CtrlK
BlogDocsLog inGet started
Tessl Logo

issue-reporter

只在用户明确要求提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request 时使用。用户只说“提交问题”“提交反馈”“上报 bug”“这是个 bug”或描述功能建议但未点名 GitHub 时不得触发,必须改用 cherry-studio-feedback 并默认提交飞书。

70

Quality

86%

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

86%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.

A genuinely lean, command-driven skill body that respects the context window and gives copy-paste-ready commands for nearly every step. The gaps are narrow but real: the terminal `gh issue create` step lacks concrete flags, and the workflows define no failure paths (dedup hit, auth failure mid-flow, submission error).

Suggestions

Give `gh issue create` its full form (e.g., `gh issue create --repo CherryHQ/cherry-studio --title "…" --body-file <tmp> --template ...`) so the final, irreversible step is as specified as the search step.

Define the dedup-hit branch (existing open issue found — append a 👍/subscribe and link it to the user instead of filing a duplicate), since the 查重 step currently has no defined outcome.

Add one line for failure recovery: what to do when `gh issue create` errors (fall back to 本地模式 and mark 待提交).

DimensionReasoningScore

Conciseness

Every line is operational instruction — commands, paths, a compact archive template, and terse guardrails ("提交前必须用户确认", "脱敏日志中 token/key") with zero concept explanation. Nothing explains what GitHub or an issue tracker is; every token earns its place, matching the lean anchor-5 example.

5 / 5

Actionability

Concrete, runnable commands throughout ("gh auth status 2>&1", "gh search issues \"[关键词]\" --repo CherryHQ/cherry-studio --state open --limit 5", template paths, copy-ready markdown archive block). Falls short of 5 because "gh issue create" is given bare with no --title/--body/--template/--repo flags, and the 预览 (preview) step has no specified format, leaving the most important step the least specified.

4 / 5

Workflow Clarity

Both GitHub-mode flows are clearly arrow-sequenced (收集→查重→读模板→预览→确认→提交→告知链接) with an explicit user-confirmation checkpoint, and the batch flow includes per-item dedup, preview, confirm and status update ("逐个查重预览确认→更新状态为「已提交 #号」"), so batch validation is present rather than missing. Not 5 because there is no error-recovery handling (e.g., what to do when gh auth fails mid-batch or create errors) and the dedup-hit path (existing issue found) is undefined.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, needs no external reference files (verified: no references/, scripts/, or assets/ bundle exists), and is cleanly organized into 触发边界 / 检测 GitHub 登录 / GitHub 模式 / 本地模式 / 注意 sections. Per the simple-skill guideline this is the well-organized-sections case that scores 5.

5 / 5

Total

18

/

20

Passed

Description

86%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 trigger-focused description with excellent negative-trigger boundary engineering and natural phrasing that minimizes conflict with the sibling cherry-studio-feedback skill. Its one weakness is that the skill's actual capabilities are never stated — the reader learns when it fires, but must infer what it does.

Suggestions

Open with a short third-person capability statement (e.g., submits bug reports and feature requests to the CherryHQ/cherry-studio GitHub repo, with dedup search and template filling) so the 'what' is explicit, not inferred from triggers.

Mention the local-archive fallback (.cherry-assistant/*.md) and the offline flow in one clause, so users without GitHub auth know the skill still applies.

DimensionReasoningScore

Specificity

Names several concrete actions and objects ("提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request", "改用 cherry-studio-feedback 并默认提交飞书") but describes the skill almost entirely through trigger conditions, leaving its actual capabilities (dedup search, template reading, local archiving) unstated. Not 5 because action coverage is not comprehensive; not 3 because more than 1-2 concrete actions are named.

4 / 5

Completeness

The "when" is explicit and strong ("只在用户明确要求…时使用", plus a full negative-trigger list), but the "what" is only implied by the trigger objects — the description never states what the skill does once triggered. Anchor 4 (both present, one less explicit) fits better than 5, which requires both stated explicitly; better than 3, where 'when' would be missing or weakly implied.

4 / 5

Trigger Term Quality

Comprehensive natural user phrases both positive ("提交 GitHub Issue", "GitHub Bug Report", "GitHub Feature Request") and negative ("提交问题", "提交反馈", "上报 bug", "这是个 bug", feature suggestions without naming GitHub). This is exactly the anchor-5 pattern of full natural-term coverage including synonymous variants, written from the user's mouth.

5 / 5

Distinctiveness Conflict Risk

The description is built around an explicit boundary against a sibling skill ("必须改用 cherry-studio-feedback") with a list of phrases that must NOT trigger it, eliminating overlap risk. Clear niche with distinct triggers — a textbook anchor-5 match; anchor 4 (minor overlap risk) understates the explicit disambiguation.

5 / 5

Total

18

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
CherryHQ/cherry-studio
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.