kalarislabs/research-agent-skills
v1.2.0MIT
283 Agent Skills for researchers: scientific and research paper writing, journal formats, literature review, citations, data science, ML research and domain science.
Changelog
All notable changes to this project are documented here. The format follows Keep a Changelog and the project uses Semantic Versioning.
Fixed vulnerabilities are listed under Security in the release that contains the fix, with the advisory or CVE identifier. Security advisories are also published at https://github.com/KalarisLabs/research-agent-skills/security/advisories.
[Unreleased]
[1.2.0] - 2026-11-16
This release makes the skills do what their descriptions say. Every claim a SKILL.md makes about a script is
now either true in the code or caught by CI, and the library grows to 283 skills.
Fixed
citation-verificationnow detects retracted papers: Crossref update notices (retraction, withdrawal, removal, expression of concern, with Retraction Watch as source) and OpenAlexis_retracted. New statusretracted; an expression of concern reportsuncertain. Dataset and software DOIs resolve through DataCite instead of failing asdoi-not-found.verify_citations.pydegrades per source: an unreachable Crossref, DataCite or OpenAlex givesuncertain, never a falsenot-found. HTTP 429 honoursRetry-After.--helpno longer crashes on the--annotatetext.verify_citations.py --annotatewrites% UNVERIFIEDcomments above flagged entries, as the skill promised.systematic-review-prismarefuses counts that have no logged search (search_log: source, platform, exact query, date, hits, limits; PRISMA 2020 item 7 and PRISMA-S).--allow-unloggedis for legacy counts only.--search-tablewrites the supplement table.- Retrieved abstracts and paper text are treated as untrusted data in ten search and review skills, so an instruction embedded in a paper is quoted, not followed.
Added
- New skill
paper-card: one verified card per paper.check_card.pyconfirms every claim's page, verbatim quote and numbers against the converted text, evaluates derived numbers safely, and builds an independent second-reviewer packet. A claim is accepted only when both checks pass. - New skill
fulltext-acquisition:fulltext_status.pyfinds which included records lack full text and writesmissing.csvandretrieval.md(offline by default;--resolve-oauses Unpaywall);match_pdf.pyidentifies downloaded PDFs by the DOI, PMID or title inside them and attaches only text-verified matches. paper-corpus-ragrebuilt around locate-then-read:paper_convert.py(page markers, quality grade per page, symbol-font repairs logged in a sidecar), heading-bound page-aware chunks, hybrid retrieval (FTS5 BM25 plus optional embeddings fused by reciprocal rank),readandeval(recall@k, MRR) subcommands. Existing indexes needindex --rebuild.unslop-academic-writing:slop_check.py --claimslists what each paragraph claims and whether it carries evidence, and the skill asks for that before any rewriting.tools/claim_audit.py(CI andmake claims): fails when aSKILL.mdnames a script, flag, host, service or status its scripts do not have.tools/check_skill_count.pyfails when prose quotes a stale skill count.tools/validate.pyenforces an eval floor for script-backed original skills (10 prompts, 3 near-misses); six older skills are grandfathered as warnings intools/eval_floor_baseline.txt.- Citation benchmark: retracted entries (Wakefield 1998, Séralini 2012) and a Zenodo dataset; the run gates on
retraction_recall. unpaywall.organdeuropepmc.orginsecurity/allowed-domains.txt.
Changed
- Trigger-routing evals: prompts that quote a skill's own scripts or errors are marked
follow_up: trueand skipped by the BM25 router. The reviewed suite doubled to 106 prompts, so the PR-gate numbers are harder (hit@1 0.90, hit@3 0.99, false-trigger 0.08, was 1.00/1.00/0.12 on 53 prompts). - Benchmark README tables, charts and skill-count claims regenerated for 283 skills.
Changed (earlier in this cycle)
- README repositioned around turning any agent into a research co-scientist: a research-stage map of skills and a "Works in any harness" section covering skills.sh, the plugin marketplace and manual installs.
- Distribution is skills.sh, the Claude Code plugin marketplace, GitHub CLI and the checksum-verified
install.sh/install.ps1installers. Theresearch-agent-skillsCLI is not published to npm; README, docs, generated skill pages and metadata no longer point to npm.
Added
- Eval suites for all 283 skills (
evals/<skill>/evals.json): realistic prompts plus near misses naming the better skill. Suites for adapted skills were generated from eachSKILL.mdand are markedpending review. - Import-time enrichment of adapted skills (
tools/enrich.py): oversized skills split intoreferences/, dead links repaired, category-specific agent operating procedures (environment check, small first run, validation, failure-recovery table, integrity rules) and computed related-skill handoffs. - Trigger-rich description overrides for 84 adapted skills (
third_party/description-overrides.yaml, generated bytools/generate_skill_data.pyand validated). - Offline smoke tests for every skill script: all 497 compile; 327 standard-library CLIs run
--helpon every CI OS (tests/test_skill_scripts_smoke.py). tools/trigger_bench.py --sample N --seed Sfor reproducible subsamples with the paid Claude router.- Search tags for all 283 skills. Tags for adapted skills live in
third_party/tag-overrides.yamland are applied at import;tools/validate.pywarns when a skill has none. llms-full.txt: every skill with its full description, tags and install command.- Generated skill pages now carry tags, example requests from the eval suites, related skills, field-guide links, every install route and a sentence-complete meta description.
