Chalk Labs
Need help deploying literature?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code. Read the repository before you give any tool access to your data.
npx agentmarket install skill/congruentsys-literature
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/literature
Tools it pre-approves 5
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
WebSearch,WebFetch,Write,Read,Glob
What's inside
- Skill name
literature- Description
- LLM-assisted literature review for HDD (Phase 0)
- License
- MIT
- Allowed tools
- WebSearch,, WebFetch,, Write,, Read,, Glob
- Instructions
- 112 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Literature Review
Conduct an LLM-assisted literature review as part of HDD Phase 0: Discovery.
## Overview
Literature reviews discover existing frameworks, prior work, and standards that
inform hypothesis formulation. HDD uses LLM assistance to rapidly survey a field.
## Steps
### 1. Identify the Topic
If starting from an idea:
```bash
cat research/ideas/IDEA-R-XXX.md
```
### 2. Search for Prior Work
Use web search to find relevant papers, standards, and frameworks:
- Academic papers (Google Scholar, arXiv)
- Industry standards (ISO, IEEE, RFCs)
- Existing frameworks
- Benchmarks and evaluation methods
- Similar projects or implementations
### 3. Create Literature File
Create `research/literature/LIT-{N}.md`:
```markdown
---
id: LIT-{N}
type: literature
topic: "$TOPIC"
status: active
created: YYYY-MM-DD
source-idea: IDEA-R-XXX
---
# LIT-{N}: Literature Review - $TOPIC
## Research Question
[The question being explored]
## Key Findings
### 1. [Framework/Standard/Paper Name]
**Source:** [URL or citation]
**Relevance:** [Why this matters]
**Key Concepts:**
- [Concept 1]
- [Concept 2]
### 2. [Next Framework]
...
## Prior Art Summary
| Prior Work | Contribution | Gap / What We Add |
|------------|--------------|-------------------|
| [Name] | [What they did] | [What's missing] |
## Implications for Hypothesis
Based on this review:
1. **Potential Hypothesis 1:** [Testable claim]
2. **Potential Hypothesis 2:** [Another possibility]
## References
1. [Full citation 1]
2. [Full citation 2]
## Next Steps
- [ ] Formalize hypothesis: `/hypothesis "claim"` (add `--paper <n>` only if a paper exists)
```
### 4. LLM-Assisted Research
Good prompts:
- "What are the standard frameworks for measuring [X]?"
- "How do researchers typically evaluate [Y]?"
- "What prior work exists on [Z]?"
- "What are the gaps in current approaches to [W]?"
**Document findings** as you go.
### 5. Synthesize
After researching:
1. Update the LIT file with findings
2. Link back to source idea
3. Propose potential hypotheses
4. Suggest which paper this might contribute to
## Output
Complete literature file with:
- Key findings summarized
- Prior art table filled
- At least one potential hypothesis proposed
- Clear next stepsFrom Congruentsys/yurtle-kanban, MIT.
More from Congruentsys/yurtle-kanban
- 0.587score
yk-next
Congruentsys
ONE pass — what should THIS session do next in yurtle-kanban?
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
steer
Congruentsys
The outer loop above /yk-loop.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
yk-loop
Congruentsys
The yurtle-kanban work loop.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
release-foss
Congruentsys
Release a public (FOSS) repo — version bump, CHANGELOG, reviewed release PR, tag after merge, a public GitHub release with notes cut to fit, the registry…
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
pairit
Congruentsys
XP pair work for ONE yurtle-kanban issue.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
external-pr
Congruentsys
Carry ONE external PR (author not OWNER/MEMBER/COLLABORATOR) through the Captain's
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
experiment
Congruentsys
Create an experiment protocol for HDD - tests enhancement on branch
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
blocked
Congruentsys
Mark expedition as blocked with reason and optional unblock agent
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
done
Congruentsys
Complete current expedition - run tests, commit, push, and update kanban status
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
work
Congruentsys
Find and start the next highest-priority expedition from the kanban board
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
review
Congruentsys
Pre-merge review - verify tests, docs, and merge readiness for an expedition
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
release
Congruentsys
Release an internal repo — version bump, CHANGELOG section, reviewed release PR, annotated tag after merge
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 2
- Last commit (this folder)
- Aug 28, 2026 (2 months ago)
- Last release
- Oct 3, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Congruentsys/yurtle-kanban
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Congruentsys
- 0.587score
yk-next
Congruentsys
ONE pass — what should THIS session do next in yurtle-kanban?
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
yk-loop
Congruentsys
The yurtle-kanban work loop.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
steer
Congruentsys
The outer loop above /yk-loop.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
release-foss
Congruentsys
Release a public (FOSS) repo — version bump, CHANGELOG, reviewed release PR, tag after merge, a public GitHub release with notes cut to fit, the registry…
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
pairit
Congruentsys
XP pair work for ONE yurtle-kanban issue.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
external-pr
Congruentsys
Carry ONE external PR (author not OWNER/MEMBER/COLLABORATOR) through the Captain's
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get literature running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
literature skill. Agent Mart. https://agentmart.dev/skills/congruentsys-literature (last updated 2026-10-24)