CtrlK
BlogDocsLog inGet started
Tessl Logo

manage-ccv-projects

التعريف الأساسي لمسؤولية IM في cc-viewer: مساعدة المستخدم على إدارة مشاريع ccv على هذا الخادم. سواء سأل المستخدم «ماذا يمكنك أن تفعل / بماذا تستطيع مساعدتي»، أو «اعرض/ما هي المشاريع المتاحة» «ما الـ ccv التي شُغّلت» «أي المشاريع قيد التشغيل» «شغّل لي مشروع X / افتحه / ابدأ تشغيله» «أعطني عنوانًا يمكن فتحه على الهاتف/الشبكة المحلية»، أو حتى مجرد «hi / hello / مرحبا / السلام عليكم / أهلا» كتحية بسيطة دون طلب محدد، فينبغي في كل هذه الحالات استخدام هذه المهارة (عند التحية بادر بالتعريف عن نفسك وأخبر المستخدم بما يمكنك فعله). ما دامت الرسالة تتعلق بعرض مشاريع ccv أو تشغيلها أو الحصول على عنوان وصول، أو كانت مجرد تحية ومجاملة، فاسلك هذا الطريق أولًا — فهذا هو العمل الأصلي لـ IM، لا تتجاوزه لتُبدِع من تلقاء نفسك.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

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.

An actionable, well-sequenced body with concrete commands and clear error handling. Its weak spots are mild repetition that hurts conciseness and a progressive-disclosure defect: a referenced script that is missing and an undocumented subcommand.

Suggestions

Ship the referenced `scripts/ccv-projects.mjs` so the bundle path actually resolves, or remove the reference if the logic is intended to be inline.

Document the `probe` subcommand shown in the usage line (`<list|probe|start>`) in its own capability section, or drop it from the synopsis.

Consolidate the repeated «single address line / never fabricate an address» rules into one place to tighten the body.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands and no extraneous concept explanations, but it repeats the same UX constraints («лише один рядок з адресою», «не вигадуй адресу») across «Можливість два» and «Стиль відповіді та межі», and «Можливість три» re-expands trigger cases already in the description, so it could be tightened.

2 / 3

Actionability

Provides fully executable, copy-paste commands (`node scripts/ccv-projects.mjs <list|probe|start> [dir]`, `list`, `start <dir>`) with concrete output format and explicit success/failure handling.

3 / 3

Workflow Clarity

The start workflow is a clear sequence — determine directory, run `start`, branch on success (return the single address line) vs. failure (read stderr, explain, list common cases) — with error-recovery guidance and validation delegated to the script's readiness check; not a destructive/batch operation, so no cap applies.

3 / 3

Progressive Disclosure

Well-organized into clearly labeled one-level sections and a single one-level-deep reference, but the referenced bundle `scripts/ccv-projects.mjs` does not exist on disk (no scripts/ directory) and the `probe` subcommand in the usage line is undocumented in any capability section.

2 / 3

Total

10

/

12

Passed

Description

90%

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, trigger-rich description that clearly states both capability and invocation conditions with natural user phrasings. Its only structural flaw is second-person directive voice, which the rubric penalizes on specificity.

Suggestions

Rewrite the description in third person (e.g., «Helps the user manage ccv projects…») and move the second-person directives («не обходь», «відрекомендуйся») into the body to avoid the voice penalty.

Consider narrowing the bare-greeting trigger so the skill does not claim every «hi/hello», reducing conflict risk with a general assistant.

DimensionReasoningScore

Specificity

Names multiple concrete actions («покажи / які є проєкти», «запусти / відкрий / підніми мені проєкт X», «дай мені адресу»), which is a 3, but the second-person directive voice («не обходь її», «сам відрекомендуйся й розкажи, що вмієш») triggers the −1 voice penalty per the guidelines.

2 / 3

Completeness

Explicitly answers both what (help manage ccv projects: list, start, give accessible address) and when, with an explicit «Use when...»-equivalent enumeration of triggering situations including bare greetings.

3 / 3

Trigger Term Quality

Excellent coverage of natural phrasings a user would actually say: «що ти вмієш / чим можеш допомогти», «які ccv запускалися», «запусти / відкрий / підніми мені проєкт X», «дай мені адресу», plus greetings «hi / hello / привіт / вітаю / ти тут?».

3 / 3

Distinctiveness Conflict Risk

A clear niche — ccv project management on this server — with triggers tightly bound to ccv concepts; unlikely to fire for unrelated skills, though the bare-greeting trigger is a mild, non-distinctive edge.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
weiesky/cc-viewer
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.