- Marketplace plugins declare
version,author,homepage,repository,license,categoryandkeywords(the most common tags of their skills). .zenodo.jsonandcodemeta.jsonfor DOI minting and research-software indexing.- 1280×640 GitHub social preview image (
PUBLIC/social-preview.png) and a 59 KB WebP README banner.
Changed
- Marketing residue (GitHub star counts, user numbers) is stripped from imported skills.
- The 500-line
SKILL.mdbudget is now enforced for every skill (the size baseline is empty). - Adapted-skill quality rose from a mean of 80.9 to 95.2. Claude-router trigger accuracy on a 100-prompt sample of all evals is hit@3 0.96 with no false triggers.
Fixed
openpiv/run_example.pyexplains a missing dependency instead of raising a traceback.- The release workflow's npm job no longer skips when the optional vendor security gate is skipped.
- The npm installer is no longer described as unreleased.
plugin.json, the npm package,CITATION.cffandSUPPORT.mdpoint at one documentation URL.
Removed
- Unused MkDocs configuration (
mkdocs.yml,docs/overrides/) and thedocsdependency group. The site is built by Mintlify, which never loaded the MkDocs Open Graph and JSON-LD templates. - MkDocs-only
???admonitions in the FAQ, now plain headings that Mintlify renders.
[1.1.0] - 2026-10-01
Added
unslop-academic-writing: removes AI slop from research prose (stock vocabulary, empty emphasis, hedge stacks, formulaic signposting, monotone rhythm) with a zero-dependency linter for Markdown, LaTeX, text and Word files.- Skill verification tooling: static quality rubric (
tools/skill_quality.py), trigger-routing benchmark (tools/trigger_bench.py, BM25 and Claude routers), with-vs-without-skill task benchmark with a blind judge (benchmarks/task_evals), labeled citation-verification benchmark and a human-vs-model slop benchmark. benchmarks.ymlworkflow: quality and routing gates on every PR, weekly citation benchmark, manual paid benchmarks.- Documentation site restructure: getting started, guides (papers, theses, no-slop writing, systematic reviews, skills by field), reference (CLI, architecture, benchmarks, security, contributing), FAQ, JSON-LD metadata.
- Generated
llms.txtfor AI search engines and agents. .editorconfig,.pre-commit-config.yaml,Makefile,SUPPORT.md,GOVERNANCE.md.
Changed
- Repository moved to
KalarisLabs/research-agent-skills; code owner @saynchowdhury. - Journal-format and other original skills gained numbered workflows and explicit integrity rules.
- Sharper descriptions for
cover-letter-to-editorandrebuttal-and-response-to-reviewersto prevent mis-triggering.
[1.0.0] - 2026-10-01
Added
- 278 agent skills across 19 categories: research writing, journal formats, literature review, ideation and design, data science, visualization, knowledge graphs and RAG, scientific databases, life sciences, chemistry, clinical research, physical sciences, lab automation, research automation and ML research engineering.
- 21 original skills, including journal formats (Nature Portfolio, Science, Cell Press, IEEE, ACM, Elsevier, Springer LNCS, PLOS, APA 7, arXiv), citation verification, BibTeX hygiene, systematic reviews (PRISMA 2020), reference-manager interop, paper-corpus RAG, research knowledge graphs, abstracts and titles, reviewer responses, cover letters, reproducibility statements and a research skill creator.
research-agent-skillsCLI: one-command install for Claude Code, Codex, Cursor, Gemini CLI, Copilot, OpenCode, Windsurf and.agents/skillsharnesses, with checksum verification, integrity checks (doctor), update and uninstall.- Standalone
install.sh/install.ps1installers with SHA-256 verification. - Security CI: spec validation, prompt-injection lint, Cisco AI Defense skill-scanner, CodeQL, Semgrep, Bandit, TruffleHog, OSV/pip-audit/npm audit, zizmor, actionlint, OpenSSF Scorecard, signed releases with build provenance.
Fixed
- Windows console crashes (cp1252) in skill scripts that print non-ASCII text.
- experimental-design: fractional allocation ratios no longer silently drop an arm.
- analytical-method-validation: ragged CSV rows exit cleanly with code 2; JSON and CSV inputs are normalized identically.
- arbor:
set-evidencevalidates status; node lists sort n1..n10 numerically. - deeptools: BAM index detection no longer breaks when a parent directory contains
.bam. - Doubled
uv uv pipinstall commands.