claude-to-deerflow

Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

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

An actionable, well-structured API skill body with executable curl examples covering the full operation set and sensible reference scripts. Slight conciseness and workflow-checkpoint refinements would push it higher.

Suggestions

Add an explicit validation checkpoint in the messaging workflow (e.g. 'Confirm the response contains a thread_id before proceeding to stream') so the sequence has a clear feedback step.

Trim low-value preamble and tips such as 'Read these env vars before making any request' and 'Thread IDs persist — you can return to a conversation later' to tighten token efficiency.

Consider moving the SSE parsing details into a short references section or a dedicated script so the core operations stay scannable.

Dimension	Reasoning	Score
Conciseness	Mostly lean with executable curl snippets and minimal concept re-explanation, though a few tips and preamble lines ('Read these env vars before making any request', 'Thread IDs persist') are slightly redundant. Not a 5 because minor padding remains.	4 / 5
Actionability	Copy-paste-ready curl commands with complete JSON payloads, real endpoints, and documented response shapes cover every common operation (health, messaging, models, skills, uploads, history).	5 / 5
Workflow Clarity	The primary flow is a clear two-step sequence (create thread, then stream a run) and the helper script lists a numbered process, but it lacks an explicit validation checkpoint confirming the thread_id before streaming; not a 5 because checkpoints are implicit rather than stated.	4 / 5
Progressive Disclosure	Well-organized into per-operation sections with a one-level reference to the real scripts/chat.sh and scripts/status.sh; SSE parsing guidance is inline rather than extracted to a reference, but for a single-purpose API skill that placement is reasonable.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

A strong, specific description that clearly states the skill's capabilities and when to invoke it, using natural trigger language tied to a distinct named platform. No fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('send messages or questions', 'start a conversation thread', 'check status or health', 'list models/skills/agents', 'manage memory', 'upload files', 'delegate research tasks') with comprehensive coverage of the API's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (enumerate the HTTP operations) and 'when' ('Use this skill when...', 'Also use when the user mentions deerflow, deer flow...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases and synonyms ('send messages or questions', 'check DeerFlow status', 'deerflow', 'deer flow', 'deep research task') covering the ways a user would actually request this skill.	5 / 5
Distinctiveness Conflict Risk	Targets a specifically named platform (DeerFlow) with its own distinct trigger terms, making overlap with other skills minimal.	5 / 5
	Total	20 / 20 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: bytedance/deer-flow
Path: skills/public/claude-to-deerflow/SKILL.md
Commit: 2a261d2

Reviewed: about 16 hours 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.