6-osp-review
OSP Phase 6: Synthesize verified findings into a single venue-formatted review
Install / Use
npx skills add amirkiarafiei/open-scholar-peer --skill 6-osp-reviewInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Our assessment of 6-osp-review
6-osp-review scores 69/100 on our quality scale, 3909th of 4,720 Development & Engineering skills we index.
Its SKILL.md is 4.0 KB long, well organised into 8 sections and no code examples: a solid amount of guidance for an agent.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- The repository was last updated 12 days ago, so 6-osp-review is actively maintained.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 80/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
6-osp-review compared with similar skills
All 4 of these similar skills score higher than 6-osp-review; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| 6-osp-review (this skill)by amirkiarafiei | 69 | 0 | 12d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 117.8k | 9d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.3k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.4k | 3d ago | CLAUDE.md |
| lobehubby lobehub | 100 | 85.7k | today | MCP Server |
Frequently asked questions
- How do I install 6-osp-review?
- Run
npx skills add amirkiarafiei/open-scholar-peer --skill 6-osp-review. The install tabs above show the steps for each supported agent. - Which AI agents does 6-osp-review work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is 6-osp-review safe to use?
- It declares no license and scores 80/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is 6-osp-review still maintained?
- The repository was last updated 12 days ago, so 6-osp-review is actively maintained.
Skill content
View source on GitHubname: 6-osp-review description: "OSP Phase 6: Synthesize verified findings into a single venue-formatted review"
/6-osp-review — Final Review Generation
Synthesizes the structured summary, retrieved literature, domain narrative, missing baselines, and verified Q&A pairs into a single consolidated review formatted to the venue's guidelines.
Activation
Invoke the osp-reviewer-agent skill.
Inputs — none of these is a gate
This is the phase most exposed to a skip, and the one that must never refuse: a review the user can read beats no review at all. Take whatever artifacts exist.
summary,literature,historian,baseline_scout,qa— any of them may be absent orskipped.05_qa_<slug>.md, one per criterion, holding however many pairsqa_pairs_per_criterionasked for. Some criteria may have none.
Every gap goes in ## What this review did not have (see the reviewer skill), and the Confidence
section must reflect it. A thin review that says it is thin is honest work. A thin review that reads like
a complete one is the failure this section exists to prevent.
Record any skip before you start. The orchestrator is not in the loop when the user runs this
command directly, so it falls to you: for every earlier phase still pending, set
phases.<name>.status = "skipped" and phases.<name>.skip_reason to their reason, or
"user ran /6-osp-review first". A phase left pending reads as "not reached yet", and the final review
cannot tell the difference.
Opening block (print before step 1)
Render the opening block exactly as .kiro/defaults/phase_block_template.md defines it — that
file holds the rail, the rules and the widths, and it is the only place they are written down.
This is phase 7 of 7 (review); read the rail's state from session.json. Values:
DOING synthesise everything into one review
READS every .brain/raw/ artifact that exists
WRITES .brain/review/final_review.md
COST ~2 min, no external calls
Steps
- Read all artifacts listed in the frontmatter.
- Activate the
osp-reviewer-agentskill. - The skill follows the structure dictated by
00_review_guidelines.md. If using the generic fallback, the structure is: Summary / Strengths / Weaknesses / Detailed comments per criterion / Questions for authors / What this review did not have / Decision recommendation / Confidence. That gap section is appended whatever the venue format — see the skill. - The skill performs no new retrieval — it is decoupled from investigation, synthesis only.
- Write
.brain/review/final_review.md. - Update
session.json:phases.review.status = "completed"phases.review.completed_at = <now>phases.review.notes = "Final review written; decision: <recommendation>"resume_from = "completed"
Closing block (print when the phase ends)
Render the closing block from .kiro/defaults/phase_block_template.md. Build the rail from
session.json — ● only where status == "completed", ○ for pending and skipped. A
phase the user skipped must not show as done.
Drop BLOCKED and NOTE when there is nothing to put on them. Values:
DONE decision: <from the reviewer's scale>
.brain/review/final_review.md
NOTE <what the review did not have, or omit this line>
YOURS a draft. Cut what you disagree with, check the
citations. Your name is on it, not ours.
NEXT re-run any phase, then /6-osp-review again
Re-run behavior
Re-running overwrites final_review.md. Useful when the user wants to regenerate the review after revising an earlier phase (e.g., re-running /5-osp-qa for a single criterion). Warn before overwriting.
Pitfalls
- Do not introduce new findings. Every claim in the review must trace to a prior artifact.
- Do not invent citations. Every cited paper must be in
02_retrieved_literature.md. - Match the venue's tone and structure exactly. ICLR ≠ NeurIPS ≠ workshop.
Related Skills
taste-skill
117.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.3kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.4kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
lobehub
85.7k🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
