Learning & Documentation Agent Skills for Codex CLI

Use when drafting or revising EuroSys prose — building the problem-to-mechanism arc systems reviewers expect, budgeting the 12 technical…

Capture solved problems as categorized documentation with YAML frontmatter for fast lookup

Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus…

Transforms verified literature, experimental data, and research notes into rigorous, traceable academic arguments while preventing…

Use when research must support an action or claim.

Evidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TODO plan (which stage/skill to…

Use when assembling and handling the non-visual evidence for an Art Bulletin article — objects, archives, primary documents, provenance…

Create a minimal working Exa search example with real results.

Use when the user wants exam-focused drilling from the course's analyzed material.

Use when demonstrating plugin workflow features - shows how skills can guide multi-step processes

Create C-suite and VP level resumes emphasizing strategic leadership

Explain code, concepts, or technical decisions in clear, understandable terms

Output format templates for all 5 explanation modes — quick (compact), deep (full analysis with diagrams), onboarding (project guide)…

Automatically explain every completed implementation from repository and verification evidence; also use whenever someone requests a…

Use when explaining code, technical concepts, or implementation decisions.

Build a complete explicit instruction sequence from teacher modelling through guided practice to independent work.

Use when organizing the exposition and structure of a pure-mathematics manuscript for Annals of Mathematics — sectioning, notation…

Use when responding to external-review / R&R comments for 《中国工业经济》 (China Industrial Economics).

Extract technical PDFs into source-backed Markdown or compact review guides when parser choice, table or reading-order loss…

Extract project-specific coding rules and domain knowledge from existing codebase, generating markdown documentation for AI agents.

Use when reasoning about how an ACM FAccT submission is evaluated — mutually-anonymous review by a mixed CS+law+social-science pool…