afk-team-workflow

把一个 Spec 的全部子 issue（或一组显式 issue）组建团队无人值守跑到全部合并或明确暂停。

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/afk-team-workflow/SKILL.md

Quality

Content

81%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.

This is a well-structured, dense orchestration skill with strong sequencing, explicit validation/feedback loops for a batch operation, and good one-level-deep progressive disclosure into real reference files. It is held just short of top marks by a couple of high-level planning steps and two references that point outside the skill bundle.

Suggestions

Tighten the few abstract planning phrases (e.g. '得到真实的验收边界、canonical dependency graph') into concrete checklist items the team-lead must produce.

Make the out-of-bundle references (issue-tracker.md, CONTRIBUTING.md) explicit about being repo-level docs, or inline the minimal convention needed so the skill is self-contained.

Consider a short 'Quick start / inputs' block at the top so the entry command (batch-poll.sh + ledger.sh) is immediately visible before the staged detail.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence, delegating role detail to references and avoiding restatement of known concepts; only a few sentences could be tightened further, keeping it just short of fully lean.	4 / 5
Actionability	Concrete commands and paths are given (scripts/batch-poll.sh, scripts/ledger.sh, git cherry-pick, rebase merge, Closes #<N>/Refs #<N> conventions) with specific handoff paths; a few planning steps remain high-level ('得到真实的验收边界'), leaving minor gaps.	4 / 5
Workflow Clarity	Four sequenced stages with explicit validation checkpoints (green HEAD, mergeable=MERGEABLE, headRefOid match, quiesce-first, abort-on-conflict) and clear feedback loops (re-enter review loop, rebase/force-with-lease, re-validate) cover this batch operation thoroughly.	5 / 5
Progressive Disclosure	SKILL.md is an overview pointing one level deep to real reference files (recovery.md, model-selection.md, spawn-prompts.md, implementer.md, local-reviewer.md, review-looper.md) and scripts, all present in the bundle; two references resolve to repo-level paths outside the skill bundle (../../../docs/agents/issue-tracker.md, ../../../../CONTRIBUTING.md), a minor navigation gap.	4 / 5
	Total	17 / 20 Passed

Description

53%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.

The description conveys a clear, distinctive purpose but is a single terse sentence that omits an explicit 'Use when...' trigger clause and lists only the headline action. It is adequate but would benefit from explicit trigger guidance and a slightly broader action enumeration.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when you want to run a Spec's sub-issues (or an explicit issue set) unattended through to merge or pause.'

Enumerate 1-2 more concrete actions the team-lead performs (plan stages, dispatch implementer/reviewer, integrate via cherry-pick) to lift specificity beyond the headline outcome.

Include a natural-language synonym or two (e.g. '无人值守 / 后台跑 / 批量推进') so users phrase the need in their own words.

Dimension	Reasoning	Score
Specificity	Names the domain ('Spec 的全部子 issue 或一组显式 issue') and concrete outcomes ('组建团队无人值守跑到全部合并或明确暂停'), but covers only the core action without enumerating the plan/schedule/integrate/adjudicate activities the body reveals.	3 / 5
Completeness	It states a clear 'what' (run a team over spec sub-issues to merge or pause) but provides no 'when' / explicit trigger clause, which the rubric caps at 3.	3 / 5
Trigger Term Quality	Relevant domain terms ('Spec', '子 issue', '组建团队', '无人值守') are present, but it leans on workflow jargon and omits natural trigger phrases a user would say; no synonyms or 'Use when...' phrasing.	3 / 5
Distinctiveness Conflict Risk	The niche is fairly specific (unattended team execution of spec sub-issues to terminal merge/pause state), distinct from generic coding skills with only minor overlap risk against general agent-orchestration skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: ArcReel/ArcReel
Path: .agents/skills/afk-team-workflow/SKILL.md
Commit: 5350d64

Reviewed: 4 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.