fastgpt-docker-deploy

FastGPT Docker Compose self-hosting deployment workflow. Use when a user asks an AI agent to deploy FastGPT with Docker by referencing /deploy/SKILL.md, including creating an empty fastgpt directory, running the install script in non-interactive mode, starting Docker Compose, monitoring service health, troubleshooting compose issues, and returning the access URL plus root credentials and next steps.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a high-quality, command-driven deployment runbook with an explicit sequenced workflow, validation checkpoints, and recovery guidance. Its only weakness is conciseness: scattered version-number references (v4.14/v4.15) act as time-sensitive information that is not isolated in a deprecated section.

Suggestions

Consolidate version-specific guidance (v4.14/v4.15, STORAGE_EXTERNAL_ENDPOINT, FASTGPT_S3_ENDPOINT) into a dedicated '旧版/兼容 (Legacy compatibility)' section so the main flow stays version-agnostic and avoids time-sensitive clutter.

Move the optional environment-variable override list into a short reference table or a companion file so the core 6-step flow reads as a lean quick-start path.

Consider extracting the 常见问题处理 troubleshooting matrix into a separate TROUBLESHOOTING.md reference, keeping SKILL.md as a concise overview with one-level-deep navigation.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and command-driven with no conceptual padding about what Docker or Compose is, but time-sensitive version numbers (v4.14, v4.15) are scattered through the main flow and troubleshooting rather than isolated in a deprecated/old-patterns section, which the rubric flags as a conciseness penalty; not level 3 for that reason, not level 1 because there is no generic conceptual explanation.	2 / 3
Actionability	Provides fully executable commands ('curl -fsSL https://doc.fastgpt.cn/deploy/install.sh -o install.sh', 'FASTGPT_NON_INTERACTIVE=true bash install.sh', 'docker compose up -d', 'curl -I http://localhost:3000') plus specific env-var overrides; copy-paste ready; not level 2 because there is no pseudocode and key details are complete.	3 / 3
Workflow Clarity	A clearly numbered 1–6 sequence includes explicit validation checkpoints (step 5 waits for running/healthy services via 'docker compose ps' and logs, step 6 verifies access via 'curl -I http://localhost:3000') and a troubleshooting section giving fix-and-retry feedback loops; not level 2 because checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	A single well-organized SKILL.md with clear section headers (目标, 工作边界, 部署流程, 常见问题处理, 最终回复), no nested references, and no bundle files needed; per the simple-skills scoring note this qualifies for 3, and not level 2 because structure is clear and nothing that should be split is inlined.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong across all dimensions: third-person voice, concrete enumerated actions, an explicit 'Use when...' trigger, and a distinct niche. The only minor awkwardness is the 'by referencing /deploy/SKILL.md' phrase, which reads as an internal path hint rather than a user-facing trigger, but it does not weaken the score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'creating an empty fastgpt directory, running the install script in non-interactive mode, starting Docker Compose, monitoring service health, troubleshooting compose issues, and returning the access URL plus root credentials and next steps' — matching the 'lists multiple specific concrete actions' anchor; not level 2 because coverage is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both what (the deployment workflow actions) and when via a clear 'Use when a user asks an AI agent to deploy FastGPT with Docker' clause; not level 2 because the trigger is explicit rather than implied.	3 / 3
Trigger Term Quality	Natural user phrasing is present ('deploy FastGPT with Docker', 'FastGPT Docker Compose self-hosting deployment'), which a user would genuinely say; not level 2 because it covers the common variations rather than only one keyword.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (FastGPT Docker self-hosting) with distinct triggers unlikely to fire for unrelated skills; not level 2 because it is specific enough to avoid overlap with generic Docker skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: labring/FastGPT
Path: document/public/deploy/SKILL.md
Commit: dc97c08

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.