Research

Research, evidence gathering, literature, reports, investigation, and synthesis

skills in category: 30,315
pages available: 1,264

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse research skills

Showing 11,065–11,088 of 30,315 skills

Duck CutAShrink a backlog the honest way — obsolete work out, duplicates merged, viable items unblocked. Use when the user asks to cut or clean a backlog, critique open or blocked backlog items, autonomously close, cut, merge, or unblock every item that does not need the owner, or when open, blocked, and deferred work keeps accumulating.researchgoVotes: 0GitHub stars: 5
Bug ReportATriage a user-pasted bug report (from Discord, Slack, GitHub, etc.) about the Gradient Bang game. READ-ONLY — investigates the codebase and produces TWO things in one response: (1) a compact **bug summary** (verdict, why, fix, evidence with file:line citations) the user can keep for their records or paste into Notion, and (2) a separate **Discord reply** of only 1–2 friendly sentences at the very bottom that the user can paste straight back to the reporter in the Discord channel. This skill N...researchgoreactVotes: 0GitHub stars: 419
Analyze ContextAAnalyzes a gameplay session context dump from Gradient Bang. Summarizes agent activity and, if the user reports a problem, identifies where it occurred and scans source code for the root cause.researchgodebuggingVotes: 0GitHub stars: 419
Search TavilyAOwns live-web retrieval through Tavily CLI (`tvly`), search, extract, map, crawl, research, on the cheapest verb that answers: relevance resolved server-side, not post-filtered locally, and bulk page content routed to disk, never the context window. Beats blind single-URL fetching, which ranks and scopes nothing. Any current-web question routes here.researchjavascriptgoVotes: 0GitHub stars: 2
Emacs FreezeADiagnose a frozen, hung, beachballing, or unresponsive Emacs by sampling the process, reading server buffers when possible, and recommending recovery. Use when Emacs is stuck or not responding; do not use for ordinary Elisp errors while Emacs is responsive.researchpythongoVotes: 0GitHub stars: 12
Document Elisp ExtrasAAudit, create, or refresh documentation for all Emacs extras packages in the dotfiles repo. Use when the user asks to document every extras package, fill missing extras docs, refresh outdated extras docs, check extras documentation coverage, or bring emacs/extras/doc up to date with emacs/extras sources.researchdocumentationVotes: 0GitHub stars: 12
ProofreadAProofread specified Markdown prose for spelling, grammar, punctuation and light clarity changes. Supports local aspell or explicitly scoped Gemini editing, preserving source files and reviewed suggestions; not factual review, broad rewriting or permission to upload restricted content.researchrustgoVotes: 0GitHub stars: 12
HumanizeARewrite English prose to remove formulaic AI-style wording while preserving meaning, voice, quotations, citations and markup. Use for /humanize, de-slop, removing AI tells, "sounds like ChatGPT/Claude/Gemini", or final cleanup of AI-assisted prose. For writing under Pablo's name, use personalize, which incorporates this catalogue.researchgoVotes: 0GitHub stars: 12
Add Bib EntryAUse when adding works to Pablo's bibliography, creating BibTeX/BibLaTeX entries, adding DOI/ISBN/URL references, resolving missing citekeys, replicating zotra-extras-add-entry followed by ebib-extras-process-entry, or preparing notes that cite works not yet in the configured bibliography files.researchpythonrustVotes: 0GitHub stars: 12
Find SkillsADiscover, vet, and optionally install agent skills when the user asks "find a skill for X", "is there a skill that can...", "how do I add support for X", or otherwise wants reusable/installable agent capabilities. Do not use for ordinary task execution unless the user is explicitly exploring skills, tools, or capability extensions.researchrustgoVotes: 0GitHub stars: 12
Memory MaintenanceAUse when curating the persistent file-based memory (…/memory/MEMORY.md + per-fact *.md) — structuring/grouping the index, removing cruft or duplication, fixing stale index hooks, trimming a bloated index line, or ensuring open action-items in memory are also tracked in 00_07. The HOW lives in .claude/prompts/memory_housekeeping.md; the memory FORMAT standard lives in the system prompt (don't restate). The 17 curation traps — scout counts run low, a half-home may be a duplicate, machine dedup ...researchrustgoVotes: 0GitHub stars: 23
