From literate-agent
Python-specific literate-programming traps — tangle path resolution, ruff formatter file-local-var, noweb refs for big classes, byte-equivalence gate, bare-* parser trap. Auto-activates when editing .py files or literate .org files with Python src blocks. Consult before renaming .org files (tangle paths break), before adding new tangle targets, or after editing a literate-python .org.
How this skill is triggered — by the user, by Claude, or both
Slash command
/literate-agent:lp-hint-pythonWhen to use
editing .py files; editing .org files containing
**/*.pyThis 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 Python LP hint file:
Points at the canonical Python LP hint file:
~/projects/literate-agent/hints/python.org
.py directly — it's a generated
artefact. Edit the owning .org section. The PreToolUse hook
block-tangled-edit.sh enforces this and points at the owning
.org via .cache/tangle-map.tsv.# -*- Mode: POLY-ORG; indent-tabs-mode: nil; literate-org-py-formatter: ruff; -*- ---
Without it, tangle output drifts vs. canonical formatter format.:tangle path resolves relative to the .org file's
directory, NOT the project root. A git mv of the .org
silently breaks tangling.* at column 0 inside #+BEGIN_SRC python
blocks — even inside docstrings. Org parses bare * as a
headline and silently terminates the src block.:noweb yes to split big classes — see
rules/lp-noweb-for-big-blocks.md for the canonical pattern.make tangle,
git diff --stat python/ MUST be empty (or match your intent).
Non-empty for untouched modules = drift; investigate..py file (via the paths: "**/*.py" matcher) —
including blocked tangle outputs, where the hint reinforces "go
edit the .org instead.".org file when Claude infers it
contains Python src blocks.~/projects/literate-agent/hints/python.org end-to-end on
first activation in a session.docs/tangle-map-schema.org for the reverse-lookup mechanism.~/projects/literate-agent/rules/python-literate-programming.md~/projects/literate-agent/rules/lp-noweb-for-big-blocks.md~/projects/literate-agent/rules/lp-comma-escape-leading-star.md~/projects/literate-agent/docs/tangle-map-schema.orgProvides 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.
npx claudepluginhub jingtaozf/literate-agent --plugin literate-agent