CtrlK
BlogDocsLog inGet started
Tessl Logo

deerflow-maintainer-orchestrator

Use when a DeerFlow maintainer needs comment-only GitHub issue or PR handling: resolve issue/PR scopes with gh, analyze issues, post or draft issue comments, perform PR review comments, review PR or issue batches, compare competing PRs that target the same issue, give fix strategy, risk classification, and validation guidance. Intended for maintainers and trusted local agents, not general contributors.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A highly actionable, well-sequenced instruction skill with concrete commands, templates, and validation checkpoints. Its main weaknesses are verbatim redundancy of the no-ask/existing-coverage rules and a monolithic structure with no progressive disclosure into separate reference files.

Suggestions

Consolidate the no-ask and existing-coverage rules into their dedicated sections and reference them once from the flows instead of restating them verbatim across Core Rule, Artifact Resolution, Issue Flow, and PR Review Flow to reduce token cost.

Split reference-style content (DeerFlow Review Heuristics, the Validation Guidance table, the Output templates, and the Diff Base Rule) into one-level-deep reference files under references/ and link to them from SKILL.md so the body stays a lean overview.

Trim repeated phrasing such as multiple definitions of "post only the net-new delta" to a single authoritative statement in the Existing Coverage section.

DimensionReasoningScore

Conciseness

The body is dense and avoids explaining concepts Claude already knows, but the no-ask policy and existing-coverage rule are restated near-verbatim across Core Rule, Artifact Resolution, Issue Flow, PR Review Flow, and the No-Question Policy, so it could be tightened; it is not at score 1 because it never pads with known concepts, and not at 3 because of the redundancy.

2 / 3

Actionability

It provides copy-paste-ready commands — e.g. "gh issue view <number> --repo <repo> --json number,title,url,state,body,labels,author,comments" and "git fetch <base-remote> +refs/heads/<base-branch>:refs/remotes/<base-remote>/<base-branch>" — plus concrete comment/finding templates, a severity guide, and an exact validation-command table, fully executable rather than pseudocode.

3 / 3

Workflow Clarity

Multi-step flows (Artifact Resolution, Issue Flow, PR Review Flow) are explicitly numbered and carry real validation checkpoints — "refresh comments" before posting, "re-check the head SHA immediately before posting," and "re-review the new diff or abort" — giving explicit feedback loops for risky batch/post operations.

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets all absent) and the body has no file references, so navigation is safe from nested-reference problems, but the ~290-line multi-flow skill is monolithic with reference-like sections (Review Heuristics, Validation Guidance, Output templates, Diff Base Rule) kept inline that could be split into one-level-deep files; it is not at 1 because section headers are well-organized, and not at 3 because nothing is appropriately split.

2 / 3

Total

10

/

12

Passed

Description

100%

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 with an explicit trigger clause, comprehensive concrete actions, natural maintainer keywords, and a highly distinctive niche. No meaningful weaknesses relative to the rubric.

DimensionReasoningScore

Specificity

The description enumerates many concrete actions — "resolve issue/PR scopes with gh, analyze issues, post or draft issue comments, perform PR review comments, review PR or issue batches, compare competing PRs that target the same issue, give fix strategy, risk classification, and validation guidance" — matching the score-3 anchor of listing multiple specific concrete actions rather than vague language.

3 / 3

Completeness

It opens with an explicit "Use when a DeerFlow maintainer needs comment-only GitHub issue or PR handling:" trigger and follows with a full list of what the skill does, clearly answering both what and when (the guideline caps at 2 only when the Use when clause is missing).

3 / 3

Trigger Term Quality

It covers natural maintainer phrasings — "GitHub issue", "PR", "issue comments", "PR review comments", "review ... batches", "compare competing PRs" — that the target audience would actually say, with good breadth rather than only jargon or a single keyword.

3 / 3

Distinctiveness Conflict Risk

The "DeerFlow maintainer" + "comment-only GitHub issue or PR handling" niche, reinforced by "Intended for maintainers and trusted local agents, not general contributors," gives it a clear, narrow scope unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bytedance/deer-flow
Reviewed

Table of Contents

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.