agentleFS
niksavisniksavis/basicly/.claude/skills/interface-facts/SKILL.md

interface-facts

Skill2 starsChanged 6 days agoMITView on GitHub

Establishes a third-party CLI flag, API field, model, price or limit from the tool and live vendor docs. Use before code depends on it.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do steps 1 to 4 in order and stop at the first one that answers the question.

    line 15
  2. Distinctive:

    Read the vendor's changelog: when a version matters, and the vendor's source or issue tracker when a documented feature does not work.

    line 20
  3. Distinctive:

    When a repo document and the vendor disagree, the vendor decides what the interface does.

    line 34
  4. Distinctive:

    When a value we depend on can be compared with data we already record, make the comparison a gate.

    line 36

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Generated by `basicly skills-build` from skill.yaml. Do not edit; edit the source. -->

Interface Facts

Establish how a third-party interface behaves from evidence you observe now. A model knows an interface only as it was at training time, and vendors change interfaces.

The skill covers CLI flags and output formats, API fields and endpoints, model ids, context windows, token accounting, prices, rate limits, config schemas and behaviour that changes with a version.

Steps

Do steps 1 to 4 in order and stop at the first one that answers the question. If an earlier step contradicts that answer, take the vendor's answer and say what disagreed. Always do step 5.

  1. Read our own code that touches the interface: git grep -n TOOL; an empty result counts as absence only after the same search finds a known match. An adapter, a parser or a hook was written against a real probe and is under test. Read it before our own prose.
  2. Run the installed binary: TOOL --help, TOOL --version, --dry-run, or an invalid flag whose error names the valid set. For a default behaviour, run the command itself; a flag list does not show a default.
  3. Fetch the vendor's current documentation from the route in routes. Limit any search to the vendor's own host; an aggregator, a mirror or a summary is not a source. Ask a narrow question: the exact flag or field name. Use browser tools only when a page needs JavaScript.
  4. Read the vendor's changelog when a version matters, and the vendor's source or issue tracker when a documented feature does not work.
  5. Record the fact, as shown below.

Writing by anyone other than the vendor is the weakest evidence and never enough alone. A landing page or a feature grid is marketing. A README is a claim.

State the claim precisely

  • Keep "the capability exists" apart from "we can reach it". A documented feature can have no flag or output mode that our dispatch can read. A value that is not on stdout can still be readable from another place.
  • Write the claim at the precision the evidence supports. "Has no config-file deny rule" is correct where "has no config file" is not. A vague note invites the next reader to remove what it justifies.

Record the fact

Comment on the tracker record, as work-tracker shows, with verified DATE against URL (TOOL VERSION): .... Never cache or commit the fetched page; its licence is not ours to give.

When a repo document and the vendor disagree, the vendor decides what the interface does. The repo decides what we chose to do. Correct the document in place and name what refuted it.

When a value we depend on can be compared with data we already record, make the comparison a gate. A declared limit that recorded data contradicts is a defect that a machine can detect.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.