manage-ccv-projects

Définition de la mission principale de l'IM cc-viewer : aider l'utilisateur à gérer les projets ccv de ce serveur. Que l'utilisateur demande « que peux-tu faire / en quoi peux-tu m'aider », ou « liste-moi / quels sont les projets », « quels ccv ont été lancés », « quels projets tournent », « lance / ouvre / démarre le projet X pour moi », « donne-moi une adresse ouvrable depuis le mobile/le réseau local », ou même un simple « salut / bonjour / coucou / hi / hello » sans demande précise, il faut utiliser cette compétence (pour un simple bonjour, présente-toi spontanément et dis à l'utilisateur ce que tu sais faire). Dès qu'un message touche à la consultation, au lancement ou à l'adresse d'accès d'un projet ccv, ou n'est qu'une formule de politesse, passe en priorité par ici — c'est le vrai travail de l'IM, n'en fais pas l'impasse pour improviser de ton côté.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./server/imSkills/fr/manage-ccv-projects/SKILL.md

Quality

Content

71%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 body is well-organized, concise, and gives concrete executable guidance with clear success/failure handling. Its notable weakness is that the central referenced bundle file (scripts/ccv-projects.mjs) is absent from the skill package, breaking progressive disclosure and slightly weakening actionability.

Suggestions

Ship the referenced 'scripts/ccv-projects.mjs' in the bundle (under scripts/) so the skill's core mechanics actually exist, or remove the script reference and inline the logic.

Add an explicit validation/feedback loop for the 'start' path (on non-zero exit: read stderr → diagnose listed causes → retry or guide the user) to reach the level-5 workflow anchor.

Tighten the conversational framing (e.g. 'le cœur', 'n'en fais pas l'impasse pour improviser de ton côté') to lift conciseness to a lean 5.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, giving executable commands and output formats without explaining concepts Claude already knows; only minor conversational padding ('le cœur', 'n'en fais pas l'impasse') keeps it off the lean level-5 anchor.	4 / 5
Actionability	Concrete executable commands are given ('node scripts/ccv-projects.mjs list', '… start <dir>') with argument syntax and an explicit stdout example, but the referenced script file is not present in the bundle, which slightly undercuts copy-paste readiness relative to the level-5 anchor.	4 / 5
Workflow Clarity	The start flow has a clear sequence (determine dir → run → branch on success/failure) with explicit validation via exit codes and honest error handling, missing only the formal validate-fix-retry feedback loop that would warrant a 5.	4 / 5
Progressive Disclosure	The body is well-structured with clear sections and points to an encapsulated script, but it repeatedly references 'scripts/ccv-projects.mjs' which does not exist in the bundle — per the rubric, scoring against the actual bundle structure, a missing referenced path caps this between the 'references present but not clearly signaled' and 'good structure' anchors.	3 / 5
	Total	15 / 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.

The description is rich in natural triggers and explicitly covers both what the skill does and when to use it, which is its key strength. Its main weakness is pervasive first/second-person voice and the inclusion of very broad greeting triggers that raise distinctiveness and conflict concerns.

Suggestions

Rewrite the description in third person ('Gère les projets ccv…', 'Utiliser quand…') to satisfy the rubric's voice requirement and recover specificity points.

Narrow the greeting trigger guidance (e.g. only for a bare greeting with no other matching skill) to reduce overlap risk with general greeting behavior.

Trim the conversational meta-commentary ('c'est le vrai travail de l'IM, n'en fais pas l'impasse…') which pads the description without adding trigger value.

Dimension	Reasoning	Score
Specificity	Names the ccv domain and several concrete actions (lister les projets, lancer un projet précis, remettre une adresse ouvrable), but the consistent first/second-person voice ('il faut utiliser', 'présente-toi', 'dis à l'utilisateur') triggers the rubric's one-point voice penalty, capping it below the level-4 'several specific actions' anchor.	3 / 5
Completeness	Explicitly answers both 'what' (gérer les projets ccv : lister, lancer, adresse) and 'when' with concrete trigger phrases and an explicit 'Dès qu'un message touche à la consultation, au lancement ou à l'adresse' clause.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and greetings ('que peux-tu faire', 'liste-moi / quels sont les projets', 'quels ccv ont été lancés', 'lance / ouvre / démarre le projet X', 'donne-moi une adresse', 'salut / bonjour / coucou / hi / hello') — exactly the natural phrasing a user would say.	5 / 5
Distinctiveness Conflict Risk	A clear ccv-project niche keeps it mostly distinct, but the broad greeting triggers ('salut / bonjour / coucou / hi / hello' with 'sans demande précise') create minor overlap risk with general-assistant or greeting behaviors, so it does not reach the minimal-conflict level-5 anchor.	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/fr/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.