manage-ccv-projects

The core responsibility of the cc-viewer IM: helping users manage the ccv projects on this server. Whether the user asks "what can you do / how can you help me", or "list / what projects are there", "which ccv have been started", "which projects are running", "start / open / spin up project X for me", "give me an address I can open on my phone / LAN", or even just says "hi / hello" as a plain greeting without any concrete request, you should use this skill (on a greeting, proactively introduce yourself and tell the user what you can do). As long as a message touches on viewing, starting, or getting access addresses for ccv projects, or is just small talk, route it here first—this is the IM's actual job; don't sidestep it and improvise on your own.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

82%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 well-structured, highly actionable skill body that delegates mechanical logic to a companion script and gives crisp success/failure handling. The main gaps are minor verbosity in the boundaries section and a referenced script that is missing from the bundle.

Suggestions

Ship the referenced 'scripts/ccv-projects.mjs' (or correct the path) so the progressive-disclosure pointer resolves to a real file.

De-duplicate the 'forward the address verbatim / no small talk' guidance between Capability Two and Reply Style to tighten conciseness.

Add a short validate step for the start workflow (e.g., confirm the address is reachable) to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no explaining what node/ccv is), with concrete command blocks; minor over-explanation such as restating 'no small talk, no explanation' across the start section and the Reply Style boundaries.	4 / 5
Actionability	Fully executable, copy-paste-ready commands ('node scripts/ccv-projects.mjs <list\|probe\|start> [dir]') with per-subcommand usage, exact output formats ('name ⇥ path ⇥ last used time'), and a verbatim address example.	5 / 5
Workflow Clarity	Clear sequence with explicit checkpoints (already-running reuse, success = one address line, failure = non-zero exit / read stderr) and enumerated error cases; not a 5 because there is no explicit validate-fix-retry loop, though the operation is not destructive/batch so the cap does not apply.	4 / 5
Progressive Disclosure	Well-organized into Capability One/Two/Three and Reply Style sections with a clear companion-script pointer, but the referenced 'scripts/ccv-projects.mjs' is not present in the bundle and no references/ files exist, so navigation is asserted but not fully realized.	4 / 5
	Total	17 / 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 strong, trigger-rich description that clearly scopes the skill's purpose and routing, with excellent natural-language trigger coverage. Its main weakness is second-person voice throughout, which the rubric penalizes, and a slight over-capture of generic greetings.

Suggestions

Rewrite the description in third person ('Manages ccv projects... Use when the user asks to list, start, or get a LAN/phone address for a ccv project') to remove the second-person penalty.

Tighten the greeting capture so it does not appear to claim all small talk; scope it to greetings within the cc-viewer IM context.

Trim redundant restating of the routing directive to reduce length without losing trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('list the projects that have been started, start a specified project on demand, and hand the user an address'), but is penalized one level for pervasive second-person voice ('you should use this skill', 'tell the user what you can do') which the rubric docks from specificity.	3 / 5
Completeness	Explicitly answers both what (manage ccv projects: list, start, get LAN/phone address) and when, with concrete trigger phrases and an explicit routing directive ('route it here first', 'you should use this skill').	5 / 5
Trigger Term Quality	Comprehensive coverage of natural phrases users actually say, including synonyms: 'what can you do / how can you help me', 'list / what projects are there', 'which projects are running', 'start / open / spin up project X', 'give me an address I can open on my phone / LAN', plus 'hi / hello'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (cc-viewer IM ccv project management on this server) with distinct triggers and minimal conflict risk, but capturing plain greetings/small talk ('hi / hello') creates minor overlap with general assistant handling.	4 / 5
	Total	17 / 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
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: weiesky/cc-viewer
Path: server/imSkills/en/manage-ccv-projects/SKILL.md
Commit: 817dc87

Reviewed: 9 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.