Research
Research, evidence gathering, literature, reports, investigation, and synthesis
Browse research skills
Showing 12,721–12,744 of 21,381 skills
[Research] Use when a workflow step or the user asks for a research synthesis: findings into a structured report.
[Fix & Debug] Use when a workflow step or the user asks for how an existing feature works (read-only code-flow trace) or --mode=debug: a bug''s root cause (reproduce, trace end-to-start). --mode=explain. Plans or decisions: understand.
[Documentation] Use when a workflow step or the user asks for a demo guide, demo script or sprint-demo walkthrough: user stories, case identities, evidence carriers.
[Workflow] Use when seeding test data or implementing idempotent QC happy-path seeders.
[Workflow] Use when researching a topic from web sources then synthesizing. Flag: --output={synthesis|business-eval|marketing|course}.
[Workflow] Use when creating or updating the configured canonical feature/spec artifact with its native paths, sections, identifiers and test-evidence carriers; portable 8-section/README/TC form only when no native profile applies.
[Workflow] Use when auditing the whole project''s architecture or production readiness: read-only, one consolidated health report.
[Research] Use when a workflow step or the user asks for a market landscape analysis: competitors, TAM/SAM/SOM, trends, SWOT, segments.
[Research] Use when a workflow step or the user asks for a research synthesis: findings into a structured report.
Implement one tracked IronCrew `IC-NNN` finding end to end across Rust code, tests, documentation, Lua examples, evaluations, and deployment evidence. Use when the user says to proceed with, fix, resolve, continue, or take the next tracked IronCrew issue or development goal. Do not use for an unrelated untracked change unless the user asks to add it to the ledger.
Universal document converter for transforming Markdown to PDF, DOCX, HTML, LaTeX, and 40+ other formats. Covers templates, filters, citations with BibTeX/CSL, and batch conversion automation scripts.
Systematic multi-source research of an engineering domain. Spawns parent issue → 6 research subissues (Standards, Academic, Industry, LinkedIn-marketing, Code-audit, Synthesis) → gap implementation subissues. Replaces LinkedIn-only extraction with defensible comprehensive sourcing.
"Main orchestrator as lightweight router \u2014 stay responsive to user\
Assess a multi-machine, multi-repo AI-enabled workspace for readiness, provider allocation, and issue prioritization.
Doc-type-aware extraction contract for llm-wiki source ingestion with measurable coverage and source-anchored traceability. Use when (1) ingesting a PDF, DOCX, XLSX, PPTX, HTML, or scanned-image source into a wiki `sources/` page, (2) computing the pre-extraction estimate (what fraction of the source we expect to recover) and post-extraction yield (what fraction we actually recovered), (3) anchoring wiki claims back to specific page / paragraph / cell / slide positions in the source so a revi...
Route wiki content using current source rights, ownership and destination authority. Apply project-name abstraction only after checking whether publication is permitted; private visibility and anonymization do not grant rights.
Enforce the page-shape contract when a repo-side document or analysis output gets converted into an llm-wiki page. Use when (1) running `scripts/knowledge/llm_wiki.py ingest`, (2) writing or rewriting a wiki page from docs/reports/*, docs/handoffs/*, scripts/review/results/*, or calc citation outputs, (3) deciding whether a page should be split into a folder of sub-pages, (4) reviewing wiki PRs for length / diagram / divide-and-conquer compliance. Codifies the Karpathy + Astro-Han + lewislulu...
Triage and rank GitHub issues across a workspace-hub style multi-repo ecosystem using machine-readiness, provider-utilization, and leverage scoring.
Class-level digitalmodel OrcaWave/OrcaFlex readiness, semantic-proof, fixture-proof, and closeout workflows.
Reapply the Hermes Kanban dashboard readability customizations (clickable bare URLs in card descriptions + readable card-text font, a visible horizontal scrollbar so all columns are reachable) as a user-override plugin that survives hermes-agent updates. Use when the Kanban board reverts to the Mondwest display font / plain-text Source URLs after a hermes update, or when bootstrapping a machine whose ~/.hermes was wiped.
Plan and operate a Hermes-led control plane that routes AI provider work across workstations using quota urgency, machine readiness, GitHub issue gates, and a dispatch ledger.
Verify proposed copy changes to vamseeachanta/aceengineer-website against canonical sources in workspace-hub (llm-wiki, live site, strategy repo) before shipping. Produces a GitHub issue on the site repo documenting the check with a Match / Drift / Gap verdict.
Operate ace-linux-1 as the continuous AI-agent control surface for overnight and continuous batches that keep GTM material moving toward client outreach.
Competitive intelligence with positioning analysis, battlecards, and