cs-feedback

CodeStable 使用反馈闭环。仅在用户明确要求记录或上报 cs skill 跑偏、工具失败、规则不清、agent 被纠正时使用；采集本机证据并准备可确认的公开 issue。

Quality

100%

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

Quality

Content

100%

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

A well-engineered, safety-conscious skill body: executable commands, explicit privacy boundaries, validation checkpoints, and a clean separation between overview and reference material. It earns high marks across all four content dimensions.

Dimension	Reasoning	Score
Conciseness	Information-dense operational prose with no padding explaining concepts Claude already knows; every section (state machine, allowlists, file layout) carries domain-specific weight the model would not infer.	3 / 3
Actionability	Provides complete, copy-paste-ready bash invocations with full argument lists, exact JSON field names, and enumerated allowlist fields (8 v1 / 7 v2) rather than vague direction.	3 / 3
Workflow Clarity	A clearly sequenced 6-step workflow with explicit validation checkpoints (triage_ready requirements, public-preview confirmation before any GitHub call) plus a Failure Behavior section and an exit-condition checklist.	3 / 3
Progressive Disclosure	Body stays an operational overview and pushes the detailed template to references/report-template.md; the 相关文档 section signals real one-level-deep bundle paths, all of which exist on disk.	3 / 3
	Total	12 / 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, third-person description that states concrete capabilities, explicit trigger conditions, and a clearly bounded niche. It avoids fluff and answers both 'what' and 'when' directly.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "记录或上报" (record/report), "采集本机证据" (collect local evidence), "准备可确认的公开 issue" (prepare confirmable public issue) — rather than vague abstractions.	3 / 3
Completeness	Explicitly answers both what (feedback loop that collects local evidence and prepares a public issue) and when ("仅在...时使用" is an explicit Use-only-when clause), so it is not capped at 2.	3 / 3
Trigger Term Quality	Covers natural trigger phrasing a CodeStable user would actually say — "cs skill 跑偏", "工具失败", "规则不清", "agent 被纠正" — across the four common failure modes.	3 / 3
Distinctiveness Conflict Risk	A narrow, explicitly user-invoked niche (CodeStable self-feedback only) with distinct triggers makes accidental activation by other skills unlikely.	3 / 3
	Total	12 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: codestable/CodeStable
Path: plugins/codestable/skills/cs-feedback/SKILL.md
Commit: 7bed4ed

Reviewed: 1 day 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.