cli-doc-maintainer
Skill38 starsChanged 6 days agoApache-2.0View on GitHub
Maintain AILANG CLI help as single source of truth. Use when: adding new commands, adding environment variables, updating command behavior, auditing CLI documentation, ensuring help.go matches codebase implementation, improving CLI discoverability for AIs.
In this repository85 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- docs/llms.txtllms.txt
- llms.txtllms.txt
- agent-inboxSkill
- ailang-core-triageSkill
- ailang-packagesSkill
- benchmark-managerSkill
- benchmark-runnerSkill
- builtin-developerSkill
- cloud-cascade-debugSkill
- cloud-setupSkill
- codebase-organizerSkill
- collaboration-hubSkill
- coordinator-helperSkill
- design-doc-creatorSkill
- design-spec-auditorSkill
- docs-syncSkill
- eval-analyzerSkill
- eval-gap-finderSkill
- gemini-cli-helperSkill
- github-issue-triageSkill
- headless-runnerSkill
- local-model-onboardingSkill
- local-ollama-evalSkill
- mission-briefSkill
- mission-controlSkill
- mission-loop-changeSkill
- model-managerSkill
- motoko-analyzerSkill
- parser-developerSkill
- post-releaseSkill
- pr-monitorSkill
- prompt-managerSkill
- release-managerSkill
- sonarcloud-triageSkill
- sprint-evaluatorSkill
- sprint-executorSkill
- sprint-plannerSkill
- test-coverage-guardianSkill
- trace-debuggerSkill
- use-ailangSkill
- wasm-debuggerSkill
- agent-inboxSkill
- ailang-core-triageSkill
- ailang-packagesSkill
- benchmark-managerSkill
- benchmark-runnerSkill
- builtin-developerSkill
- cli-doc-maintainerSkill
- cloud-cascade-debugSkill
- cloud-setupSkill
- codebase-organizerSkill
- collaboration-hubSkill
- coordinator-helperSkill
- design-doc-creatorSkill
- design-spec-auditorSkill
- docs-syncSkill
- eval-analyzerSkill
- eval-gap-finderSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
16 rules. About 0 are common, 12 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Ensure AILANG CLI help system (ailang --help) remains the authoritative, accurate, and complete source of truth for all CLI features.
- Distinctive: line 31
After adding new features (ensure they're documented)
- Distinctive: line 33
Proactively: After implementing any user-facing CLI change
- Distinctive: line 85
Run audit scripts to identify discrepancies:
- Very specific: line 98
Missing command: Add to appropriate category in help.go
- Distinctive: line 99
Missing env var: Document with clear purpose and example
- Distinctive: line 100
Stale documentation: Remove or update
- Distinctive: line 101
New feature: Add examples showing usage
- Very specific: line 105
Update cmd/ailang/help.go:
- Distinctive: line 106
Add new commands in correct category
- Distinctive: line 107
Document new flags/subcommands
- Distinctive: line 108
Add environment variables with examples
- Distinctive: line 164
Practical Examples: Every major command has a working example
- Distinctive: line 169
Run audits after every CLI change (make it a habit)
- Very specific: line 172
Keep main help.go under 250 lines (currently ~220)
- Distinctive: line 174
Test examples actually work before documenting them
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
CLI Documentation Maintainer
Ensure AILANG CLI help system (ailang --help) remains the authoritative, accurate, and complete source of truth for all CLI features. Critical for AI discoverability in external repositories where AGENTS.md isn't available.
Quick Start
Most common usage:
# User says: "I added a new command, update the help"
# This skill will:
# 1. Audit help.go against main.go for missing commands
# 2. Check environment variables usage
# 3. Suggest improvements to help text
# 4. Validate all documented features exist
# 5. Update help.go with new contentWhen to Use This Skill
Invoke this skill when:
- Adding new commands to cmd/ailang/main.go
- Adding new environment variables (DEBUG_, AILANG_, etc.)
- Updating command behavior or flags
- Auditing CLI documentation for accuracy
- Improving CLI discoverability for AIs
- After adding new features (ensure they're documented)
- Quarterly CLI documentation review
- Proactively: After implementing any user-facing CLI change
Available Scripts
scripts/audit_commands.sh
Compare commands in main.go against help.go to find undocumented commands.
Usage:
scripts/audit_commands.shOutput:
- Lists all commands in main.go
- Highlights commands missing from help.go
- Shows commands in help.go that don't exist in main.go (stale)
- Exit code 0 if synchronized, 1 if discrepancies found
scripts/audit_env_vars.sh
Find environment variables used in codebase and compare against help.go documentation.
Usage:
scripts/audit_env_vars.shOutput:
- Lists all DEBUG_* and AILANG_* variables found in internal/
- Shows which are documented in help.go
- Highlights undocumented variables
- Flags documented variables that don't exist in code (stale)
- Exit code 0 if synchronized, 1 if discrepancies found
scripts/suggest_improvements.sh
Analyze help text organization and suggest improvements.
Usage:
scripts/suggest_improvements.shOutput:
- Checks help text length (should be scannable)
- Verifies examples are present
- Suggests missing categories or groupings
- Recommends cross-references between related commands
- Flags verbose or unclear descriptions
Workflow
1. Audit Phase
Run audit scripts to identify discrepancies:
# Check commands
.Codex/skills/cli-doc-maintainer/scripts/audit_commands.sh
# Check environment variables
.Codex/skills/cli-doc-maintainer/scripts/audit_env_vars.sh2. Analysis Phase
For each discrepancy found:
- Missing command: Add to appropriate category in help.go
- Missing env var: Document with clear purpose and example
- Stale documentation: Remove or update
- New feature: Add examples showing usage
3. Update Phase
Update cmd/ailang/help.go:
- Add new commands in correct category
- Document new flags/subcommands
- Add environment variables with examples
- Include practical usage examples
- Maintain consistent formatting
4. Validation Phase
# Rebuild binary
make quick-install
# Test help output
ailang --help
# Test specific command help
ailang <command> --help
# Verify examples work
# (copy examples from help and test them)5. Documentation Phase
Update supporting documentation:
- CHANGELOG.md - Document CLI changes
- This skill's reference.md - Update best practices if needed
- Website docs (docs/docs/) - Mirror critical CLI info
Resources
CLI Documentation Best Practices
See resources/best_practices.md for:
- Formatting conventions
- Category organization
- Example writing guidelines
- Environment variable naming conventions
Help Text Template
See resources/help_template.md for:
- Command entry templates
- Category section templates
- Environment variable documentation template
- Example section templates
Progressive Disclosure
This skill loads information progressively:
- Always loaded: This SKILL.md file (YAML frontmatter + workflow overview)
- Execute as needed: Scripts in
scripts/(audit, validate) - Load on demand:
resources/best_practices.md,resources/help_template.md
Design Principles
- CLI as Source of Truth: Help text is THE authoritative reference
- AI-First: Optimize for discoverability by AIs in external repos
- Progressive Disclosure: Main help scannable, detailed help via subcommands
- Practical Examples: Every major command has a working example
- Accurate: Zero stale documentation - audit regularly
Notes
- Run audits after every CLI change (make it a habit)
- Environment variables must be used in code before documenting
- Commands must exist in main.go before adding to help.go
- Keep main help.go under 250 lines (currently ~220)
- Per-command help (e.g.,
coordinator --help) can be longer - Test examples actually work before documenting them
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.

