skill lit-review

Installs into the current project.

Summary

Use this skill for \"literature review workflow\", \"multi-phase lit review\", \"direction paper\", \"review paper protocol\", \"strand-based literature review\", \"citation-grounded review\", \"systematic lit review with paper cards\", \"build a lit review corpus\", \"lit review

Files · 1

View on GitHub

SKILL.md

1	# Multi-Phase Literature Review Workflow
2
3	Orchestrate a rigorous, citation-grounded literature review across phases: angles to briefs, parallel paper collection, taxonomic synthesis, direction papers, and self-review loops. Every claim in a final document is traceable back to a paper-card.
4
5	## When to Use
6
7	- Building a corpus-grounded review paper or a set of direction documents
8	- Multi-strand reviews where breadth + depth must be coordinated across distinct angles (e.g. tools strand, data strand, science strand)
9	- Reviews where claim-to-evidence traceability matters (grant lit reviews, position papers, white papers)
10	- Iterative reviews where new papers, refined angles, or updated synthesis must roll forward without losing prior work
11
12	## When NOT to Use
13
14	- Original research IMRAD writing. Use `manuscript:manuscript-writing`.
15	- Peer review of a submitted manuscript. Use `manuscript:paper-review`.
16	- Journal formatting. Use `manuscript:manuscript-formatting`.
17
18	## Two modes
19
20	This skill covers two workflows:
21
22	- Express mode (single-pass synthesis): thematic synthesis for an Introduction, Background section, or quick standalone review. See [references/single-pass-synthesis.md](references/single-pass-synthesis.md). Pair with [references/review-frameworks.md](references/review-frameworks.md) for PRISMA, PICO, SPIDER, scoping protocol, and risk-of-bias tools.
23	- Full protocol (multi-phase): citation-traceable corpus reviews and direction papers. Use the Phase 0-4 workflow below.
24
25	When in doubt: if the user wants flowing prose for one section, use express mode; if they want a corpus with claim-to-card traceability, use the full protocol.
26
27	## Workflow Phases
28
29	```
30	Phase 0: Briefs -> _briefs/strand-*.md (one brief per strand)
31	Phase 1: Collection -> research/collection/<strand>/<slug>/{card.md, source.{pdf,md}, meta.json}
32	+ INDEX.md + <strand>.bib per strand
33	Phase 2: Synthesis -> research/synthesis/{<strand>-ontology, gap-analysis, scope-diagram, <domain>-map}.md
34	Phase 3: Direction papers -> direction-papers/<topic>-direction.md
35	Phase 4: Review loop -> revised direction; may reopen Phase 1 with new gaps
36	```
37
38	Each angle is realized as a strand; the brief is the strand's dispatch document. Iteration is expected: loop back from any phase. The directory layout is the persistence layer; treat it as the source of truth between sessions.
39
40	### Phase 0: Define angles and write briefs
41
42	Inputs: prior work, gap statement, epic-dev findings (if any), grant call or thesis question.
43
44	Output: one brief per strand in `_briefs/strand-<name>.md`.
45
46	Each brief defines:
47	- Goal (one sentence)
48	- Scope categories (numbered list, breadth first)
49	- Per-entry deliverable (cards + source + bib + index)
50	- Seed material (existing prior-work documents to import)
51	- Acceptance criteria (count thresholds, breadth thresholds, completeness gates)
52	- Out-of-scope items
53	- Sister skills to use (`opencite:opencite`, `manuscript:manuscript-writing`)
54
55	See [references/brief-template.md](references/brief-template.md) for the full structure.
56
57	If the user names a project domain (neuro tools, clinical trials, ML methods, etc.), generate strands by partitioning the topic on dimensions that cannot be merged later without information loss. Common partitions: methods vs. infrastructure vs. application; tools vs. data vs. theory; modality A vs. modality B.
58
59	### Phase 1: Collection (parallel strand agents)
60
61	For each strand, build a corpus of paper-cards under `research/collection/<strand>/`. Each entry is a folder with `card.md` plus `source.md` plus `meta.json`, and `source.pdf` only when redistributable. Per-strand aggregates are `INDEX.md` and `<strand>.bib`. Use `opencite:opencite` for all paper operations.
62
63	Schema and storage rules: [references/paper-card-schema.md](references/paper-card-schema.md). License-to-redistribution policy and CI rule: [references/license-rules.md](references/license-rules.md).
64
65	When parallelizing strands, dispatch one agent per strand. Use the brief as the agent's full context. Do not let strand agents synthesize across strands; that is Phase 2's job.
66
67	### Phase 2: Synthesis (whole-corpus integration)
68
69	Inputs: full collection across all strands.
70
71	Outp

