arming-thought

触发：在每次新的顶层对话开始时自动调用，用于建立“实事求是”的总原则，并在明确适用时为后续任务选择下游 skill；如果你是被派遣执行单一具体任务的子 agent，则跳过此 skill。 English: Trigger at the start of each new top-level conversation to establish the core methodology and select downstream skills only when clearly useful. Skip this skill when you are a delegated sub-agent handling a narrow, concrete task.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/arming-thought/SKILL.md

Quality

Content

78%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.

The content is a well-structured, actionable methodology/router skill that stays concise and organizes its decision logic clearly in tables. Its only soft spot is mild philosophical framing and the absence of an explicit verification checkpoint in the routing flow.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with efficient tables and sectioned structure; only minor philosophical framing (the Mao quote and '武装思想' motivation) could be trimmed without losing actionability.	4 / 5
Actionability	Provides concrete, actionable guidance: a situation-to-skill dispatch table and explicit platform-specific invocation instructions (Skill tool, commands/ directory, skills/*/SKILL.md); minor gaps because per-skill execution detail is delegated downstream.	4 / 5
Workflow Clarity	The decision flow (apply 实事求是 → evaluate dispatch criteria → select one skill → respect priority order) is clearly sequenced; as a non-destructive router it needs no validation checkpoint, and the simple-skill exception supports a high score, but the flow lacks an explicit verification step.	4 / 5
Progressive Disclosure	A single self-contained SKILL.md with well-organized sections and tables, no bundle files, and no need for external references; per the simple-skill note this qualifies for the top score on organization alone.	5 / 5
	Total	17 / 20 Passed

Description

62%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 clearly states both purpose and trigger condition with a useful skip clause, making it functional and fairly distinctive as a conversation-start router. Its main weakness is abstract action language and contextual rather than user-utterance trigger terms.

Suggestions

Add concrete behavioral verbs for what the skill does (e.g., 'applies a fact-first check, then routes to one downstream skill when clearly useful') to lift specificity toward the higher anchors.

Include a couple of natural trigger phrases a user might say, or natural synonyms, so trigger term quality better matches user language.

Keep the bilingual description but align voice to third person throughout; the Chinese line currently addresses the reader in second person ('如果你是…').

Dimension	Reasoning	Score
Specificity	Names the domain (methodology/router framework) and two concrete actions — 'establish the core methodology' and 'select downstream skills' — but the actions are abstract rather than the kind of concrete operations the higher anchors require.	3 / 5
Completeness	Clearly answers both 'what' (establish methodology, select downstream skills) and 'when' (start of each new top-level conversation, with an explicit sub-agent skip condition); not a 5 because the trigger is contextual rather than the user-mention pattern in the top anchor.	4 / 5
Trigger Term Quality	Has an explicit trigger ('Trigger at the start of each new top-level conversation') with relevant terms, but these are contextual/auto-fire conditions rather than natural phrases a user would say, and synonyms are absent.	3 / 5
Distinctiveness Conflict Risk	Occupies a distinct conversation-start router niche with explicit skip/defer conditions that reduce overlap with task skills; minor residual broadness from applying to every top-level conversation keeps it below 5.	4 / 5
	Total	14 / 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: HughYau/qiushi-skill
Path: skills/arming-thought/SKILL.md
Commit: cbe6b08

Reviewed: ~18 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.