markdown-vague
Skill10 starsChanged todayMITView on GitHub
Markdown parsing skipping fenced code blocks in step validation
In this repository44 other files it gives its agents.
- llms-full.txtllms.txt
- llms.txtllms.txt
- ai-prompt-engineering-safety-reviewSkill
- ast-codemapSkill
- ast-grepSkill
- autoharnessSkill
- autonomous-backlog-driverSkill
- claude-kimi-mcp-normalizationSkill
- cli-self-updaterSkill
- code-frugalitySkill
- codemode-gatewaySkill
- codemode-typesSkill
- consequence-simulationSkill
- context-pruningSkill
- github-update-checkerSkill
- google-agents-cli-evalSkill
- google-agents-cli-scaffoldSkill
- history-searchSkill
- hook-gatingSkill
- hybrid-semantic-searchSkill
- kimi-code-agent-integrationSkill
- kimi-mcp-configurationSkill
- leann-vectorSkill
- log-summarizerSkill
- memory-reconciliationSkill
- mode-classificationSkill
- multiagent-orchestrationSkill
- output-compressionSkill
- prompt-injectionSkill
- python-anti-patternsSkill
- regression-sentinelSkill
- restart-trackingSkill
- rollback-guardSkill
- rust-call-graphSkill
- secrets-managementSkill
- security-best-practicesSkill
- session-compactorSkill
- sqlite-memorySkill
- swarm-barrierSkill
- swarm-dagSkill
- autoharnessSkill
- code-reliability-checksSkill
- skill-threat-rulesSkill
- autoharnessSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Use when extracting lists, steps, and procedures from Markdown documents while ignoring nested or illustrative code snippets.
- Very specific: line 16
When encountering a fence delimiter, toggle in_fence and reset any current item accumulator.
- Very specific: line 19
Run vague step heuristics (vague_step) only on genuine procedural items.
- Very specific: line 22
Run pytest testing vague.vague_steps on Markdown containing fenced code blocks with dash lines (e.g.
- Distinctive: line 23
Verify that no false positive warnings or trailing fence markers are produced.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
markdown-vague
When to use
Use when extracting lists, steps, and procedures from Markdown documents while ignoring nested or illustrative code snippets.
Steps
- Detect fenced code blocks in Markdown:
- Identify triple backtick (
```) or triple tilde (~~~) delimiters with optional language tags. - Maintain a boolean
in_fencestate across line iterations.
- Identify triple backtick (
- In list item extraction (
vague.items):- When encountering a fence delimiter, toggle
in_fenceand reset any current item accumulator. - While
in_fenceis true, ignore list item markers (-,*,+,1.) so code lines are never treated as procedural steps.
- When encountering a fence delimiter, toggle
- Validate steps outside code blocks:
- Run vague step heuristics (
vague_step) only on genuine procedural items.
- Run vague step heuristics (
How to verify
- Run pytest testing
vague.vague_stepson Markdown containing fenced code blocks with dash lines (e.g.- do it properly). - Verify that no false positive warnings or trailing fence markers are produced.
Facts found here
- Standard Markdown fenced code blocks start and end with at least three consecutive backticks or tildes at line start (source: https://spec.commonmark.org/0.31.2/#fenced-code-blocks).
- Lines inside code blocks frequently use dash prefixes for CLI flags, bullet comments, or diffs that must not be parsed as CommonMark list items.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

