From literate-agent
Run the 6-point dual-audience checklist on a literate .org section. Each item maps to a research-backed LP rule (heading-as-concept, :CUSTOM_ID: for ≥2 refs, WHY in prose, one mechanism per section, structural-not-typographic affordances, cold-start agent recoverability). Use after editing or writing an .org section, or as a manual review pass.
How this skill is triggered — by the user, by Claude, or both
Slash command
/literate-agent:lp-dual-audience-checkWhen to use
user says "check this section", "review the LP section", "run the dual-audience checklist", "did I miss anything in this section"; or proactively after editing a literate .org section's prose preamble or first src block.
**/*.orgThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Points at the canonical checklist:
Points at the canonical checklist:
~/projects/literate-agent/hints/dual-audience-checklist.org
Runs the 6-point dual-audience review on a single literate .org
section the user just edited (or one they point at). Each item is
yes/no; the skill outputs a compact report grouped by which rule
each fail maps to.
^(Functions|Helpers|Utilities|Misc|Things|Stuff)$?[[*<heading>]] or [[#<expected-anchor>]]
references; count; if ≥2 and no :CUSTOM_ID: drawer, flag.#+begin_src;
check for non-empty prose (≥ 1 sentence) that names a why
(trade-off, constraint, rejected alternative).:PROPERTIES: / :CUSTOM_ID:?## Dual-audience check: <file>::<heading>
Pass: 4/6
✗ Item 2: missing :CUSTOM_ID:
Section is referenced from 3 locations:
- other.org:42 ([[*Heading Name][label]])
- here.org:108 ([[*Heading Name]])
- README.org:15 ([[#expected-anchor]])
→ Add :CUSTOM_ID: per rules/lp-stable-anchors-for-multi-referenced-sections.md
✗ Item 5: load-bearing affordance is typographic-only
Line 47: "*public API* — call this from external code"
→ Add :PROPERTIES: :PUBLIC: yes :END: drawer, or :CUSTOM_ID: public-api
→ See rules/lp-load-bearing-affordances-structural.md
~/projects/literate-agent/hints/dual-audience-checklist.org — the
canonical checklist with detailed rationale per item.~/projects/literate-agent/docs/transfer-gradient.org — the research
figure each item derives from.~/projects/literate-agent/skills/audit-prose/ — sibling skill that
focuses on prose deletion-test only; this skill is structurally
broader.npx claudepluginhub jingtaozf/literate-org --plugin literate-agentProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.