Skip to content

docs: add concrete usage examples for all 24 tools - #213

Open
TerminalGravity wants to merge 4 commits into
mainfrom
docs/tool-usage-examples
Open

docs: add concrete usage examples for all 24 tools#213
TerminalGravity wants to merge 4 commits into
mainfrom
docs/tool-usage-examples

Conversation

@TerminalGravity

Copy link
Copy Markdown
Collaborator

The Tool Reference section lists all 24 tools but doesn't show how to actually use them. This adds a Usage Examples section with real-world invocations organized by workflow:

  • Everyday preflight_check usage (triage, force levels)
  • Planning with scope_work
  • Clarifying vague prompts (clarify_intent, sharpen_followup)
  • Sub-agent enrichment
  • History search and contracts
  • Session management (checkpoint, handoff, health)
  • Analysis and scoring (prompt_score, scorecard, cost, token_audit)
  • Verification before shipping
  • Learning from mistakes (log_correction, check_patterns)
  • Multi-task sequencing

Every example uses real parameter names and realistic values.

- examples/.preflight/config.yml — profile, related projects, thresholds, embeddings
- examples/.preflight/triage.yml — keyword rules and strictness tuning
- examples/.preflight/contracts/api.yml — manual cross-service contract definitions
- examples/README.md — quick setup instructions
- README.md — link to examples from config reference section
…MCP server

The 'preflight-dev' bin runs the init wizard, not the server. Users following
the npm install path had no way to launch the actual MCP server without
pointing into node_modules (which the init script was doing incorrectly,
referencing 'preflight' instead of 'preflight-dev').

- Add bin/serve.js as 'preflight-dev-serve' entry point
- Fix init CLI to generate correct .mcp.json using preflight-dev-serve
- Update README quickstart to use npx -y preflight-dev-serve
Adds a new 'Usage Examples' section to README with real-world
invocations organized by workflow: everyday preflight, planning,
clarifying vague prompts, sub-agent enrichment, history search,
session management, analysis/scoring, verification, learning
from mistakes, and multi-task sequencing.

@TerminalGravity TerminalGravity left a comment

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

24 tools with examples — this is going to be a huge help for discoverability. People shouldn't have to read source code to understand what each tool does. LGTM.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant