The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll.

Apache-2.0Auto-check passed

Install Gideon API

skills CLI
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill gideon-api -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Sidiora-Labs/centra-gideon-agent gideon-api --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/gideon-api .claude/skills/gideon-api && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gideon-api
GitHub stars
181
Token cost
~1.4k tokens
SKILL.md length
702 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
Apache-2.0

At a glance

The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll.

  • Works in 6 steps: Orient, then drill (don't read everything) → Never guess a signature — copy it → The mandatory verify loop (after every… → …
  • SKILL.md covers 1. Orient, then drill (don't…, 2. Never guess a signature —…, 3. The mandatory verify loop… and 4. Read the error envelope —…, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gideon API is an agent skill from Sidiora-Labs/centra-gideon-agent. The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll. Load this before creating triggers, wiring models, driving app routes, or authoring skills through the API.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The companion AI agent that learns, adapts and gets the work done no matter the task. The licence is Apache-2.0.

Example prompts

  • “s manual for DRIVING Gideon”
  • “/gideon-api”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Orient, then drill (don't read everything)
  2. Never guess a signature — copy it
  3. The mandatory verify loop (after every mutation)
  4. Read the error envelope — it tells you the fix
  5. Worked patterns
  6. Scope — what NOT to do

What it can do on your machine

Read from SKILL.md and the folder at commit 2176d5b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gideon API loads about 1.4k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 702 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Sidiora-Labs/centra-gideon-agent at commit 2176d5b, republished under its Apache-2.0 licence (© Sidiora-Labs). 702 words, ~1,377 tokens.

Download SKILL.mdSave it as .claude/skills/gideon-api/SKILL.md (or your agent's skills folder).
name
gideon-api
description
The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll. Load this before creating triggers, wiring models, driving app routes, or authoring skills through the API.
always
false
triggers
api, manifest, tool signature, drive gideon, /api, endpoint, route, agent-callable, doctor --paths, offline reference, wire a trigger, bind a model, call app…

Driving Gideon (operator's manual)

This is the operator twin of the gideon-features skill. gideon-features answers "what can Gideon do" in prose; this skill is how you drive it correctly from the API and native tools — the exact-signature discipline that turns a driving session from guess-and-retry into first-try success.

The companion to this skill is the offline reference shipped in the distribution. It is the single source of truth for signatures — generated from the same registry the live GET /api/manifest walks, so it never drifts from reality.

1. Orient, then drill (don't read everything)

The reference is four files. Read the index first, then open only the one section you need:

  • reference/index.md — the map + repo gotchas + what-not-to-do. Start here.
  • reference/tools.md — every registered tool, grouped by provider, with its exact input schema and worked examples.
  • reference/routes.md — the agent-callable /api/* HTTP routes with summaries.
  • reference/providers.md — the provider-type taxonomy + registered providers.

Find the reference from the binary alone — you don't need to know the install layout:

gideon doctor --paths

prints tab-separated key<TAB>path lines; the reference line is the directory above. (It also prints config, skills, and install.) On a running gateway the same content is live at GET /api/manifest — same source, two renderings.

2. Never guess a signature — copy it

Hallucinated parameters are the dominant driving failure. Before you call any tool or route:

  1. Look it up in tools.md / routes.md (or GET /api/manifest).
  2. Copy the exact parameter names from the schema. The examples there use real, schema-verified arg names — start from an example and adjust.
  3. If a name isn't in the schema, it doesn't exist — don't invent it.

The examples[] in each tool entry are checked against the live schema by the drift test, so an example never carries an invented parameter. Trust them.

3. The mandatory verify loop (after every mutation)

A tool or route reporting success is not proof the change took. After any mutating call — create/update/delete a trigger, bind a model, install a skill, create a task — read the entity back and confirm the field you set is present:

  • Wired a trigger with hook_register → list hooks / re-read and confirm it's there.
  • Bound a model with PUT /api/models/active/{use_case} → GET /api/models/active and confirm the binding.
  • Added a knowledge item with knowledge_create → knowledge_search (or knowledge_get by id) and confirm it's retrievable.
  • Installed a skill → skill_search and confirm it's in the index.

If the read-back doesn't show your change, the call silently missed — treat that as a failure and diagnose, don't report success.

Show full SKILL.md (294 more words)Show less

4. Read the error envelope — it tells you the fix

Failures returned into your session carry a WHAT / WHY / FIX envelope and a stable code (e.g. ERR_TOOL_ARG_INVALID, ERR_MODEL_UNRESOLVED, ERR_HOOK_PROVIDER_UNKNOWN). Branch on the code, never on the prose. A DID YOU MEAN: line lists the nearest valid values — pick from it directly. When a hook/trigger rejects an unknown action provider, the allowed set arrives as the suggestions; use one of those.

5. Worked patterns

  • Create + wire a trigger: register the follow-up with hook_register (hook_id, context_summary), or schedule recurring work with automation_create. Then read it back (§3).
  • Add knowledge and verify retrieval: knowledge_create (type, title, content) → knowledge_search for the title to confirm it's indexed.
  • Bind a model to a use case: PUT /api/models/active/{use_case} with body {"models": ["provider_name:model_id", ...]} → GET /api/models/active to confirm.
  • Drive an app backend route: call the app-route tool the manifest surfaces for that app's declared route (see app_surfaces[] in the manifest); don't reach into the app's process directly.
  • Author + install a skill: persist a reusable how-to with skill_remember (title, body) → skill_search to confirm it's live.

6. Scope — what NOT to do

  • Don't hand-roll UI when a tool or route already does the job. The manifest is the inventory of what exists; check it before building.
  • Don't edit an installed app's files to change its behavior. Push edits with POST /api/apps/{name}/update {source, confirm:true} — the gateway runs the INSTALLED copy under $GIDEON_HOME/apps/<name>/, not the workspace tree.
  • Don't call a route the manifest doesn't mark agent_callable as if it were an agent API — those are UI transport or websocket surfaces.
  • Don't replace the static/dist symlink with a copy — a cp -R shadows it and serves a stale SPA; rebuild the frontend in place.

For the capability overview and channel-neutral "what can you do", see the gideon-features skill.

© Sidiora-Labs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in runtime/gideon/extensions/skills/bundled/gideon-api of Sidiora-Labs/centra-gideon-agent.

Open the folder on GitHubat commit 2176d5b

Compare with similar skills

Gideon API next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gideon API compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gideon API this skillSidiora-Labs/centra-gideon-agent181—~1.4kAutomated safety check: PassApache-2.0
Personal Operating Manualmohitagw15856/pm-claude-skills1.4k—~1kAutomated safety check: PassMIT
It Operationsdavila7/claude-code-templates32k1 repos~3.7kAutomated safety check: PassMIT
Operator Approval Loopaffaan-m/ECC275k—~3.3kAutomated safety check: PassMIT
Business Operations Skillsalirezarezvani/claude-skills28k—~2.3kAutomated safety check: PassMIT
Feishu Driveopenclaw/openclaw392k—~375Automated safety check: PassMIT

Similar skills

  • Personal Operating Manual

    mohitagw15856/pm-claude-skills

    Write the manual for how you work best — your energy, triggers, communication style, and non-negotiables — to share with a manager, team, or partner (or to know yourself).

    1.4k GitHub stars~1k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • It Operations

    davila7/claude-code-templates

    Manages IT infrastructure, monitoring, incident response, and service reliability.

    32k GitHub starsUsed in 1 repo~3.7k tokens
    DevOps & CloudAuto-check passed
  • Operator approval contract with internal filing notices for agent-drafted outbound messages, hashed drafts, epoch-keyed decisions, durable delivery claims and receipts, and a pre-draft baseline gate.

    275k GitHub stars~3.3k tokensUpdated 3 days ago
    Auto-check passed
  • Business Operations Skills

    alirezarezvani/claude-skills

    A skill your agent uses when running, diagnosing, or designing internal business operations — process documentation, vendor SLAs, capacity planning, internal comms, SOP/runbook authoring…

    28k GitHub stars~2.3k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Feishu Drive

    openclaw/openclaw

    Feishu cloud-storage and comment workflows. An agent skill from openclaw/openclaw.

    392k GitHub stars~375 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Kubernetes Operator

    alirezarezvani/claude-skills

    A skill your agent uses when building a Kubernetes Operator — custom controllers that reconcile CRD state.

    28k GitHub stars~2.8k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed

More from Sidiora-Labs/centra-gideon-agent

All 24 skills in this repo
  • Artifacts

    Sidiora-Labs/centra-gideon-agent

    Persist, version, and iterate on LLM-generated UI (widgets, HTML, markdown).

    181 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Best Of N

    Sidiora-Labs/centra-gideon-agent

    Sample several candidate answers in parallel, judge them against stated criteria, and present the winner with the runners-up kept one click away.

    181 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Document Authoring

    Sidiora-Labs/centra-gideon-agent

    Author a real document — a report, proposal, slide deck, spec, or paper — by settling audience, claim, and structure before drafting prose, then writing to that structure.

    181 GitHub stars~970 tokensUpdated today
    Auto-check passed
  • Editorial Document

    Sidiora-Labs/centra-gideon-agent

    Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups.

    181 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Infographic Syntax

    Sidiora-Labs/centra-gideon-agent

    Author infographics with the AntV declarative DSL — pick a template, fill a small indented data tree, and save as an artifact (kind=infographic) that renders to crisp SVG and streams as you write it.

    181 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Research Campaign

    Sidiora-Labs/centra-gideon-agent

    Run a multi-cycle research campaign — grill the question, decompose it into answerable sub-questions, investigate each against sources, then synthesize with confidence and gaps stated.

    181 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Questions about Gideon API

What does Gideon API do?

The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll. Gideon API is an agent skill from Sidiora-Labs/centra-gideon-agent. The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll.

How do I install Gideon API in Claude Code?

Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill gideon-api -a claude-code`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/gideon-api in Sidiora-Labs/centra-gideon-agent) into .claude/skills/gideon-api in your project. Claude Code loads it when a task matches its description.

How do I install Gideon API in Codex?

Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill gideon-api -a codex`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/gideon-api in Sidiora-Labs/centra-gideon-agent) into .agents/skills/gideon-api in your project. Codex loads it when a task matches its description.

Can I use Gideon API in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Sidiora-Labs/centra-gideon-agent --skill gideon-api -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gideon-api, .gemini/skills/gideon-api, .github/skills/gideon-api and .opencode/skills/gideon-api in your project.

What does Gideon API need to run?

SKILL.md names no scripts, command-line tools or credentials: Gideon API is instructions for the agent only.

Does Gideon API access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Gideon API safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gideon API use?

Gideon API is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gideon API use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gideon API?

Skills that share tags, products or a category with Gideon API: Personal Operating Manual (mohitagw15856/pm-claude-skills, 1.4k stars), It Operations (davila7/claude-code-templates, 32k stars), Operator Approval Loop (affaan-m/ECC, 275k stars) and Business Operations Skills (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gideon API?

Sidiora-Labs (a GitHub organization) maintains it in Sidiora-Labs/centra-gideon-agent, which has 181 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 8, 2026.

Source: Sidiora-Labs/centra-gideon-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.