How do I install the Kiss API Docs skill?

Run npx skillmds@latest add dauquangthanh/kiss-api-docs-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Kiss API Docs safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Kiss API Docs?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Kiss API Docs free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Kiss API Docs?

dauquangthanh (@dauquangthanh) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Kiss API Docs by dauquangthanh — Agent Skill

Name: Kiss API Docs
Author: dauquangthanh

Kiss API Docs

Generates API documentation from source code: lists endpoints / RPC methods / queue topics with their schemas and auth. Works backward from routes + OpenAPI / proto / gql definitions. Use when documenting an API, generating endpoint reference docs, or when the project needs OpenAPI, gRPC, or GraphQL schemas documented.

dauquangthanh Updated Sep 21, 2026

File contents

User Input

$ARGUMENTS

Audience and tone (interactive mode)

When KISS_AGENT_MODE=interactive (the default), assume the user has limited technical background and limited domain knowledge — they may know basics but lack deep expertise in this skill's area. Run this skill as a guided questionnaire:

One question at a time. No walls of questions.
Yes / no first. Phrase so yes, no, not sure, or skip is a valid answer.
Translate jargon, don't strip it. Use the technical term but always pair it with a plain-English gloss the first time it appears.
Choices, not blank fields. When yes/no isn't enough, offer 2-4 lettered options (A/B/C/D) with one-line plain-language descriptions of the trade-off. Always include "Not sure — pick a sensible default".
Always recommend. State the option you would pick and why in one sentence so the user can reply "yes" / "ok" to accept. Pull defaults from upstream artefacts (spec, architecture, ADRs, standards) before asking blank.
Show, don't ask. When upstream artefacts already imply an answer, propose it as a pre-filled finding and ask for a yes / no confirmation rather than asking the user to fill in a blank.
not sure / skip triggers a sensible default, marked "(default applied — confirm later)" in the artefact, and a debt entry in this skill's debt file.

When KISS_AGENT_MODE=auto (or --auto), skip the questionnaire entirely: apply sensible defaults from upstream artefacts and log decisions to the parent agent's decision log.

Inputs

.kiss/context.yml
{context.paths.docs}/analysis/codebase-scan.md
Route modules + OpenAPI / proto / GraphQL schema files

Outputs

{context.paths.docs}/analysis/api-docs.md
{context.paths.docs}/analysis/api-docs.extract

Context Update

Does not mutate .kiss/context.yml.

Handoffs

kiss-dev-design (architect / developer) references api-docs when evolving contracts.
kiss-security-review uses the endpoint list for authZ review.

AI authoring scope

Does: enumerate endpoints, include request / response schemas, auth requirement, error responses; annotate with source file:line.

Does not: invent routes; guess schemas where the code doesn't declare them; hit live endpoints.

Usage

<SKILL_DIR> = the integration's skills root (e.g. .claude/skills/ for Claude Code, .agents/skills/ for Antigravity / Codex, .cursor/skills/ for Cursor, .windsurf/workflows/ for Windsurf). Scripts live at <SKILL_DIR>/<skill-name>/scripts/….

API_STYLE=rest bash <SKILL_DIR>/kiss-api-docs/scripts/bash/generate-api-docs.sh --auto

Answer keys

Key	Default
`API_STYLE` (`rest`/`graphql`/`grpc`/`trpc`/`events`)	`rest`

---name: kiss-api-docs-2description: Generates API documentation from source code: lists endpoints / RPC methods / queue topics with their schemas and auth. Works backward from routes + OpenAPI / proto / gql definitions. Use when documenting an API, generating endpoint reference docs, or when the project needs OpenAPI, gRPC, or GraphQL schemas documented.---## User Input```text$ARGUMENTS```## Audience and tone (interactive mode)When `KISS_AGENT_MODE=interactive` (the default), assume the userhas **limited technical background and limited domain knowledge**— they may know basics but lack deep expertise in this skill'sarea. Run this skill as a guided questionnaire:- **One question at a time.** No walls of questions.- **Yes / no first.** Phrase so `yes`, `no`, `not sure`, or `skip` is a valid answer.- **Translate jargon, don't strip it.** Use the technical term but always pair it with a plain-English gloss the first time it appears.- **Choices, not blank fields.** When yes/no isn't enough, offer 2-4 lettered options (A/B/C/D) with one-line plain-language descriptions of the trade-off. Always include "Not sure — pick a sensible default".- **Always recommend.** State the option you would pick and why in one sentence so the user can reply "yes" / "ok" to accept. Pull defaults from upstream artefacts (spec, architecture, ADRs, standards) before asking blank.- **Show, don't ask.** When upstream artefacts already imply an answer, propose it as a pre-filled finding and ask for a yes / no confirmation rather than asking the user to fill in a blank.- **`not sure` / `skip` triggers a sensible default**, marked "(default applied — confirm later)" in the artefact, and a debt entry in this skill's debt file.When `KISS_AGENT_MODE=auto` (or `--auto`), skip the questionnaireentirely: apply sensible defaults from upstream artefacts and logdecisions to the parent agent's decision log.## Inputs- `.kiss/context.yml`- `{context.paths.docs}/analysis/codebase-scan.md`- Route modules + OpenAPI / proto / GraphQL schema files## Outputs- `{context.paths.docs}/analysis/api-docs.md`- `{context.paths.docs}/analysis/api-docs.extract`## Context UpdateDoes not mutate `.kiss/context.yml`.## Handoffs- `kiss-dev-design` (architect / developer) references api-docs when evolving contracts.- `kiss-security-review` uses the endpoint list for authZ review.## AI authoring scope**Does:** enumerate endpoints, include request / responseschemas, auth requirement, error responses; annotate with source`file:line`.**Does not:** invent routes; guess schemas where the code doesn'tdeclare them; hit live endpoints.## Usage> `<SKILL_DIR>` = the integration's skills root (e.g. `.claude/skills/`> for Claude Code, `.agents/skills/` for Antigravity / Codex,> `.cursor/skills/` for Cursor, `.windsurf/workflows/` for Windsurf).> Scripts live at `<SKILL_DIR>/<skill-name>/scripts/…`.```bashAPI_STYLE=rest bash <SKILL_DIR>/kiss-api-docs/scripts/bash/generate-api-docs.sh --auto```### Answer keys| Key | Default ||---|---|| `API_STYLE` (`rest`/`graphql`/`grpc`/`trpc`/`events`) | `rest` |

Frequently asked questions