People who liked this also viewed

6 picks

Type

lit-review

37stars7forks

View on GitHub

How to install lit-review?

neuromechanist/research-skills/lit-review

$npx -y skills add neuromechanist/research-skills --skill lit-review

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Multi-Phase Literature Review Workflow
2
3	Orchestrate a rigorous, citation-grounded literature review across phases: angles to briefs, parallel paper collection, taxonomic synthesis, direction papers, and self-review loops. Every claim in a final document is traceable back to a paper-card.
4
5	## When to Use
6
7	- Building a corpus-grounded review paper or a set of direction documents
8	- Multi-strand reviews where breadth + depth must be coordinated across distinct angles (e.g. tools strand, data strand, science strand)
9	- Reviews where claim-to-evidence traceability matters (grant lit reviews, position papers, white papers)
10	- Iterative reviews where new papers, refined angles, or updated synthesis must roll forward without losing prior work
11
12	## When NOT to Use
13
14	- Original research IMRAD writing. Use `manuscript:manuscript-writing`.
15	- Peer review of a submitted manuscript. Use `manuscript:paper-review`.
16	- Journal formatting. Use `manuscript:manuscript-formatting`.
17
18	## Two modes
19
20	This skill covers two workflows:
21
22	- Express mode (single-pass synthesis): thematic synthesis for an Introduction, Background section, or quick standalone review. See [references/single-pass-synthesis.md](references/single-pass-synthesis.md). Pair with [references/review-frameworks.md](references/review-frameworks.md) for PRISMA, PICO, SPIDER, scoping protocol, and risk-of-bias tools.
23	- Full protocol (multi-phase): citation-traceable corpus reviews and direction papers. Use the Phase 0-4 workflow below.
24
25	When in doubt: if the user wants flowing prose for one section, use express mode; if they want a corpus with claim-to-card traceability, use the full protocol.
26
27	## Workflow Phases
28
29	```
30	Phase 0: Briefs -> _briefs/strand-*.md (one brief per strand)
31	Phase 1: Collection -> research/collection/<strand>/<slug>/{card.md, source.{pdf,md}, meta.json}
32	+ INDEX.md + <strand>.bib per strand
33	Phase 2: Synthesis -> research/synthesis/{<strand>-ontology, gap-analysis, scope-diagram, <domain>-map}.md
34	Phase 3: Direction papers -> direction-papers/<topic>-direction.md
35	Phase 4: Review loop -> revised direction; may reopen Phase 1 with new gaps
36	```
37
38	Each angle is realized as a strand; the brief is the strand's dispatch document. Iteration is expected: loop back from any phase. The directory layout is the persistence layer; treat it as the source of truth between sessions.
39
40	### Phase 0: Define angles and write briefs
41
42	Inputs: prior work, gap statement, epic-dev findings (if any), grant call or thesis question.
43
44	Output: one brief per strand in `_briefs/strand-<name>.md`.
45
46	Each brief defines:
47	- Goal (one sentence)
48	- Scope categories (numbered list, breadth first)
49	- Per-entry deliverable (cards + source + bib + index)
50	- Seed material (existing prior-work documents to import)
51	- Acceptance criteria (count thresholds, breadth thresholds, completeness gates)
52	- Out-of-scope items
53	- Sister skills to use (`opencite:opencite`, `manuscript:manuscript-writing`)
54
55	See [references/brief-template.md](references/brief-template.md) for the full structure.
56
57	If the user names a project domain (neuro tools, clinical trials, ML methods, etc.), generate strands by partitioning the topic on dimensions that cannot be merged later without information loss. Common partitions: methods vs. infrastructure vs. application; tools vs. data vs. theory; modality A vs. modality B.
58
59	### Phase 1: Collection (parallel strand agents)
60
61	For each strand, build a corpus of paper-cards under `research/collection/<strand>/`. Each entry is a folder with `card.md` plus `source.md` plus `meta.json`, and `source.pdf` only when redistributable. Per-strand aggregates are `INDEX.md` and `<strand>.bib`. Use `opencite:opencite` for all paper operations.
62
63	Schema and storage rules: [references/paper-card-schema.md](references/paper-card-schema.md). License-to-redistribution policy and CI rule: [references/license-rules.md](references/license-rules.md).
64
65	When parallelizing strands, dispatch one agent per strand. Use the brief as the agent's full context. Do not let strand agents synthesize across strands; that is Phase 2's job.
66
67	### Phase 2: Synthesis (whole-corpus integration)
68
69	Inputs: full collection across all strands.
70
71	Outp

People who liked this also viewed

6 picks

Type