amirkiarafiei/open-scholar-peer/2-osp-literature
Claude Code and agent skill by amirkiarafiei/open-scholar-peer
- community
Checking that the SKILL.md file is still in the repository.
OSP Phase 2: External retrieval — one round per invocation (sub-domain, method, temporal)
Install
npx vskill@latest install amirkiarafiei/open-scholar-peer/2-osp-literatureSKILL.md
/2-osp-literature — Literature Review & Expansion
Runs ONE round of external retrieval per invocation. Three rounds are recommended; the user decides how many to run. After each round it reports what it found and offers both routes: another round, or move on.
Activation
Invoke the osp-literature-review-agent skill.
Inputs — none of these is a gate
phases.summary.status == "completed"and01_structured_summary.mdexists. Without it, read
.brain/input/paper.md and derive the query terms yourself; say in Provenance that you did.
- Rounds run in order (1 → 2 → 3) because each strategy builds on the last. **How many you run is the
user's choice** — one round is a valid, thinner corpus, not an error.
Resource notice
⚠️ Each invocation makes ~8-12 API calls across whichever databases this project installed, plus native web search. Expect 1-3 minutes per round.
Round definitions
| # | Anchor | Goal | |
|---|---|---|---|
| 1 | sub-domain-anchor | Search using the paper's stated sub-domain and primary keywords | |
| 2 | method-anchor | Search using the method's name and key technical terms | |
| 3 | temporal-expansion | Filter to last 12 months; include arXiv pre-prints, concurrent submissions |
Opening block (print before the round starts)
Render the opening block exactly as .hermes/defaults/phase_block_template.md defines it — that file holds the rail, the rules and the widths, and is the only place they are written down. This is phase 3 of 7 (literature); the rail carries ◐ while rounds remain. Values:
DOING <the anchor for this round, in one line> READS .brain/raw/01_structured_summary.md WRITES .brain/raw/02<a|b|c>_literature_round<N>.md COST ~1-3 min, ~8-12 searches
Steps
- Read
.brain/session.json.
- Determine
next_round = phases.literature.rounds_completed + 1(default 0 → next = 1). - If
next_round > 3, all three recommended rounds are done: consolidate if that has not happened
yet, and point at /3-osp-historian.
- If any earlier round file is missing, resume from that round instead.
- Read
.brain/raw/01_structured_summary.md.
- Run the next pending round only:
- Activate the
osp-literature-review-agentskill for that round. - The skill lists the retrieval tools this project installed, picks the ones that suit the paper's
field (its ## Sources section is the rule), and dispatches them together with different query formulations.
- Write the round file (
02a,02b, or02c) using the template at.hermes/defaults/round_strategy_template.md.
- Update
session.json:
- Increment
phases.literature.rounds_completed. - Set
phases.literature.status = "in_progress". - Then offer the choice, and act on the answer. Another round, or move on. Whenever the user
moves on — after 1, 2 or 3 rounds — set phases.literature.status = "completed", phases.literature.notes = "<N> of 3 rounds; <M> unique papers retained", resume_from = "historian", and write the consolidated 02_retrieved_literature.md (deduplicated table of everything retained so far). Stopping at 1 or 2 rounds is a completed phase with a smaller corpus, not an incomplete one.
- If they stopped early, set
phases.literature.skip_reasonto their reason, or
"user moved on after round <N>" if they gave none.
- Print the closing block from
.hermes/defaults/phase_block_template.md, labelled
LITERATURE round N of 3. Values:
DONE <n> retained, <m> excluded · <anchor-name> top finds: <2-3 short phrases> .brain/raw/02<a|b|c>_literature_round<N>.md BLOCKED <source> — <reason>, nothing was searched NEXT /2-osp-literature round N+1 (recommended) /3-osp-historian move on with <N> rounds
One BLOCKED line per provider that failed — an error is not an empty result; drop the label when nothing failed. After round 3 the literature marker becomes ● and the label reads LITERATURE 3 rounds; after a deliberate stop it stays ◐ and reads LITERATURE <N> rounds. Under NEXT, say once what stopping here would cost: after round 1 the method-anchor search has not run, so work using the same technique may be missing; after round 2 the temporal expansion has not run, so concurrent work from the last 12 months may be missing. Do not repeat it on the next invocation. Once round 3 is done, NEXT carries /3-osp-historian alone.
Re-run behavior
Each invocation runs the next round that has not run — step 1 computes it from rounds_completed. Calling it again after round 2 gives you round 3, and never overwrites a round you already have. To redo a particular round, delete its file (02a, 02b or 02c) first; step 1 then resumes from there. Warn once before overwriting its file, then proceed.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingextensions/.hermes/skills/2-osp-literature/SKILL.md
Popularity
- Repository stars
- 48
- Repository forks
- 7
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/amirkiarafiei/open-scholar-peer/2-osp-literature)