In SilicoAUse when working on the silken_net in-silico surface — the EBFC Gen 2.0 Zero-Lab DFT+MD pipeline (tools/in_silico/, silken_md conda env): L1 AlphaFold-3 protein architecture, L2 OpenMM MD, L3 PySCF quantum chemistry (ΔSCF redox cascade, Hammett mediator series, ZIF-cathode DET, cluster-continuum solvation), L4 kinetics/EIS, the Стаття 1 computes, and the anchor-mechanics series (Lamé press-fit and thermal stress, pogo Z-stack tolerance, EDLC aging + Kirkendall, bus mechanics and contact, per-...researchpythongoVotes: 0GitHub stars: 23
Workflow Platform Differential DiscoveryAUse when 尚未选定用例，需要从 CPython/CinderX 平台差异中筛选优化候选。researchpythonperformanceVotes: 0GitHub stars: 2
Workflow Platform Differential Discovery DeepdiveAUse when 深钻已选定的单个用例，贯通性能、JIT、ISA/微架构证据并验证优化价值。researchperformanceVotes: 0GitHub stars: 2
Using Cpython OptimizeAUse when CPython/CinderX 任务需要跨环境、跑分、crash 或 JIT 分析选择工作流；单项操作直接用对应技能。researchpythonperformanceVotes: 0GitHub stars: 2
Cinderx Evidence TableAUse when 建立或审查单用例 E1–E9 根因证据表，判定穿刺与优化价值是否可信。researchnodeVotes: 0GitHub stars: 2
Update ResearchACheck upstream tool documentation for drift in the version-stamped surfaces: docs/cross-tool-strategy.md, docs/native-sandbox.md, docs/open-weight-models.md, and the workflow doc's stamped sections. Fetches source URLs, compares claims against current doc, and reports drift. Use when updating the cross-tool strategy guide or checking for tool changes.researchgojavaVotes: 0GitHub stars: 15
Review HarnessAPeriodic multi-angle improvement review of the reference. Always fans out all five read-only research agents in parallel — maintainer tooling, documentation, runtime cost, source duplication, consumer surface — so cross-angle tension informs the synthesis. Every agent carries the challenge charter: question the design against the README's stated philosophy, recommend removals that pay for themselves. Judges findings by the resilience-first doctrine; a settled ADR decision is rebuttable with a...researchgogitVotes: 0GitHub stars: 15
Dr DiagnoseALocate the cause of a DeepReason defect from the typed record, not from code reading. Produces DIAGNOSIS.md naming one primary cause with evidence pointers. Use only after GOAL.md exists.researchpythongoVotes: 0GitHub stars: 142
Dr Deliver ChangeAClose a validated change tranche — final commit and push, requirement-by-requirement reconciliation against the operator's verbatim words, and the delivery report (DELIVERY.md). Use only after VALIDATION.md says PASS.researchgogitVotes: 0GitHub stars: 142
Dr Change OrchestratorAEntry point for implementing an operator-suggested change to DeepReason. Routes through capture, spec, plan, stepwise execution, validation, and delivery — one phase at a time, with a verbatim request ledger nothing may drift from. Use when the operator says "add", "change", "make it", "I want", or suggests any modification.researchgoVotes: 0GitHub stars: 142
Dr Audit OrchestratorARouter for the code-audit family. Runs five read-only audit dimensions (broken, dead, docs-drift, spec-drift, goal-trace) over the repo and produces AUDIT_REPORT.md plus ready-to-send fix prompts. Use when the operator asks for an audit, a sweep, or "what is broken / unused / out of date". Findings only — fixes happen in later tranches.researchrustgoVotes: 0GitHub stars: 142
Dr Ask The Right QuestionAQuestion discipline for working DeepReason - route every question to the cheapest authority (record, then framework, then operator), translate the operator's shorthand into typed obligations, and frame uncertainty as falsifiable forks. Load whenever an operator message is ambiguous or short, whenever any workflow phase says "stop and ask", whenever evidence contradicts your expectation, and at the start of any session run by a model that has not worked this repo before.researchrustgoVotes: 0GitHub stars: 142
Deepreason OrchestratorAEntry point for any DeepReason problem. Routes work to exactly one subskill at a time and enforces the scope contract. Use when asked to manage, diagnose, or fix anything in DeepReason.researchgogitVotes: 0GitHub stars: 142